Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

Back to skills

Archive

ASecurity

> **Status**: Archived > **Created**: 20260913-0258 > **Slug**: repo-harness-test-skill > **Planning Source**: codex-plan-or-waza-think > **Orchestration Kind**: host-plan > **Source Ref**: (none) > **Artifact Level**: work-package > **Promotion Reason**: verification_boundary > **Verification Boundary**: Commands named in the captured planning output plus `repo-harness run verify-contract --contract tasks/archive/contract-20260913-0417-repo-harness-test-skill.md --strict`. > **Rollback Surfa...

431 stars
0 votes
0 copies
0 views
Added 9/21/2026
developmentgobashtesting

Works with

cli

Security Analysis

A100/100

Scanned 9/21/2026

Install to Claude Code

$npx -y skills add Ancienttwo/repo-harness --skill archive --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Archive?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Archive
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/ancienttwo-archive-repo-harness/badge)](https://www.skillsdirectory.com/skills/ancienttwo-archive-repo-harness)

More formats (shields.io, HTML) on the badges page.

Download Zip
Files
.gitkeep
> **Archived**: 2026-09-13 04:17
> **Related Plan**: plans/archive/plan-20260913-0258-repo-harness-test-skill.md
> **Outcome**: Completed
> **Lifecycle**: plan
> **Parent Run ID**: run-20260913-0417
> **Archive Projection V1**: `plans/plan-20260913-0258-repo-harness-test-skill.md` => `plans/archive/plan-20260913-0258-repo-harness-test-skill.md`
> **Archive Projection V1**: `tasks/notes/20260913-0258-repo-harness-test-skill.notes.md` => `tasks/archive/notes-20260913-0417-repo-harness-test-skill.md`
> **Archive Projection V1**: `tasks/contracts/20260913-0258-repo-harness-test-skill.contract.md` => `tasks/archive/contract-20260913-0417-repo-harness-test-skill.md`
> **Archive Projection V1**: `tasks/reviews/20260913-0258-repo-harness-test-skill.review.md` => `tasks/archive/review-20260913-0417-repo-harness-test-skill.md`

# Plan: Ship the repo-harness-test skill as the testing policy router

> **Status**: Archived
> **Created**: 20260913-0258
> **Slug**: repo-harness-test-skill
> **Planning Source**: codex-plan-or-waza-think
> **Orchestration Kind**: host-plan
> **Source Ref**: (none)
> **Artifact Level**: work-package
> **Promotion Reason**: verification_boundary
> **Verification Boundary**: Commands named in the captured planning output plus `repo-harness run verify-contract --contract tasks/archive/contract-20260913-0417-repo-harness-test-skill.md --strict`.
> **Rollback Surface**: Before execution remove `plans/archive/plan-20260913-0258-repo-harness-test-skill.md`; after execution revert branch `codex/repo-harness-test-skill` or the explicitly reviewed diff.
> **Spec**: `docs/spec.md`
> **Research**: See `docs/researches/`
> **Task Contract**: `tasks/archive/contract-20260913-0417-repo-harness-test-skill.md`
> **Task Review**: `tasks/archive/review-20260913-0417-repo-harness-test-skill.md`
> **Implementation Notes**: `tasks/archive/notes-20260913-0417-repo-harness-test-skill.md`

## Agentic Routing
- Selected route: planning
- Routing reason: Captured from codex-plan-or-waza-think planning output.
- Source ref: (none)
- Due diligence:
  - P1 map: See captured planning output below.
  - P2 trace: See captured planning output below.
  - P3 decision rationale: See captured planning output below.

## Workflow Inventory
Complete this inventory before implementation. If any line is unknown, keep the plan in Draft and fill it before projection.

- Active plan: `plans/archive/plan-20260913-0258-repo-harness-test-skill.md`
- Sprint contract: `tasks/archive/contract-20260913-0417-repo-harness-test-skill.md`
- Sprint review: `tasks/archive/review-20260913-0417-repo-harness-test-skill.md`
- Implementation notes: `tasks/archive/notes-20260913-0417-repo-harness-test-skill.md`
- Deferred-goal ledger: `tasks/todos.md`
- Current checks: `.ai/harness/checks/latest.json`
- Run snapshots: `.ai/harness/runs/`
- Scope authority: `tasks/archive/contract-20260913-0417-repo-harness-test-skill.md` `allowed_paths`
- Concurrency rule: `.ai/harness/active-plan` selects the active plan for this worktree when present; `.ai/harness/active-worktree` records the owning worktree. If another worktree already owns active work, open or switch to the matching worktree instead of serializing unrelated plans.
- Execution isolation: approved contract-level work projects through `repo-harness run plan-to-todo --plan plans/archive/plan-20260913-0258-repo-harness-test-skill.md` and may start `repo-harness run contract-worktree start --plan plans/archive/plan-20260913-0258-repo-harness-test-skill.md`.

## Approach
### Strategy
Use the captured planning output below as the execution source of truth.

### Trade-offs
| Option | Pros | Cons | Decision |
|--------|------|------|----------|
| Captured plan | Preserves the approved Codex Plan or Waza think decision | Requires the captured text to be concrete enough to execute | Use |

## Detailed Design
### File Changes
| File | Action | Description |
|------|--------|-------------|
| See captured planning output | Follow | Implement only the approved scope named below |

### Code Snippets
See captured planning output.

### Data Flow
See captured planning output.

## Risk Assessment
| Risk | Likelihood | Impact | Mitigation |
|------|------------|--------|------------|
| Captured plan lacks enough detail | Medium | Execution may need clarification | Stop before implementation if the captured output contradicts repo rules or lacks concrete file targets |

## Task Contracts
- Contract file: `tasks/archive/contract-20260913-0417-repo-harness-test-skill.md`
- Review file: `tasks/archive/review-20260913-0417-repo-harness-test-skill.md`
- Implementation notes file: `tasks/archive/notes-20260913-0417-repo-harness-test-skill.md`
- Template: `.claude/templates/contract.template.md`
- Verification command: `repo-harness run verify-contract --contract tasks/archive/contract-20260913-0417-repo-harness-test-skill.md --strict`
- Active plan rule: this captured plan is written to `.ai/harness/active-plan` and the owning worktree is written to `.ai/harness/active-worktree` unless --no-active is used. Do not infer active execution from the latest non-archived plan.

## Handoff

- Checks file: `.ai/harness/checks/latest.json`
- Session handoff: `.ai/harness/handoff/current.md`

## Promotion Gate

- **Merge/PR unit**: Captured plan `plans/archive/plan-20260913-0258-repo-harness-test-skill.md` is the proposed mergeable execution unit; revise before execute if this is only a checklist step.
- **Rollback surface**: Before execution remove `plans/archive/plan-20260913-0258-repo-harness-test-skill.md`; after execution revert branch `codex/repo-harness-test-skill` or the explicitly reviewed diff.
- **Verification boundary**: Commands named in the captured planning output plus `repo-harness run verify-contract --contract tasks/archive/contract-20260913-0417-repo-harness-test-skill.md --strict`.
- **Review/acceptance boundary**: `tasks/archive/review-20260913-0417-repo-harness-test-skill.md` must record pass against the captured acceptance criteria.
- **High-risk surface**: Risks named in captured planning output; keep the plan Draft if risk ownership is not concrete.
- **Why not checklist row**: verification_boundary

## Evidence Contract

- **State/progress path**: `plans/archive/plan-20260913-0258-repo-harness-test-skill.md` task breakdown, `tasks/todos.md` deferred-goal ledger, `tasks/archive/contract-20260913-0417-repo-harness-test-skill.md`, `tasks/archive/review-20260913-0417-repo-harness-test-skill.md`, and `tasks/archive/notes-20260913-0417-repo-harness-test-skill.md`
- **Verification evidence**: `.ai/harness/checks/latest.json`, `.ai/harness/runs/`, and the commands named in the captured planning output
- **Evaluator rubric**: `tasks/archive/review-20260913-0417-repo-harness-test-skill.md` must record a passing Waza /check style recommendation
- **Stop condition**: all task breakdown items are complete, sprint verification passes, and the review recommends pass
- **Rollback surface**: Before execution remove `plans/archive/plan-20260913-0258-repo-harness-test-skill.md`; after execution revert branch `codex/repo-harness-test-skill` or the explicitly reviewed diff.

## Captured Planning Output

# Ship the repo-harness-test skill as the testing policy router

## P1 Map
- Skill packages live under `assets/skills/<name>/` with `SKILL.md` plus `references/`.
- The single shipping registration point is `assets/skill-commands/manifest.json` (`version: 2`, `packages[]`
  plus `expectedProjections`). `src/core/skill-surface/catalog.ts` parses it; `src/cli/commands/init.ts`,
  `src/cli/installer/install-profile.ts`, `scripts/skill-surface-select.ts`,
  `scripts/sync-codex-installed-copies.sh` and `scripts/run-skill-routing-eval.ts` all read the parsed
  catalog. There is no second list to add.
- `computeFacadesForProfile` (catalog.ts) only projects `kind: "facade"` packages whose `profiles` include
  the install profile, so a shipped, profile-projected skill must be a facade.
- Prose policy authority for testing is `docs/reference-configs/sprint-contracts.md`
  `## Testing Policy and Artifact Standards` (authoring source `assets/reference-configs/sprint-contracts.md`).

## P2 Trace
- `repo-harness install` / `update` -> `sync-codex-installed-copies.sh` ->
  `skill-surface-select.ts` -> `parseSkillSurfaceCatalog(manifest)` -> facade projection into
  `~/.claude/skills/<name>` and `~/.codex/skills/<name>` for the selected profile.
  Public `init` handles repo-local adoption and disables host skill sync.
- Several tests pin the shipped surface as an exact set derived from that one manifest: they are the drift
  checks between the manifest and the declared surface, and each gains the new package name.

## P3 Decide
- The skill is a router only: it names four entrypoints and links their references. It restates no policy;
  `sprint-contracts.md` stays the single prose authority. The references carry executable technique and
  repo-specific tooling that the policy deliberately does not own.
- `profiles: ["full"]`, `component: "verifier"`: the testing surface belongs to the verification component,
  which the minimal profile does not install. This also keeps the minimal discovery matrix untouched.
- No new authority, no second policy, no runtime validator.

## Task Breakdown
- [x] Author `assets/skills/repo-harness-test/SKILL.md` (<= 2048 bytes) plus four references.
- [x] Register the package in `assets/skill-commands/manifest.json` and its `expectedProjections`.
- [x] Add the package name to the manifest-derived surface inventories in
      `tests/skill-surface/catalog.test.ts`, `tests/skill-surface/canonical-packages.test.ts`,
      `tests/action-command-skills.test.ts`, `tests/skill-routing-eval.test.ts`.
- [x] Add one routing row to `assets/reference-configs/agentic-development-flow.md` and sync the projection.
- [x] Run the verification plan.

## Verification Plan
- `bun test tests/skill-surface tests/action-command-skills.test.ts tests/skill-routing-eval.test.ts tests/readme-dx.test.ts tests/install-profiles.test.ts tests/installed-copy-sync.test.ts`
- `bun run check:type`, `check:hooks`, `check:helpers`, `check:reference-configs`
- `bash scripts/check-architecture-sync.sh`, `bash scripts/check-task-workflow.sh --strict`
- `REPO_HARNESS_DIFF_BASE=origin/main REPO_HARNESS_DIFF_MODE=merge-base bash scripts/check-task-sync.sh`
- `bun src/cli/index.ts init --repo . --dry-run`

## Rollback
Revert branch `codex/repo-harness-test-skill`.

## Annotations
<!-- [NOTE]: prefixed inline. Claude processes all and revises. -->

## Task Breakdown
- [x] Author `assets/skills/repo-harness-test/SKILL.md` (<= 2048 bytes) plus four references.
- [x] Register the package in `assets/skill-commands/manifest.json` and its `expectedProjections`.
- [x] Add the package name to the manifest-derived surface inventories in
- [x] Add one routing row to `assets/reference-configs/agentic-development-flow.md` and sync the projection.
- [x] Run the verification plan.

Attribution

AncienttwoAncienttwo
View sourceMore from Ancienttwo →
SSkills DirectorySkills Directory

Know which skills are safe — weekly.

Best new skills + every skill we flagged as malicious. From the team that scanned 103,619.

Join free

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Know which skills are safe — weekly.

Best new skills + every skill we flagged as malicious. From the team that scanned 103,619.

Join free

Related Skills

Browser Extension Developer

Use this skill when developing or maintaining browser extension code in the `browser/` directory, including Chrome/Firefox/Edge compatibility, content scripts, background scripts, or i18n updates.

281612 votes

Seo Optimizer

SEO optimization with keyword analysis, readability assessment, technical validation, content quality. Use for search rankings, blog posts, content audits, or encountering keyword density, readability scores, meta tags, schema markup errors.

2132 votes

Google Official Seo Guide

Official Google SEO guide covering search optimization, best practices, Search Console, crawling, indexing, and improving website search visibility based on official Google documentation

1862 votes

Tanstack Start

Build a full-stack TanStack Start app on Cloudflare Workers from scratch — SSR, file-based routing, server functions, D1+Drizzle, better-auth, Tailwind v4+shadcn/ui. Use whenever the user mentions TanStack Start, asks to scaffold a full-stack Cloudflare app with SSR, wants an SSR dashboard, or asks for a React 19 + Cloudflare Workers app with file-based routing and server functions — even if they don't name TanStack Start specifically. No template repo — Claude generates every file fresh per ...

9881 votes

Pentest

PTES-aligned adversarial security audit for backend, frontend, and mobile applications. Produces a CVSS-scored Hacker Report with verified PoCs and phased remediation.

5491 votes
View all in development →