E2e Test

---
name: e2e-test
description: '[Testing] Use when generating, updating, or maintaining E2E tests from recordings, specs, or code changes.'
---

> Codex compatibility note:
> - Invoke repository skills with `$skill-name` in Codex; this mirrored copy rewrites legacy Claude `/skill-name` references.
> - Task tracker mandate: BEFORE executing any workflow or skill step, create/update task tracking for all steps and keep it synchronized as progress changes.
> - User-question prompts mean to ask the user directly in Codex.
> - Ignore Claude-specific mode-switch instructions when they appear.
> - Strict execution contract: when a user explicitly invokes a skill, execute that skill protocol as written.
> - Subagent authorization: when a skill is user-invoked or AI-detected and its protocol requires subagents, that skill activation authorizes use of the required `spawn_agent` subagent(s) for that task.
> - Do not skip, reorder, or merge protocol steps unless the user explicitly approves the deviation first.
> - For workflow skills, execute each listed child-skill step explicitly and report step-by-step evidence.
> - If a required step/tool cannot run in this environment, stop and ask the user before adapting.
<!-- CODEX:PROJECT-REFERENCE-LOADING:START -->
## Codex Project-Reference Loading (Hook-Independent)

Claude and Codex use static project-reference loading as the authority; hooks may accelerate discovery but never replace the explicit read.
When coding, planning, debugging, testing, or reviewing, open project docs explicitly using this routing.

**Always read:**
- `docs/project-config.json` (project-specific paths, commands, modules, and workflow/test settings)
- `docs/project-reference/docs-index-reference.md` (routes to the full `docs/project-reference/*` catalog)
- `docs/project-reference/lessons.md` (always-on guardrails and anti-patterns)

**Missing/stale context route:** If `docs/project-config.json`, the docs index, `lessons.md`, `CLAUDE.md`, `AGENTS.md`, or any task-required reference doc is missing or stale, auto-run `$project-init` or the narrow setup route (`$project-config`, `$docs-init`, `$scan-all`, `$scan --target=<key>`, `$claude-md-init`) before ordinary project-specific work. If Codex mirrors or `AGENTS.md` are missing/stale, ask the user to run `$sync-codex`; do not auto-run it.

**Situation-based docs:**
- Project structure/architecture/tech-stack/deployment/setup (any layer — backend, frontend, or infra): `project-structure-reference.md`
- Backend/CQRS/API/domain/entity changes: `backend-patterns-reference.md`, `domain-entities-reference.md`
- Frontend/UI/styling/design-system: `frontend-patterns-reference.md`, `scss-styling-guide.md`, `design-system/README.md`
- Spec authoring, `docs/specs/` pathing, or TC format: `feature-spec-reference.md`, `spec-system-reference.md`, `spec-principles.md`
- Behavior/public-contract changes or spec-test-code sync: `workflow-spec-test-code-cycle-reference.md` plus the spec docs above
- Derived spec indexes/ERDs/reimplementation guides: `spec-system-reference.md` and source Feature Specs under `docs/specs/`
- Integration test implementation/review: `integration-test-reference.md`
- E2E test implementation/review: `e2e-test-reference.md`
- Code review/audit work: `code-review-rules.md` plus domain docs above based on changed files

Do not read all docs blindly. Start from `docs-index-reference.md`, then open only relevant files for the task.
<!-- CODEX:PROJECT-REFERENCE-LOADING:END -->

<!-- PROMPT-ENHANCE:STEP-TASK-ANCHOR:START -->

> **[BLOCKING]** Execute skill steps in declared order. NEVER skip, reorder, or merge steps without explicit user approval.
> **[BLOCKING]** Before each step or sub-skill call, update task tracking: set `in_progress` when step starts, set `completed` when step ends.
> **[BLOCKING]** Every completed/skipped step MUST include brief evidence or explicit skip reason.
> **[BLOCKING]** If Task tools are unavailable, create and maintain an equivalent step-by-step plan tracker with the same status transitions.

<!-- PROMPT-ENHANCE:STEP-TASK-ANCHOR:END -->

## Quick Summary

**Goal:** Produce maintainable, spec-traceable E2E tests (`TC-{MODULE}-E2E-{NNN}`) from recordings, specs, or code changes with the project's configured framework (Playwright, Selenium, Cypress, or another), protecting business behavior so cosmetic UI changes do not break tests and intended behavior breaks do.

**Summary:**
- **Testability contract:** resolve Unit/Integration/System/E2E applicability from runner/config evidence; record owner/root/data, copy-ready full + focused commands, zero-match behavior, CI/simple-Windows entry, unique run/data identity, and repeat proof; unresolved applicable fields block handoff, while non-applicable tiers require evidence-backed `N/A`.

- **Purpose:** turn recordings/specs/code changes into maintainable, spec-traceable E2E tests that break ONLY when intended business behavior breaks — never on cosmetic UI churn.
- **Main steps (in order):** (1) detect the E2E framework from project files; (2) read `docs/project-reference/e2e-test-reference.md` + the `e2eTesting` block of `docs/project-config.json` FIRST — never assume a stack or invent a TC-annotation marker; (3) load `TC-{MODULE}-E2E-{NNN}` specs from `docs/specs/`; (4) pass the Real-World Fidelity Gate BEFORE writing test code — can this flow, timing, and data actually occur in production?; (5) generate/update tests via Page Object Model (spawn the `e2e-runner` sub-agent); (6) run tests with the project's configured command; (7) update `e2e-test-reference.md` with learnings.
- Every test carries its `TC-{MODULE}-E2E-{NNN}` code traced to the §8 invariant/behavior it guards, structured with Page Object Model (locators/actions in the page class, assertions in the test).
- Selector priority semantic/BEM > data-testid > ARIA/role > visible text; AVOID generated classes, `:nth-child`, XPath.
- Generate unique self-sufficient data (GUID/timestamp); NEVER depend on pre-existing DB state, NEVER tear down seeded data; pick a workflow by asking the user directly when not already in one.

**Workflow:**

1. **Detect** — classify request scope, target artifacts, and framework from project files.
2. **Read** — **MUST ATTENTION** load the E2E reference, `e2eTesting` config, and TC specs before writing.
3. **Gate** — pass the Real-World Fidelity Gate for flow, pacing, data, and settle signals.
4. **Generate/update** — use Page Object Model and the `e2e-runner` sub-agent with TC traceability.
5. **Verify** — run the configured tests, confirm constraints and evidence, and record learnings.

**Key Rules:**

- MUST ATTENTION keep claims evidence-based (`file:line`), confidence >80% to act.
- MUST ATTENTION apply the Real-World Fidelity Gate before writing setup — a flow, pacing, or data shape production can never reach proves nothing; fix the SCENARIO, never the assertion.
- MUST ATTENTION keep task tracking updated as each step starts/completes.
- NEVER skip mandatory workflow or skill gates.

## ⚠️ MANDATORY: Read Project E2E Reference (FIRST)

**BEFORE ANY E2E WORK, you MUST ATTENTION:**

```bash
# 1. Read project-specific E2E patterns (REQUIRED)
head -100 docs/project-reference/e2e-test-reference.md

# 2. Read project config for framework, paths, commands
grep -A 50 '"e2eTesting"' docs/project-config.json

# 3. Find TC codes you need to implement
grep -r "TC-.*-E2E-" docs/specs/ docs/specs/
```

**The `e2eTesting` section in `docs/project-config.json` contains:**

- Framework, language, paths, run commands, TC code format
- Project-specific best practices and entry points

**When investigating/fixing E2E failures, update `docs/project-reference/e2e-test-reference.md` with learnings.**

- `docs/project-reference/domain-entities-reference.md` — Domain entity catalog, relationships, cross-service sync (read when task involves business entities/models)

---

## Framework Detection (SECOND STEP)

Detect the project's E2E stack before generating tests:

```bash
# Use project config, project-reference docs, and existing test config files as the source of truth
rg "playwright|cypress|selenium|webdriver|e2e" docs/project-config.json docs/project-reference/ . 2>/dev/null
rg --files | rg "(playwright|cypress|webdriver|selenium|e2e|test).*config|manifest|project"
```

| Framework                 | Config Source               | Test Naming             | Run Command                    |
| ------------------------- | --------------------------- | ----------------------- | ------------------------------ |
| Configured E2E framework  | project config/reference docs | existing local examples | configured test command        |

## E2E Applicability and Contract Preflight (before generation)

Record E2E as `APPLICABLE` only when the project config/reference docs, an actual framework configuration, and a runnable command all provide evidence. Otherwise record `N/A — <file:line evidence>` and stop E2E generation for that project; never infer a browser project from skill-local examples. If the current repository has no runnable E2E stack, record that project-specific evidence-backed N/A in the report; do not fabricate a browser stack, page object, or E2E command.

When E2E is applicable, add the following fields to the test plan/report before generating code:

| Applicability evidence | Owner / test root | Runner/framework | Full command | Focused/partial command | Zero-match behavior | Run identity / data mode | Parallel isolation | Simple/Windows entry point |
| ---------------------- | ----------------- | ---------------- | ------------ | ------------------------ | ------------------- | ------------------------ | ------------------ | --------------------------- |
| `{file:line}` | `{owner}` / `{path}` | `{configured stack}` | `{copy-ready command}` | `{copy-ready command or N/A + evidence}` | `{documented non-zero behavior}` | `{unique identity; reference/additive mode}` | `{worker/root strategy}` | `{entry point or N/A + evidence}` |

- Use only configured browser/service commands. A focused selection must be copy-ready and invalid or zero-match selections must fail or follow the runner's documented non-green behavior; never report zero matches as a passing scope.
- Generate unique self-sufficient data through supported public paths. Reference data is count-before-create, idempotent, and restart-safe; intentional persistent data is keyed and additive. Preserve realistic actor pacing and arrange barriers, and isolate mutable data across parallel workers.
- If the configured stack has persistent state, capture exact Passed/Failed/Skipped counts and exit status for each applicable focused/full scope and require two consecutive no-reset full runs. If no runnable E2E stack exists, report the evidence-backed N/A instead of substituting generic browser tooling.

---

## Workflow Modes

| Mode             | Input                      | Output                       |
| ---------------- | -------------------------- | ---------------------------- |
| `from-recording` | Recording JSON + feature   | Test spec + page object      |
| `update-ui`      | Git diff of UI changes     | Candidate evidence plus an explicit acceptance decision; accepted baseline changes only after approval |
| `from-changes`   | Changed test specs or code | Updated test implementations |
| `from-spec`      | TC codes from test specs   | New tests matching specs     |

---

## Visual Expectation Transition Gate

For `update-ui`, screenshot or visual output is candidate evidence until it has
been opened, inspected, compared with the intended purpose, and linked to an
explicit `HUMAN-ACCEPTED` record through `$experience-review`. Do not call
`--update-snapshots`, replace visual fixtures, or rewrite another expected
output merely because the new run passes or the generated evidence looks
plausible. Preserve the previous accepted expectation and classify a mismatch
as a potential regression, intended change pending acceptance, invalid test
condition, environment block, unverified, or ambiguous. Full contract:
`SYNC:experience-acceptance-contract`.

---

## First Principle — Easy to Change

> **The success metric of every coding decision is _future change cost_.**
> DRY, SRP, abstraction, design patterns, naming, layering, tests — every
> technique exists to serve one goal: **making the next change cheaper**.

Evaluating code, refactor, test, abstraction, ask:
**does this make next change cheaper or more expensive?**

- Reject "best practices" raising change cost (premature abstraction, speculative generality, leaky indirection, ceremony without payoff).
- Name real enemies in findings: **coupling, hidden state, duplicated knowledge, unclear intent, irreversible decisions exposed too early**.
- Simpler design easy to change beats sophisticated design that isn't.

Apply this lens **before** invoking any specific rule, pattern, checklist below — if downstream rule would raise change cost, this principle wins.

---

## Core Principles

### 1. TC Code Traceability (MANDATORY)

**Every E2E test MUST ATTENTION have:**

- TC code in test name: `TC-{MODULE}-E2E-{NNN}`
- Tag/annotation linking to spec
- Comment linking to feature doc

```typescript
// TypeScript
test('TC-RT-E2E-001: Submit return request', async () => { ... });
```

Use repository's configured test-case annotation mechanism for non-TypeScript E2E tests; NEVER invent a framework-specific marker.

> **Spec-Loop Discipline (E2E tier — tailored).** Trace each E2E scenario to the **§8 invariant/behavior it guards** — name the protected business rule, not just the click path — so the scenario fails only when that intended behavior breaks (not on cosmetic UI churn). Any coverage gap you find (an §8 behavior with no E2E scenario, or an E2E flow guarding no documented behavior) feeds the **Dual-Feedback** half into BOTH the spec (the missing/changed behavior) AND the tests — never a test-only fix. **Scoped N/A:** property/metamorphic generation and the MUTATION-SCORE assertion gate are scoped to unit/integration core-logic; they do NOT apply at the E2E tier — do not force them here.

### 2. Page Object Model

All frameworks use Page Object pattern:

- Encapsulate page locators in page class
- Methods represent user actions
- Assertions in test file, not page object

### 3. Selector Strategy (Priority Order)

1. **Semantic classes** — BEM (`.block__element`), component classes
2. **Data attributes** — `[data-testid]`, `[data-cy]`, `[data-test]`
3. **ARIA/Role** — `role=button`, `aria-label`
4. **Text content** — Visible user text (last resort)

**AVOID:** Generated classes (`.ng-star-inserted`, `.MuiButton-root`), positional selectors (`:nth-child`), XPath

### 4. Unique Test Data

Tests MUST generate unique data to be repeatable:

- Append GUIDs/timestamps to test data
- Make each test self-sufficient with own generated data; NEVER depend on specific pre-existing database state
- Leave seeded data in place after run, NEVER clean up — why: teardown across shared runs creates side effects for parallel/repeat tests

### 5. Preconditions Documentation

Document what must exist before test runs:

- System: Infrastructure running, APIs healthy
- Data: Seed data exists (users, companies)
- Feature: Configurations complete

---

## Steps

1. **Detect framework** from project files
2. **Read project E2E docs** for conventions and patterns
3. **Load test specs** with TC codes from feature docs
4. **Check real-world fidelity** — BEFORE any test code is written, answer *"Can this flow, timing, and data actually occur in production?"* State the real pacing between consecutive user actions (a user does not submit two distinct actions in the same millisecond) and, for each gap, the observable settle signal the next step waits on (rendered confirmation, persisted state change, audit/version stamp, request/worker idle marker). Any "no" → fix the SCENARIO, never the assertion. Full contract: `SYNC:real-world-fidelity-testing` below.
5. **Generate/update tests** following Page Object pattern
6. **Run tests** using project's configured commands
7. **Update e2e-test-reference.md** with any learnings

---

## Output

Report:

- Files created/modified
- TC codes covered
- Run command to execute tests (configured full command)
- E2E applicability and evidence (`APPLICABLE` or `N/A — <file:line evidence>`)
- Full and focused/partial commands, zero-match behavior, and simple/Windows entry point (or evidence-backed N/A)
- Run identity, reference/additive data mode, parallel-isolation strategy, and exact Passed/Failed/Skipped counts + exit status for each executed scope
- Repeat evidence: two consecutive no-reset full runs when persistent state is applicable
- Any preconditions or setup needed

---

## Sub-Agent Type Override

> **MANDATORY:** E2E test generation and accepted baseline updates spawn `e2e-runner` sub-agent (`agent_type: "e2e-runner"`), NOT the main agent directly. Baseline updates remain forbidden until the experience-acceptance gate is satisfied.
> **Rationale:** `e2e-runner` auto-detects the project's E2E stack, maintains test-to-spec TC traceability, and handles visual baseline updates across Playwright, Selenium, Cypress, and other frameworks.

Spawn `e2e-runner` sub-agent for:

- Generating new E2E tests from recordings or TC codes from specs
- Updating visual screenshot baselines after UI changes, but only after an explicit accepted experience record
- Maintaining TC code traceability (`TC-{MODULE}-E2E-{NNN}`) in test implementations

---

## Workflow Recommendation

> **MANDATORY IMPORTANT MUST ATTENTION — NO EXCEPTIONS:** If you are NOT already in a workflow, you MUST ATTENTION use ask the user directly to ask the user. Do NOT judge task complexity or decide this is "simple enough to skip" — the user decides whether to use a workflow, not you:
>
> 1. **Activate `e2e --source=changes` workflow** (Recommended) — investigate → e2e-test → test → watzup
> 2. **Execute `$e2e-test` directly** — run this skill standalone

---

# Skill: e2e-test

**Category:** [Testing]
**Trigger:** e2e test, e2e from recording, generate e2e, playwright test, cypress test, selenium test, webdriver, puppeteer

Generate and maintain E2E tests using project's configured testing framework.

- `docs/specs/` — Test specifications by module (read existing TCs for E2E scenario coverage; match TC codes to E2E test implementations)

**Be skeptical. Apply critical thinking, sequential thinking. Every claim needs traced proof, confidence percentages (Idea should be more than 80%).**

---

<!-- SYNC:sub-agent-selection -->

> **Sub-Agent Selection** — Full routing contract: `.claude/skills/shared/sub-agent-selection-guide.md`
> **Rule:** Route specialized domains (architecture, security, performance, DB, E2E, integration-test, git) to the matching specialist agent (see guide above) — NEVER use `code-reviewer` for these. — why: `code-reviewer` lacks each domain's checklist, so specialized issues slip through.

<!-- /SYNC:sub-agent-selection -->

<!-- SYNC:source-test-drift-check -->

> **Source/test drift check.** For coding, fix, debug, investigation, test, or review work: when source behavior changes, inspect affected unit/integration/E2E tests and decide from evidence whether tests should change to match intended behavior or the source change is an unintended bug to fix. Do not write tests for migration code; schema/data migrations are one-time execution paths, not core application logic.

<!-- /SYNC:source-test-drift-check -->

<!-- SYNC:real-world-fidelity-testing -->

> **Real-World Fidelity Gate** — MANDATORY when authoring, reviewing, or repairing any integration / E2E / system test.
>
> A test earns trust by reproducing a situation the system can actually meet in production. A scenario that could never occur in real life proves nothing when it passes, and wastes hours when it fails.
>
> 1. **Ask the fidelity question BEFORE writing the setup:** *"Can this sequence, timing, and data actually occur in production?"* If no, the test is mis-specified — fix the SCENARIO, never the assertion.
> 2. **Model real pacing between actor steps.** Two distinct actor actions that production separates by seconds, minutes, or hours MUST NOT be fired back-to-back in the same millisecond. Compressed pacing manufactures races the system was never designed to survive, then reports them as product defects.
> 3. **Wait on a real signal, never a blind sleep.** Find an observable proving the prior step finished — a persisted state change, an audit/version stamp, a queue/worker idle marker, a completion event — and poll until it settles (unchanged across a short stability window). Use a fixed delay ONLY when no observable exists, and say so in a comment.
> 4. **Barriers belong in ARRANGE, never in ASSERT.** Waiting for a precondition is fidelity. Widening an assertion's timeout, loosening a comparison, adding a retry around a failing assertion, or skipping the test is masking. NEVER do the latter to force green.
> 5. **Distinguish harness-amplified from real.** Test topologies (shared infra, fan-out consumers, parallel suites, cold starts) can make a rare production race routine locally. Before filing a product defect, state whether the trigger exists in production and at what likelihood.
> 6. **Keep the protected invariant intact.** Improving fidelity must NEVER reduce what the test protects. If a realistic scenario no longer exercises the rule, the rule needs a DIFFERENT realistic scenario — not a weaker assertion.
> 7. **Deliberate impossible-state tests are allowed, but MUST be labelled.** Corruption-repair, migration, and fail-safe tests intentionally construct states production should never reach; comment WHY the state is reachable (upstream bug, partial write, legacy data), so they are never confused with unrealistic setups.

<!-- /SYNC:real-world-fidelity-testing -->

<!-- SYNC:test-failure-fault-adjudication -->

> **Test-Failure Fault Adjudication** — When a test fails (or you are debugging or fixing a failure), the job is to determine *who is at fault — the source code or the test code*. Getting that verdict right matters more than turning the suite green. Binds every debug / fix / test skill identically.
>
> 1. **Provisional verdict before touching either side.** Classify the observed evidence as SOURCE-WRONG, TEST-WRONG, TEST-NOT-OPTIMAL, ENVIRONMENT-BLOCKED, or AMBIGUOUS; then `$debug-investigate` and trace end-to-start before editing. A green-again suite is NOT the goal.
> 2. **Triangulate against the spec AND the source.** If a governing Feature Spec covers the behavior (e.g. `docs/specs/**` — §3 ACs / §4 BRs / §5 invariants / §8 TCs), it is the tiebreaker for *intended* behavior — compare BOTH the production source and the failing test against it. With no spec, the documented intent / acceptance criteria / caller contract is the reference. Decide from this evidence whether the SOURCE is wrong or the TEST is wrong.
> 3. **Classify who is at fault, then fix the wrong side at its root:**
>     - **SOURCE-WRONG** — production code violates the spec's intended behavior or a clear invariant → fix the source at the owning layer; keep or strengthen the test that caught it.
>     - **TEST-WRONG** — the test encodes a stale or incorrect assertion, setup, or expectation that contradicts intended behavior → fix the test at its root. NEVER weaken an assertion, add a skip, or relax a timeout to force green.
>     - **TEST-NOT-OPTIMAL** — intended behavior is valid but the test seam, timing, or assertion signal is fragile → improve the test without weakening the invariant.
>     - **ENVIRONMENT-BLOCKED** — infrastructure or external state prevents a source/test verdict → preserve diagnostics and stop mutation until the environment is healthy.
>     - **AMBIGUOUS** — evidence or intended behavior does not safely select an owner → ask the user or canonical owner before editing.
>     - NEVER change a test to match broken source, and NEVER change source to satisfy a broken test. (Migration code excluded — schema/data migrations are one-time execution paths, not core application logic.)
> 4. **Ask the user when intended behavior is unclear.** If no spec covers the behavior, the spec is silent, or the spec is ambiguous about which side is correct, STOP and ask the user directly (or consult the canonical spec owner) before editing either side — never silently pick source or test just to make the suite pass.
>
> Reconcile to intended behavior, never to whichever side currently passes — green can encode the very bug.
>
> **Read-only/report-only role boundary:** when this block is carried by a report-only role (`code-reviewer`, `quality-gate-review`, `spec-compliance-reviewer`, `tester`, and any other agent whose definition declares it never edits source), "fix the wrong side" means RETURN the adjudicated verdict and the proposed repair to the parent — do not modify source, tests, generated carriers, or user data. The adjudication is the deliverable; the edit is the caller's. Without this sentence the block's step-3 imperatives read as write authority and directly contradict those agents' own declarations (e.g. `tester.md` "NEVER implement fixes"), which is the sibling `SYNC:double-round-trip-review` boundary applied to the same class of carrier.

<!-- /SYNC:test-failure-fault-adjudication -->

<!-- SYNC:ai-mistake-prevention -->

> **AI Mistake Prevention** — Failure modes to avoid on every task:
>
> **Re-read files after context changes.** Context compaction, resume, or long-running work can make memory stale; verify current files before acting.
> **Verify generated content against source evidence.** AI hallucinates APIs, names, claims, and document facts. Check the relevant source before documenting or referencing.
> **Check downstream references before deleting or renaming.** Removing an artifact can stale docs, generated mirrors, configs, and callers; map references first.
> **Trace the full impact chain after edits.** Changing a definition can miss derived outputs and consumers. Follow the affected chain before declaring done.
> **Verify ALL affected outputs, not just the first.** One green check is not all green checks; validate every output surface the change can affect.
> **Assume existing values are intentional — ask WHY before changing OR flagging one as a defect.** Before changing or reporting a constant, limit, flag, cutoff, wording, or pattern, read nearby context and history, the CALLER's ordering, and 2+ sibling call sites of the same convention. A doc stating WHAT without WHY is missing rationale, not proof of a missing guard.
> **Surface ambiguity before acting — don't pick silently.** Multiple valid interpretations require an explicit question or stated assumption with risk.
> **Assert the outcome your system owns, not the intermediate state your infrastructure owns.** When verifying async work, assert the final business state — never the delivery/retry bookkeeping held in shared infrastructure that any co-running process can write. Such a check passes when run alone and flakes the moment anything else shares that infrastructure.
> **Keep shared guidance role-relevant.** Universal guidance must help every receiving skill or agent; code-specific obligations belong only in code-specific protocols.

<!-- /SYNC:ai-mistake-prevention -->

<!-- SYNC:critical-thinking-mindset -->

> **Critical Thinking Mindset** — Apply critical thinking, sequential thinking. Every claim needs traced proof, confidence >80% to act.
> **Anti-hallucination:** Never present guess as fact — cite sources for every claim, admit uncertainty freely, self-check output for errors, cross-reference independently, stay skeptical of own confidence — certainty without evidence root of all hallucination.

<!-- /SYNC:critical-thinking-mindset -->

<!-- SYNC:test-architecture-execution-contract -->

> **Test Architecture & Execution Contract** — Treat testability as a setup/architecture acceptance condition. For every potentially applicable tier — Unit, Integration/System, E2E, and Performance/Scale (warranted at `T1+`/`B2+`) — record `APPLICABLE` only with evidence of its runner/framework/configuration; otherwise record `N/A — <evidence>` and never fabricate coverage.
>
> 1. **Matrix before implementation:** Record applicability, owner, runner/framework, test root, fixture/data strategy, full command, focused/partial command, zero-match behavior, CI gate, a simple/Windows entry point (a `.cmd` when the project needs one), the **host-mode AND container-mode commands** where the project supports both, and the **environment reach** (which of local / CI / production-shaped this tier can target).
> 2. **Runnable scopes:** Full and focused commands must be copy-ready, fail on invalid or zero-match selections, report exact counts and exit status, and be safe to repeat. E2E uses only configured browser/service commands.
> 3. **Fresh valid state:** Each run/test owns a unique run identity and business-data suffix, arranges through supported public paths, and uses realistic valid data. Reference setup is count-before-create, idempotent, and restart-safe. Intentional accumulation is additive, keyed, and integrity-checked; never hide contamination with destructive reset.
>    Run-scoped cleanup, when supported, is opt-in and idempotent: after evidence capture it may remove only ephemeral resources owned by the current run; it must never delete persistent/additive data or another run's data, reset shared state, or replace no-reset proof.
> 4. **Isolation and fidelity:** Isolate mutable roots and parallel workers; share only immutable/reference data. Preserve real actor pacing and observable arrange barriers. Do not widen retries or weaken assertions to make a scenario pass.
> 5. **Evidence gate:** Report command, scope, identity, seed/accumulation mode, exact result, and repeat proof. For each applicable persistent-state suite, require two consecutive no-reset full runs. Treat line coverage as diagnostic only; use meaningful property/invariant, mutation, change, and behavior coverage signals.
> 6. **Execution modes and environment reach:** A tier claiming two run modes must have **BOTH exercised** — the bare-host command and the fully-containerized command, driven from ONE source of truth for config and topology; record which mode CI exercises, because an unexercised mode rots silently and a claimed-but-rotten mode is worse than one never claimed. The SAME suite must reach local, CI and (where warranted) a production-shaped target, **parameterized by configuration, never by forked test code** — only one fork ever stays maintained, so forking guarantees divergence. A target lacking a required capability reports `ENVIRONMENT-BLOCKED`, never a silent pass. Tests unsafe against production are excluded by an **ENFORCED** mechanism whose absence fails loudly, not by a convention someone must remember; *"runs in prod"* means a safe, declared, **NON-MUTATING** subset. Reproducibility underwrites all of it — pinned toolchain, locked dependencies, declared external prerequisites — which is the difference between a suite that passes anywhere and one that passes on its author's machine. Depth → `SYNC:engineering-foundation-gate` **F1/F2/F3**.
>
> **Ownership:** Architecture/harness defines the matrix; scaffold/workflow makes it runnable; test writers implement tier-specific cases; reviewers verify the contract; the runner reports; seed-data owners preserve uniqueness, idempotency, realism, and accumulation integrity. Missing required evidence blocks setup completion.

<!-- /SYNC:test-architecture-execution-contract -->

<!-- SYNC:critical-thinking-mindset:reminder -->

**MUST ATTENTION** apply critical + sequential thinking — every claim needs appropriate traced evidence (`file:line` for repo/code claims; source URL or artifact section for research, product, content, and docs claims); confidence >80% to act, <60% DO NOT recommend. Anti-hallucination: never present guess as fact, admit uncertainty freely, cross-reference independently, stay skeptical of own confidence.

<!-- /SYNC:critical-thinking-mindset:reminder -->

<!-- SYNC:ai-mistake-prevention:reminder -->

**MUST ATTENTION** apply AI mistake prevention — verify generated content against evidence, trace downstream references before deleting or renaming, verify all affected outputs, re-read files after context loss, and surface ambiguity before acting.

<!-- /SYNC:ai-mistake-prevention:reminder -->

<!-- PROMPT-ENHANCE:STEP-TASK-CLOSING:START -->

## Prompt-Enhance Closing Anchors

**IMPORTANT MUST ATTENTION** follow declared step order for this skill; NEVER skip, reorder, or merge steps without explicit user approval
**IMPORTANT MUST ATTENTION** for every step/sub-skill call: set `in_progress` before execution, set `completed` after execution
**IMPORTANT MUST ATTENTION** every skipped step MUST include explicit reason; every completed step MUST include concise evidence
**IMPORTANT MUST ATTENTION** if Task tools unavailable, maintain an equivalent step-by-step plan tracker with synchronized statuses

<!-- PROMPT-ENHANCE:STEP-TASK-CLOSING:END -->

<!-- SYNC:parallel-subagent-dispatch -->

> **Parallel Sub-Agent Dispatch** — Plan parallelism the moment a task breakdown exists, BEFORE executing it — running provably independent tasks sequentially wastes wall-clock. Applies to every multi-step job: workflow steps, planning, batch updates, investigation, research, scans, reviews, doc sync. **Plan execution is metadata-gated, NEVER default-parallel** — fan-out follows ONLY what the plan declares (`PAR`/`SEQ` tags + per-phase write set); an untagged plan runs sequentially — why: a derived write set cannot see cascade or generated writes.
>
> 1. **Tag every task `PAR` or `SEQ`.** `PAR` = inputs exclude every pending task's output AND write set disjoint from every other `PAR`. Else `SEQ` — MUST ATTENTION name the dependency forcing it.
> 2. **Group `PAR` into waves.** No edge between members. Two writers of one file NEVER share a wave. Read-only work (search, investigation, review, research) parallelizes freely.
> 3. **Declare before dispatch:** `Parallel plan: wave 1 = [...] · wave 2 = [...] · SEQ = [...] (reason)`.
> 4. **Spawn each wave in ONE message** — every `spawn_agent` call in one response, NEVER dripped per turn. Route each task to its specialist (`.claude/skills/shared/sub-agent-selection-guide.md`); NEVER `code-reviewer` as catch-all.
> 5. **Brief each sub-agent self-contained:** goal · scope + owned files · reference docs · return contract (summary + `Full report:` path, per SYNC:subagent-return-contract) · incremental persistence to `plans/reports/` (per SYNC:incremental-persistence).
> 6. **Barrier per wave.** Advance ONLY after EVERY member returns (a skipped conditional counts as returned). Merge, mark each task completed/skipped, THEN dispatch the next wave. Mutating steps wait for the barrier.
> 7. **One level deep.** A dispatched sub-agent executes its own brief; further fan-out stays the orchestrator's job unless that agent's `.claude/agents/*.md` definition authorizes it.
>
> **NEVER parallelize:** tasks sharing a write target · a task consuming a pending task's output · trivial single-file work (dispatch overhead > gain) · an order a skill or workflow explicitly fixes · gates awaiting user approval.
>
> **Blocked until:** MUST ATTENTION every task tagged PAR/SEQ with a named reason per SEQ · waves declared + write-set disjointness checked · each wave spawned in ONE message · barrier honored before the next wave.

<!-- /SYNC:parallel-subagent-dispatch -->

<!-- SYNC:parallel-subagent-dispatch:reminder -->

- **MANDATORY** After planning tasks, tag each PAR/SEQ and spawn every PAR wave as parallel sub-agents in ONE message — default parallel for workflows, batch updates, investigation, research, reviews; plan execution fans out ONLY on what the plan declares.
- **MANDATORY** Disjoint write sets per wave · all-return barrier before the next wave · specialist routing · sub-agents NEVER fan out further unless their own agent definition authorizes it.

<!-- /SYNC:parallel-subagent-dispatch:reminder -->

<!-- SYNC:project-protocol-overlay -->

> **Project Protocol Overlay** — Before executing this skill, resolve any PROJECT overlay rules layered onto it: match this skill's name against the `Target` column of the project's skill-protocol index (`docs/project-reference/skill-protocols-reference.md` by default; a `referenceDocs` entry in `docs/project-config.json` overrides the path), taking the most specific matching tier ONLY — exact name > glob > `*`. **That precedence orders overlays against EACH OTHER, never against this skill.** Read ONLY the matched bodies, resolved as `<protocols-dir>/<Name>.md`; a row's Body link is display text, never a read path. A matched body that is missing or malformed is REPORTED and skipped — never reconstructed from the index Description. No index, or no match -> proceed with no overlay, silently. Full contract: `.claude/skills/project-skill-protocol/references/registry.md`.
>
> Overlays are **ADDITIVE ONLY**: they ADD rules on top of this skill's own protocol and NEVER replace, override, disable, or reinterpret a rule it already states — removing every overlay must return this skill to exactly its documented behavior. An overlay is a BRIEF, not an authority escalation: it can NEVER waive a workflow gate, git discipline, a review gate, or a user-confirmation gate. A genuine overlay-vs-skill conflict, or two equally-specific overlays that directly contradict -> surface both to the user; NEVER resolve silently.

<!-- /SYNC:project-protocol-overlay -->

<!-- SYNC:project-protocol-overlay:reminder -->

**MUST ATTENTION** resolve project protocol overlays for this skill BEFORE executing — most specific matching tier only (exact > glob > `*`, which ranks overlays against each other, NEVER against this skill), read only matched bodies at `<protocols-dir>/<Name>.md`; a missing or malformed body is reported, never reconstructed. Overlays are ADDITIVE ONLY (they never replace this skill's own rules) and are a brief, NEVER an authority escalation; an equal-specificity contradiction goes to the user.

<!-- /SYNC:project-protocol-overlay:reminder -->

<!-- SYNC:test-architecture-execution-contract:reminder -->

**MUST ATTENTION** Before implementation, record evidence-backed Unit/Integration/System/E2E **and Performance/Scale** (`T1+`/`B2+`) applicability (or explicit N/A), copy-ready full + focused commands, zero-match behavior, a simple/Windows entry point, **the host-mode AND container-mode commands where both are supported, plus each tier's environment reach (local / CI / production-shaped)**, unique run identity, realistic valid data, idempotent/restart-safe reference setup, intentional additive accumulation, parallel isolation, exact results, and two no-reset full runs for each applicable persistent-state suite. **Both claimed run modes must be EXERCISED** (an unexercised mode rots; a claimed-but-rotten mode is worse than one never claimed), the same suite reaches every target **parameterized by config, never by forked test code**, a missing capability reports `ENVIRONMENT-BLOCKED` rather than passing silently, and *"runs in prod"* means a safe, declared, **NON-MUTATING** subset excluded by an enforced mechanism, not by convention.

<!-- /SYNC:test-architecture-execution-contract:reminder -->

## Closing Reminders

**IMPORTANT MUST ATTENTION** Testability contract: resolve evidence-backed Unit/Integration/System/E2E rows, copy-ready full/focused commands, zero-match failures, owner/root/data, CI/simple-Windows entry, unique run identity, and repeat proof before claiming setup, review, or test completion.
**IMPORTANT MUST ATTENTION Goal:** Produce maintainable, spec-traceable E2E tests (`TC-{MODULE}-E2E-{NNN}`) from recordings, specs, or code changes with the project's configured framework (Playwright, Selenium, Cypress, or another), protecting business behavior so cosmetic UI changes do not break tests and intended behavior breaks do.

**IMPORTANT MUST ATTENTION — Protocols in force (concise digest of the SYNC/shared blocks this skill carries):**

- **Sub-Agent Selection:** Route specialized domains to the matching specialist agent, NEVER `code-reviewer`.
- **Source/Test Drift Check:** On source change, decide from evidence whether tests or source is wrong.
- **Real-World Fidelity Gate:** only test flows, pacing, and data production can actually reach; wait on a real settle signal in ARRANGE — never a widened assertion.
- **AI Mistake Prevention:** verify generated content against evidence, trace downstream references, verify all affected outputs, re-read after context loss, surface ambiguity.
- **Critical Thinking:** Traced `file:line` proof per claim, confidence >80% to act, NEVER guess as fact.
- **Parallel Sub-Agent Dispatch:** Tag tasks PAR/SEQ, group PAR into disjoint-write-set waves, spawn each wave in ONE message, barrier before advancing.

**IMPORTANT MUST ATTENTION — Main steps (execute in order, track each):** (1) detect E2E framework from project files; (2) read `e2e-test-reference.md` + `e2eTesting` config FIRST; (3) load `TC-{MODULE}-E2E-{NNN}` specs from `docs/specs/`; (4) pass the Real-World Fidelity Gate BEFORE writing test code; (5) generate/update tests via Page Object Model through the `e2e-runner` sub-agent; (6) run tests with the configured command; (7) update `e2e-test-reference.md` with learnings — why: AI keeps dropping the skill's own step sequence under long context.
**IMPORTANT MUST ATTENTION** read `docs/project-reference/e2e-test-reference.md` + the `e2eTesting` block of `docs/project-config.json` FIRST, then detect the framework from project files — NEVER assume a stack — why: the configured framework, paths, run commands, and TC format are project-specific, not framework defaults.
**IMPORTANT MUST ATTENTION** cite `file:line` evidence for every claim (confidence >80% to act, <60% DO NOT recommend) — NEVER speculate without proof.
**MANDATORY IMPORTANT MUST ATTENTION** break work into small todo tasks using task tracking BEFORE starting; mark one `in_progress`, set `completed` immediately after each finishes; add a final review todo.
**MANDATORY IMPORTANT MUST ATTENTION** search the codebase for 3+ similar existing E2E tests/page objects before creating new code; follow the local pattern over generic framework docs — why: projects carry local selector/data conventions that differ from defaults.
**IMPORTANT MUST ATTENTION** evaluate fit before copying a nearby test — verify the new scenario shares the same base page class, fixtures, and preconditions — why: closest example ≠ matching preconditions.
**MANDATORY IMPORTANT MUST ATTENTION** every E2E test carries its `TC-{MODULE}-E2E-{NNN}` code traced to the §8 invariant/behavior it guards — name the protected business rule, not just the click path — so it fails on intended-behavior breaks, not cosmetic UI churn.
**MANDATORY IMPORTANT MUST ATTENTION** apply the Real-World Fidelity Gate BEFORE writing setup — ask "can this flow, timing, and data actually occur in production?", model real pacing between distinct user actions instead of firing them in the same millisecond, and wait on an observable settle signal in ARRANGE; NEVER widen an assertion timeout, loosen a comparison, or retry around a failing assertion to compensate — why: a scenario production can never reach proves nothing when it passes and manufactures phantom "product defects" when it fails.
**IMPORTANT MUST ATTENTION** use the repository's configured test-case annotation mechanism — NEVER invent a framework-specific marker.
**MANDATORY IMPORTANT MUST ATTENTION** selector priority semantic/BEM > data-testid > ARIA/role > visible text; NEVER use generated classes (`.ng-star-inserted`, `.MuiButton-root`), positional selectors (`:nth-child`), or XPath — why: generated/positional selectors break on unrelated markup churn.
**MANDATORY IMPORTANT MUST ATTENTION** keep locators/actions in the Page Object class, assertions in the test file — why: encapsulation keeps the next UI change a one-place edit.
**MANDATORY IMPORTANT MUST ATTENTION** generate unique self-sufficient data (GUID/timestamp); NEVER depend on specific pre-existing DB state and NEVER tear down seeded data — why: teardown across shared/parallel runs creates side effects.
**IMPORTANT MUST ATTENTION** spawn the `e2e-runner` sub-agent (`agent_type: "e2e-runner"`) for E2E generation and accepted visual baseline updates — NEVER drive them from the main agent — why: `e2e-runner` carries the stack auto-detection and TC-traceability knowledge; `experience-review` must inspect and obtain explicit acceptance before the update.
**IMPORTANT MUST ATTENTION** any coverage gap (a §8 behavior with no scenario, or a flow guarding no documented behavior) feeds BOTH the spec AND the tests — NEVER a test-only fix; property/metamorphic generation and MUTATION-SCORE gates are scoped to unit/integration, N/A at the E2E tier.
**IMPORTANT MUST ATTENTION** update `docs/project-reference/e2e-test-reference.md` with learnings when investigating/fixing E2E failures.
**MANDATORY IMPORTANT MUST ATTENTION** add a final review todo task to verify work quality.

**Anti-Rationalization:**

| Evasion                                       | Rebuttal                                                                                          |
| --------------------------------------------- | ------------------------------------------------------------------------------------------------- |
| "I know the framework, skip the reference"    | Read `e2eTesting` config + reference FIRST — stack/paths/TC format are project-specific.           |
| "data-testid is everywhere, just use it"      | Honor the priority — semantic/BEM > data-testid > ARIA > text; show the selector you rejected.     |
| "This selector is faster via `:nth-child`"    | Positional/generated selectors break on unrelated churn. Use a semantic/data anchor.               |
| "I'll clean up the data after the run"        | NEVER tear down seeded data — teardown breaks parallel/repeat runs. Leave it in place.             |
| "Test passes, traceability is bookkeeping"    | No TC code traced to a §8 behavior = no bug protection. Name the rule the scenario guards.         |
| "Just generate the test inline, it's quick"   | Spawn `e2e-runner` — it owns stack detection, TC traceability, and baseline updates.               |

> **Closing reminder — Easy to Change is the success metric.** Every finding,
> test, refactor, and abstraction must answer one question: _does this make
> the next change cheaper or more expensive?_ If it doesn't reduce future
> change cost, reject it. Coupling, hidden state, duplicated knowledge, and
> unclear intent are the real enemies — call them out by name.

---

**IMPORTANT MUST ATTENTION** read `e2eTesting` config + `e2e-test-reference.md` FIRST and detect the framework — NEVER assume a stack.
**IMPORTANT MUST ATTENTION** every test carries its `TC-{MODULE}-E2E-{NNN}` code traced to the §8 behavior it guards; selector priority semantic > data-attr > ARIA > text — NEVER generated/positional/XPath.
**IMPORTANT MUST ATTENTION** generate unique self-sufficient data, NEVER tear down seeded data; spawn `e2e-runner` for generation and only explicitly accepted baseline updates.

<!-- CODEX:SYNC-PROMPT-PROTOCOLS:START -->
## Static Prompt Protocol Mirror (Auto-Synced)

Source: `.claude/.ck.json` + `.claude/skills/shared/sync-inline-versions.md` (`:full` blocks) + `.claude/scripts/lib/hookless-prompt-protocol.cjs` (legacy filename; static protocol composer)

## [WORKFLOW-EXECUTION-PROTOCOL] [BLOCKING] Workflow Execution Protocol — MANDATORY IMPORTANT MUST CRITICAL. Do not skip for any reason.

**Generic portability boundary:** Reusable skills and protocol text stay project-neutral; project-specific conventions are discovered from docs/project-config.json and docs/project-reference/. Apply shared AI-SDD from `shared/sdd-artifact-contract.md`. Read `docs/project-config.json` and `docs/project-reference/docs-index-reference.md`, then open the project reference docs named there immediately before the first target read, grep, edit, test, or analysis. For spec, test-case, behavior-change, public-contract, or `docs/specs/` work, route through the local spec docs named by the docs index: `feature-spec-reference.md`, `spec-system-reference.md`, `spec-principles.md`, and `workflow-spec-test-code-cycle-reference.md` when specs/tests/code must stay synchronized. If either file or a required reference doc is missing or stale, auto-run `$project-init` (or the narrow lower-level route such as `$project-config`, `$docs-init`, `$scan-all`, or `$scan --target=<key>`) before ordinary project-specific work. After compaction, resume, delegation, or a material context change, re-read the required docs and state `Reference docs read: ... | Not applicable: ...`; a hook reminder or prior conversation is not proof that the files are loaded. Any supported AI tool may execute when this shared context and local docs are available.

1. **DETECT:** If the prompt starts with an explicit slash skill/workflow command, execute it directly. Otherwise match the prompt against the workflow catalog and skill list.
2. **ANALYZE:** Choose the best option: execute directly, invoke a skill, activate a standard workflow, or compose a custom step combination.
3. **AUTO-SELECT:** Pick the best option yourself. Do not ask the user to choose between direct execution, skill, standard workflow, or custom workflow.
4. **ACTIVATE:** For a selected workflow, call `$start-workflow <workflowId>`; for a selected skill, invoke that skill; for a custom workflow, sequence custom steps directly; for direct execution, proceed with the task.
5. **CREATE TASKS:** task tracking for ALL workflow/skill/custom steps before execution when the selected path has multiple steps.
6. **PARALLELIZE:** Before executing the task list, tag each task `PAR` (independent inputs + write set disjoint from every other `PAR` task) or `SEQ` (name the blocking dependency), group `PAR` tasks into waves, declare the wave plan, and spawn each wave's sub-agents in ONE message — all-return barrier per wave, fan-out one level deep unless a sub-agent's own definition authorizes further fan-out. Sequential-by-default is a defect when tasks are independent; do not parallelize shared write targets, output-consuming tasks, trivial single-file work, ordering a skill or workflow explicitly fixes, or user-approval gates.
7. **EXECUTE:** Advance per the **Workflow Step Advancement & Parallel Phases** rule in your context instructions — model-driven; a sub-agent completion advances a step identically to an inline call; a parallel-phase group is an all-return barrier (advance only after ALL members return, never serialize it)
## Shared AI-SDD Protocol Markers

Source: `.claude/skills/shared/sync-inline-versions.md`

## SYNC:ai-sdd-artifact-contract

> **AI-SDD Artifact Contract** — Shared spec-driven development rules stay portable and source-owned.
>
> 1. Keep reusable AI-SDD principles in `.claude`; put repository-specific paths, commands, owners, products, and formats in project config/reference docs.
> 2. Preserve cycle: `spec -> plan -> tasks -> implement -> verify -> update spec/docs`.
> 3. Trace every requirement or invariant through decision, task, TC/test, source evidence, and docs/spec update.
> 4. Treat code-to-spec extraction as reference-only until accepted by the canonical spec owner.
> 5. Any supported AI tool may plan, implement, review, or verify with synced context; using multiple tools is optional.
> 6. Update `.claude` source first, then sync generated mirrors; do not manually edit `.agents`, `.codex`, or `AGENTS.md`. — why: mirrors are generated artifacts; hand-edits are overwritten on the next sync
> 7. If `docs/project-config.json`, root instruction files, or a required project-reference doc is missing or stale, auto-run `$project-init` or the narrow lower-level route before ordinary project-specific work.
>
> **Active reference:** `shared/sdd-artifact-contract.md` in the active skills root.

---

## SYNC:ai-sdd-artifact-contract:reminder

- **MANDATORY** Apply `shared/sdd-artifact-contract.md`; keep reusable AI-SDD in `.claude` and local rules in project docs.
- **MANDATORY** Code-to-spec extraction is reference-only until canonical acceptance; any supported AI tool may execute with synced context.
- **MANDATORY** Update `.claude` source before syncing generated mirrors; do not manually edit `.agents`, `.codex`, or `AGENTS.md`.
- **MANDATORY** Missing or stale project config, root instruction files, or required reference docs route project-specific work through `$project-init` or the narrow setup route automatically.
**[TASK-PLANNING] [MANDATORY]** BEFORE executing any workflow or skill step, create/update task tracking for all planned steps, then keep it synchronized as each step starts/completes.
## [LESSON-LEARNED-REMINDER] [BLOCKING] Task Planning & Continuous Improvement — MANDATORY. Do not skip.

Break work into small tasks (task tracking) before starting. Add final task: "Analyze AI mistakes & lessons learned".

**Extract lessons — ROOT CAUSE ONLY, not symptom fixes:**
1. Name the FAILURE MODE (reasoning/assumption failure), not symptom — "assumed API existed without reading source" not "used wrong enum value".
2. Generality test: does this failure mode apply to ≥3 contexts/codebases? If not, abstract one level up.
3. Write as a universal rule — strip project-specific names/paths/classes. Useful on any codebase.
4. Consolidate: multiple mistakes sharing one failure mode → ONE lesson.
5. **Recurrence gate:** "Would this recur in future session WITHOUT this reminder?" — No → skip `$learn`.
6. **Auto-fix gate:** "Could `$code-review`/`$code-simplifier`/`$security-review`/`$lint` catch this?" — Yes → improve review skill instead.
7. BOTH gates pass → ask user to run `$learn`.
**[CRITICAL-THINKING-MINDSET]** Apply critical thinking, sequential thinking. Every claim needs traced proof, confidence >80% to act.
**Anti-hallucination principle:** Never present guess as fact — cite sources for every claim, admit uncertainty freely, self-check output for errors, cross-reference independently, stay skeptical of own confidence — certainty without evidence root of all hallucination.
**AI Attention principle (Primacy-Recency):** Put the 3 most critical rules at both top and bottom of long prompts/protocols so instruction adherence survives long context windows.
**Goal-driven execution:** Define success criteria first, loop until verified, and stop only when observable checks pass.
**Tests verify intent:** Tests must protect business rules/invariants and fail when the protected intent breaks, not only mirror current behavior.
## Common AI Mistake Prevention (System Lessons)

- **Re-read files after context compaction.** Edit requires prior Read in same context; compaction wipes read state. Re-read before editing.
- **Grep for old terms after bulk replacements.** AI over-trusts find/replace completeness. Grep full repo after bulk edits for missed refs in docs/configs/catalogs.
- **Check downstream references before deleting.** Deletions cascade doc/code staleness. Map referencing files before removal.
- **After memory loss, check existing state before creating new.** Compaction wipes prior-work memory. Query current state to resume — never blindly duplicate.
- **Verify AI-generated content against actual code.** AI hallucinates APIs, class names, method signatures. Grep to confirm existence before documenting/referencing.
- **Trace full dependency chain after edits.** Changing a definition misses downstream consumers. Trace the full chain.
- **When renaming, grep ALL consumer file types.** Some file types silently ignore missing refs (no compile error). Search code, templates, configs, generated files.
- **Trace ALL code paths when verifying correctness.** Code existing ≠ code executing. Trace early exits, error branches, conditional skips — not just happy path.
- **Update docs that embed canonical data when source changes.** Docs inlining derived data (workflows, schemas, configs) go stale silently. Update all embedding docs alongside source.
- **Verify sub-agent results after context recovery.** Background agents may finish while parent compacted — grep-verify output, don't trust assumed completion.
- **Cross-check full target list against sub-agent assignments.** Parallel sub-agents by category miss boundary items. Reconcile union of assignments against target list before proceeding.
- **Sub-agents inherit knowledge only from their agent .md definition — use custom agent types, not built-in Explore.** Tool adoption = permission + knowledge + enforcement (numbered workflow step).
- **Persist sub-agent findings incrementally, not as a final batch.** Long sub-agents hit cutoffs before final write — findings lost. Instruct append-per-section to report file.
- **When debugging, ask "whose responsibility?" before fixing.** Trace caller (wrong data) vs callee (wrong handling). Fix at responsible layer — never patch symptom site.
- **Test failure → record a provisional verdict before trace/edit, then investigate.** Use the full five-way taxonomy: SOURCE-WRONG (production violates intent), TEST-WRONG (assertion/setup is stale), TEST-NOT-OPTIMAL (valid but fragile or low-signal test), ENVIRONMENT-BLOCKED (external state prevents a verdict), or AMBIGUOUS (intent/evidence cannot choose safely). Then trace root cause and triangulate against the governing spec (`docs/specs/**` if one exists) AND source. NEVER weaken an assertion, add a skip, relax a timeout, or change source merely to force green.
- **Grep ALL removed names after extraction/refactoring.** Primary file "done" ≠ secondary files clean. Grep entire scope for every removed symbol before declaring complete.
- **Assume existing values are intentional — ask WHY before changing OR flagging one as a defect.** Pattern-matching as "wrong" skips context. Before changing or reporting any constant/limit/flag/cutoff: read comments, git blame, the CALLER's ordering (the guarantee that makes the value correct usually lives in code running immediately BEFORE the cited line), and 2+ sibling call sites of the same convention. A doc stating WHAT without WHY is missing rationale, not proof of a missing guard — and in a validation pass, an accurate `file:line` citation proves the transcription, never the defect.
- **Verify ALL affected outputs, not just the first.** One build green ≠ all green. Multi-stack changes (backend/frontend/tests/docs) require verifying EVERY output.
- **Evaluate fit before copying a nearby pattern.** Closest example ≠ matching preconditions — verify the new context shares the same constraints, base classes, scope, lifetime.
- **Holistic-first debugging — resist nearest-attention trap.** Don't dive into first plausible cause. List EVERY precondition (config, env vars, paths, DB, endpoints, creds, versions, DI, data). Verify each against evidence (grep/query — not reasoning). Ask "what would falsify this?" — if nothing, it's not a hypothesis. Most expensive failure: going deeper in "obvious" layer while bug sits in layer never questioned.
- **Surgical changes — apply the diff test (context-aware).** Two modes: (1) Bug fix → every line traces to the bug; no restyling; orphan cleanup only for imports YOUR changes made unused. (2) Review/enhancement → implement improvements AND announce as "Enhancement beyond main request: [what]". Never silently scope-creep. Diff test: "Would this line exist if I wasn't asked to do X?" — if no, delete or announce.
- **Surface ambiguity before coding — don't pick silently.** Multiple valid interpretations → present each with effort: "[Request] could mean (1) [N h], (2) [N h]. Which matters?" List scope/format/volume/constraints assumptions first. If simpler path exists, say so. Never silently pick.
- **[MANDATORY FIRST ACTION] ALWAYS activate a suitable skill or workflow BEFORE responding.** Match task against workflow catalog + skill list; invoke via skill invocation or `$start-workflow <workflowId>`. NEVER answer or write code before checking. Skip = protocol violation.
- **Why-Review adversarial mindset — apply when reviewing any plan, decision, or design.** Default SKEPTIC not VALIDATOR: steel-man a rejected alternative, invert each stated reason ("what does it sacrifice?"), stress-test top 2-3 assumptions, run pre-mortem ("ships, fails in 3 months — what breaks?"), surface 1-2 alternatives author missed. Section presence ≠ quality; quality = causal reasoning + concrete mitigations + evidence, not "it's better" or "monitor closely".
- **Front-load report-write in sub-agent prompts for large reviews.** Many-file sub-agents hit budget before final write — findings lost. Design prompts so: (1) report-write is first explicit deliverable, (2) append per-file/section (not batched), (3) scope bounded so reads don't exhaust budget. Truncated mid-sentence with no report file → spawn narrower scope, don't retry same prompt.
- **After context compaction, re-verify all prior phase outcomes before continuing.** Summaries describe intent, not environment state (git index, filesystem, processes). On resume, FIRST audit: git status, re-read modified files, verify filesystem. Every "completed" claim is an untested hypothesis until evidence confirms.
- **OOM/memory: check row count before row size.** Triage: (1) Unbounded query — no DB filter for trigger? Push filter to DB; eliminates OOM. (2) Large rows? Projection reduces proportionally. Row reduction > projection in ROI.
- **Assert the outcome your system OWNS, never the intermediate state your INFRASTRUCTURE owns.** When testing anything asynchronous (queue/broker delivery, retries, background jobs, caches, replication), assert the final business/entity state. NEVER assert the delivery bookkeeping — consume/send status, attempt counts, last-error, row existence or counts in a broker, scheduler, or outbox/inbox table. That bookkeeping lives in shared infrastructure that ANY co-running process (a peer worker, a second replica, a leftover local container) can write, usually under a deterministic shared key, so the assertion silently tests the developer's environment instead of the system: green when run alone, flaky the instant anything else shares that broker + database. Gate question for every assertion: "would this hold no matter WHICH process did the work?" — if no, assert the converged data state instead. Corollary: process-local fault injection and in-process telemetry cannot gate work any process may perform — use them as stress amplifiers (arm → bounded window → disarm → assert convergence), never as preconditions.
- **Keep domain concepts out of generic/shared/infrastructure layers.** Reusable layer (shared library, framework, infra module) must reference NO consumer-specific domain concept — tenant/customer/product IDs, business entities, feature rules. Leak compiles + runs → passes review silently while coupling the "reusable" layer to one consumer. Keep shared type domain-free; push domain fields/logic down into the consumer via subclass/composition. — why: a layer coupled to one consumer's domain is no longer reusable.

<!-- CODEX:SYNC-PROMPT-PROTOCOLS:END -->