Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
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
  • Authors
  • 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
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Orchestrate Develop

ASecurity

Orchestrated Delivery O3: one Task subagent per PLAN step (sdd-develop contract); parent never writes app code. Updates CONTINUITY; handoff to code-review. Use when invoking /orchestrate-develop.

6 stars
0 votes
0 copies
0 views
Added 9/25/2026
ai-agentsgoshellrailscode-review

Works with

cursor

Security Analysis

A100/100

Pro scans all 2 files and shows the line behind each finding

Scanned 9/25/2026

$npx -y skills add tibursocampos/agent-dev-toolkit --skill orchestrate-develop --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Orchestrate Develop?

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

Security grade badge for Orchestrate Develop
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/tibursocampos-orchestrate-develop-34203a57/badge)](https://www.skillsdirectory.com/skills/tibursocampos-orchestrate-develop-34203a57)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: orchestrate-develop
description: Orchestrated Delivery O3: one Task subagent per PLAN step (sdd-develop contract); parent never writes app code. Updates CONTINUITY; handoff to code-review. Use when invoking /orchestrate-develop.
---

## STOP - Read before ANY tool call

1. Read `E:/Source/Repos/agent-dev-toolkit/scripts/validation/fixtures/cursor-install-root/rules/guardrails.mdc`
2. Read `_shared/sdd-artifacts/SESSION.md`; load session-state for `$Cwd`
3. If the relevant gate is not approved: **STOP** - ask user **(pt-BR)** - do **NOT** Write/Shell
4. SDD/develop skills: after **ONE** step/task, **STOP** session - handoff only
5. This skill body is **English**; user-facing prompts may be **(pt-BR)**

### Step -1 - Gate check (report in chat before continuing)

```
Gate check:
[ ] guardrails.mdc read
[ ] SESSION.md read; session-state loaded
[ ] PIPELINE.md read (required for orchestrate-*)
[ ] User confirmed current action (sim)
-> If any unchecked: STOP
```

---

# Skill: orchestrate-develop

## Trigger

Invoke when the user asks for: `/orchestrate-develop`, `orchestrate develop`, `/orchestrate-develop`, or Orchestrated Delivery O3 after O2 handoff.

Required: full feature path **or** a specific `PLAN/PLAN_NNN_*.md` path under a story.

## Outcome

1. Pending PLAN step(s) executed via Task children when `subagents=native` (`SPAWN.md`), each following the **`sdd-develop` contract** (one PLAN step per child / session); when `subagents=none` or Task unavailable → **fallback** handoff to manual `/sdd-develop` (parent never writes app code; never hard-fail)
2. Feature `CONTINUITY.md` updated (phase `develop`, progress, typed next invoke, **Memory-bank** path + status)
3. Handoff to `code-review` (`- single` or `- multi-angle`; skill asks if omitted) and/or next step / next story

**Step 0 (required):** Memory Bank Gate (`MEMORY-BANK.md`, policy `auto`) **before** building the step queue / spawning children. Resolve `bank_root` via `STORAGE.md`. CONTINUITY stays the feature phase/handoff source.

**Step N (after code changes):** when at least one develop child succeeded with app file changes, run `memory-bank-init` mode **`refresh-light`** at `bank_root` before final handoff (`MEMORY-BANK.md` Step N). Confirm (pt-BR) first.

**Parent orchestrator never** writes application code, never marks multiple PLAN steps done in one child, and never bypasses `sdd-develop` gates (`step_confirmed`, tests before complete).

**Alternative (always valid):** user runs manual `/sdd-develop - <portable-plan-path> - Step N` without this skill (RF05 / CA5). Manual Classic SDD does **not** require memory-bank (CA7).

**Mental map (ids unchanged):** O3 ≈ **apply** (implement PLAN steps via `sdd-develop`). O1 ≈ explore; O2 ≈ FEATURE+PRD+CHANGE. See `CHANGE-CONTRACT.md`.

**Evidence verifier (REQ-005 / CA4):** children record `features/NNN-slug/EVD/` + `STATE.md` and run `validate-evidence` inside `sdd-develop`. **Verifier ≠ O3** — do **not** use O3 / Task parallelism as the evidence verifier mechanism (sequential script gate only). Levels: `off` \| `cheap` \| `standard` \| `strict`. Contract: `EVD-STATE-CONTRACT.md`.

**Living loop / TRACE (REQ-006 / CA5):** at feature-wave close, children (or the final develop child) append `features/NNN-slug/TRACE.jsonl` and run **converge → sync current → archive**, then `validate-trace -RequireArchiveComplete`. Parent must **not** use O3 parallelism as the archive verifier. Contract: `TRACE-ARCHIVE-CONTRACT.md`.

## Lazy-load (only when needed)

| When | Path (after `scripts/sync-cursor.ps1`) |
|------|----------------------------------------|
| Caveman Mode (if active) | `E:/Source/Repos/agent-dev-toolkit/scripts/validation/fixtures/cursor-install-root/skills/_shared/caveman/CAVEMAN.md` - **Full cap** |
| Pipeline Orchestrated Delivery, paths | `E:/Source/Repos/agent-dev-toolkit/scripts/validation/fixtures/cursor-install-root/skills/_shared/sdd-artifacts/PIPELINE.md` |
| Storage | `E:/Source/Repos/agent-dev-toolkit/scripts/validation/fixtures/cursor-install-root/skills/_shared/sdd-artifacts/STORAGE.md` |
| Step 0 Memory Bank Gate | `E:/Source/Repos/agent-dev-toolkit/scripts/validation/fixtures/cursor-install-root/skills/_shared/sdd-artifacts/MEMORY-BANK.md` |
| Memory-bank create/refresh | `E:/Source/Repos/agent-dev-toolkit/scripts/validation/fixtures/cursor-install-root/skills/memory-bank-init/SKILL.md` |
| Develop contract (source of truth) | `E:/Source/Repos/agent-dev-toolkit/scripts/validation/fixtures/cursor-install-root/skills/sdd-develop/SKILL.md` + `E:/Source/Repos/agent-dev-toolkit/scripts/validation/fixtures/cursor-install-root/skills/sdd-develop/reference.md` |
| SESSION gates | `E:/Source/Repos/agent-dev-toolkit/scripts/validation/fixtures/cursor-install-root/skills/_shared/sdd-artifacts/SESSION.md` |
| CONTINUITY template | `E:/Source/Repos/agent-dev-toolkit/scripts/validation/fixtures/cursor-install-root/skills/_shared/templates/features/CONTINUITY.md` |
| Process details, anti-bypass, parallelism, Must not | `E:/Source/Repos/agent-dev-toolkit/scripts/validation/fixtures/cursor-install-root/skills/orchestrate-develop/reference.md` |
| Spawn native vs fallback (capability `subagents`) | `E:/Source/Repos/agent-dev-toolkit/scripts/validation/fixtures/cursor-install-root/skills/_shared/agents/SPAWN.md` |
| Task subagent model (default omit; rare premium gate) | `E:/Source/Repos/agent-dev-toolkit/scripts/validation/fixtures/cursor-install-root/skills/_shared/agents/SUBAGENT-MODEL.md` |
| Code review (ask mode) | `E:/Source/Repos/agent-dev-toolkit/scripts/validation/fixtures/cursor-install-root/skills/code-review/SKILL.md` |
| Context pressure | `E:/Source/Repos/agent-dev-toolkit/scripts/validation/fixtures/cursor-install-root/rules/context-management.mdc` |

**Never by default:** do not preload `sdd-develop` + all developer guideline packs into the parent, or paste guideline bodies into develop children. Parent loads contracts and SPAWN; children load `sdd-develop` for their one step.

**Progressive load:** `PIPELINE.md` + `STORAGE.md` first; fan-out to `MEMORY-BANK.md` at Step 0, `SPAWN.md` before spawn, `sdd-develop` contract into the child prompt path only, and `orchestrate-develop/reference.md` for Process step details / anti-bypass / parallelism / Must not when needed.

## Reference routing

| Situation | Path |
|-----------|------|
| Gate / Orchestrated Delivery | `PIPELINE.md` |
| Feature / PLAN / bank roots | `STORAGE.md` |
| Step 0 Memory Bank | `MEMORY-BANK.md` |
| Before Task / fallback to manual develop | `SPAWN.md` |
| Child implement contract | `E:/Source/Repos/agent-dev-toolkit/scripts/validation/fixtures/cursor-install-root/skills/sdd-develop/SKILL.md` |
| Process steps / anti-bypass / parallel / Must not | `E:/Source/Repos/agent-dev-toolkit/scripts/validation/fixtures/cursor-install-root/skills/orchestrate-develop/reference.md` |
| Review handoff | `E:/Source/Repos/agent-dev-toolkit/scripts/validation/fixtures/cursor-install-root/skills/code-review/SKILL.md` |

## Process

Read `reference.md` for procedural tables, prompts, and checklists under each step. Do not skip gates.

### Step -1b - Caveman Mode (Full cap)
Apply Full caveman prefs when active. Details: `reference.md` § Process — Caveman (Full cap).

### 1. Gate check
Report the Step -1 gate checklist in chat. Load `PIPELINE.md` (Orchestrated Delivery) and `SESSION.md`. **STOP** if any gate unchecked. Ask user **sim** before spawning the first develop child.

### 2. Resolve feature / PLAN set
Load `STORAGE.md`; resolve feature + `bank_root`; path sanitize; build PLAN queue or **STOP** if missing. Details: `reference.md` § Process — Resolve feature / PLAN set.

### 3. Step 0 - Memory Bank Gate
Follow `MEMORY-BANK.md` (policy default **`auto`**). Bank root = resolved `bank_root` - **not** under `features/`. Pass **`bank_path`** into every develop child as read-only Prior context. Details: `reference.md` § Step 0 - Memory Bank Gate.

### 4. Build step queue (deps)
Parse pending steps; respect Deps; present queue; wait for **sim**. Details: `reference.md` § Process — Build step queue + § Step queue algorithm.

### 5. Spawn exactly one step child (CA5)
SPAWN first; one Task = one PLAN step = full `sdd-develop` contract; omit Task `model` by default; fallback to manual `/sdd-develop` when Task unavailable. Parent updates CONTINUITY only after child returns. Details: `reference.md` § Process — Spawn one step child + § Task child prompt skeleton + § Anti-bypass checklist.

### 6. Safe parallelism (optional)
Default **serial**. Parallel only when all independence conditions + user **sim** + distinct SESSION files; cap ≤4. Details: `reference.md` § Process — Safe parallelism + § Safe parallelism rules.

### 7. Stop conditions
Stop on story/feature done, context pressure, child blocked, or **cancelar**. Details: `reference.md` § Process — Stop conditions.

### 8. CONTINUITY
Update phase / Memory-bank / estado / handoff at each milestone. Details: `reference.md` § Process — CONTINUITY fields + § CONTINUITY checklist.

### 9. Step N - Memory Bank refresh-light (after code changes)
When a child changed app files: confirm → `refresh-light` → CONTINUITY `refreshed` (or skip). Details: `reference.md` § Process — Step N refresh-light + § Step N - refresh-light.

### 10. Handoff - code-review + manual alternative
Emit review + manual `/sdd-develop` + continue O3 strings. Details: `reference.md` § Handoff copy.

## Anti-bypass checklist (must enforce)

Parent and children **must not** bypass CA5. Enforce the full table in `reference.md` § Anti-bypass checklist before every spawn and before marking any step done. Critical: parent writes **no** app code; one child = one PLAN step; **sim** before next spawn; PLAN-scoped SESSION files for parallel children.

## Must not

Enforce the full list in `reference.md` § Must not (full). Critical always-on: no parent app code; no multi-step children; no hard-fail when Task unavailable (fallback `/sdd-develop`); portable paths only.

## Handoff

| Situation | Next |
|-----------|------|
| Next PLAN step | New chat -> `orchestrate-develop` **or** `sdd-develop - <plan> - Step N` |
| Story/feature done | `/code-review` (pass `- single` / `- multi-angle`, or let skill ask) |
| Missing PLAN | `orchestrate-deliver` / `sdd-plan` |
| Prefer no orchestrator | Manual `sdd-develop` only |

### Canonical strings

```text
/orchestrate-develop - <portable-feature-path>
```

```text
/sdd-develop - <portable-plan-path> - Step N
```

```text
/code-review
/code-review - multi-angle
```

Attribution

tibursocampostibursocampos
View sourceSee grades on GitHubMore from tibursocampos →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

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

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698621 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →