Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add pilotspace/pilot-space --skill decompose-tasksgit clone --depth 1 https://github.com/pilotspace/pilot-spaceWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/pilotspace/pilot-space/decompose-tasks)<a href="https://agentmods.dev/skills/pilotspace/pilot-space/decompose-tasks"><img src="https://agentmods.dev/badge/skills/pilotspace/pilot-space/decompose-tasks/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/pilotspace/pilot-space/decompose-tasks"><img src="https://agentmods.dev/badge/skills/pilotspace/pilot-space/decompose-tasks.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00016 | $0.02385 |
| Opus 5.5 | $0.00006 | $0.00954 |
| Sonnet 5.5 | $0.00003 | $0.00477 |
| Haiku 4.5 | $0.00002 | $0.00238 |
Grade A, and why
decompose-tasks scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 329 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Decompose Tasks Skill
Automatically break down complex issues into actionable subtasks with dependencies and estimates.
Quick Start
Use this skill when:
- Large feature needs breakdown into subtasks
- User requests task decomposition (
/decompose-tasks) - Issue is too complex for single assignee
Example:
Issue: "Implement user authentication system"
AI decomposes into:
1. Design database schema for users/sessions (2 days, no dependencies)
2. Implement JWT token generation (1 day, depends on #1)
3. Create login/logout API endpoints (2 days, depends on #2)
4. Add frontend login form (1 day, depends on #3)
5. Write integration tests (1 day, depends on #3, #4)
Workflow
-
Analyze Issue Scope
- Parse description for distinct components
- Identify technical layers (DB, API, Frontend, Tests)
- Detect implied tasks from acceptance criteria
-
Generate Subtask Graph
- Decomposition Strategy:
- Backend features: DB schema → API → Tests
- Frontend features: Component → State → Styling → Tests
- Full-stack: Backend → Frontend → Integration
- Identify parallel vs sequential tasks
- Build dependency graph (DAG)
- Decomposition Strategy:
-
Estimate Complexity
- Small (0.5-1 day): Simple implementation, single file
- Medium (1-3 days): Multiple files, standard patterns
- Large (3-5 days): Cross-cutting changes, new architecture
-
Tag Confidence
- RECOMMENDED: Standard decomposition for known patterns
- DEFAULT: General breakdown, may need refinement
- ALTERNATIVE: Multiple valid approaches, team choice
Output Format
{
"subtasks": [
{
"order": 1,
"name": "Design user database schema",
"description": "Create users, sessions, and refresh_tokens tables with proper indexes",
"confidence": "RECOMMENDED",
"estimated_days": 2,
"labels": ["backend", "database"],
"dependencies": [],
"acceptance_criteria": [
"Schema supports email and OAuth login",
"Indexes on email and session_token fields",
"Migration script tested"
],
"code_references": [
{
"file": "backend/src/pilot_space/infrastructure/database/models/user.py",
"lines": "1-50",
"description": "Existing User model to extend",
"badge": "Model"
},
{
"file": "backend/alembic/versions/",
"description": "Migration directory for new schema",
"badge": "Migration"
}
],
"ai_prompt": "Create database schema for user sessions with proper indexes.\n\n## Context\nIssue: AUTH-42 - Implement user authentication system\nAdd support for both email and OAuth login with session management.\n\n## Requirements\n- Create users, sessions, and refresh_tokens tables\n- Add indexes on email and session_token fields\n- Write migration script for schema changes\n\n## Acceptance Criteria\n- [x] Schema supports email and OAuth login\n- [x] Indexes on email and session_token fields\n- [x] Migration script tested\n\n## Files to Reference\n- `backend/src/pilot_space/infrastructure/database/models/user.py` (lines 1-50) - Existing User model to extend\n- `backend/alembic/versions/` - Migration directory for new schema\n\n## Technical Constraints\n- Use SQLAlchemy 2.0 async\n- Follow repository pattern\n- Ensure RLS policies for multi-tenant isolation"
},
{
"order": 2,
"name": "Implement JWT token service",
"description": "Create service for generating and validating JWT access/refresh tokens",
"confidence": "RECOMMENDED",
"estimated_days": 1,
"labels": ["backend", "security"],
"dependencies": [1],
"acceptance_criteria": [
"Access tokens expire after 15 minutes",
"Refresh tokens stored in database",
"Token validation handles expired tokens"
]
},
{
"order": 3,
"name": "Create login/logout API endpoints",
"description": "POST /auth/login and POST /auth/logout endpoints with proper error handling",
"confidence": "RECOMMENDED",
"estimated_days": 2,
"labels": ["backend", "api"],
"dependencies": [2],
"acceptance_criteria": [
"Login returns access and refresh tokens",
"Logout invalidates refresh token",
"Rate limiting applied (5 attempts/minute)"
]
},
{
"order": 4,
"name": "Build login form component",
"description": "React login form with email/password validation and error display",
"confidence": "RECOMMENDED",
"estimated_days": 1,
"labels": ["frontend", "react"],
"dependencies": [3],
"can_parallel_with": [],
"acceptance_criteria": [
"Form validates email format client-side",
"Displays backend error messages",
"Redirects to dashboard on success"
]
},
{
"order": 5,
"name": "Write authentication integration tests",
"description": "End-to-end tests for full login/logout flow",
"confidence": "RECOMMENDED",
"estimated_days": 1,
"labels": ["testing"],
"dependencies": [3, 4],
"acceptance_criteria": [
"Tests cover happy path and error cases",
"Tests verify token persistence",
"Tests check session expiration"
]
}
],
"summary": "Decomposed into 5 subtasks, estimated 7 days total",
"critical_path": [1, 2, 3, 4],
"parallel_opportunities": ["#4 and #5 can start after #3"]
}
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2mo ago First seen · 329 lines · 16 tokens per session scan A 227693d1467e
decompose-tasks is a skill published in the GitHub repository pilotspace/pilot-space (2 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 16 tokens to every session and 2,385 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…