Borrowing it
Nothing to install: this file belongs to sciyoshi/decompose. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/sciyoshi/decompose/main/.claude/skills/decompose/SKILL.mdgit clone --depth 1 https://github.com/sciyoshi/decomposeWrote 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/sciyoshi/decompose/decompose)<a href="https://agentmods.dev/skills/sciyoshi/decompose/decompose"><img src="https://agentmods.dev/badge/skills/sciyoshi/decompose/decompose/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/sciyoshi/decompose/decompose"><img src="https://agentmods.dev/badge/skills/sciyoshi/decompose/decompose.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 | $0.00035 | $0.00936 |
| Opus 5.5 | $0.00014 | $0.00374 |
| Sonnet 5.5 | $0.00007 | $0.00187 |
| Haiku 4.5 | $0.00003 | $0.00094 |
Grade A, and why
decompose 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 yesterday.
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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are helping the user manage their local development environment using decompose, a process orchestrator that is broadly compatible with Docker Compose but runs native processes.
Quick reference
decompose up -d # Start all services detached
decompose up -d SERVICE... # Start specific services (+ deps)
decompose up -d --no-deps SERVICE # Start without pulling in deps
decompose down # Stop everything, tear down daemon
decompose ps # Show process status
decompose ps --json # Machine-readable status
decompose logs -f # Follow all logs
decompose logs -f SERVICE # Follow specific service logs
decompose logs -n 100 SERVICE # Last 100 lines of a service
decompose start SERVICE # Start a stopped service
decompose stop SERVICE # Stop a running service
decompose restart SERVICE # Restart a service
decompose attach # Reattach to daemon log stream
How decompose works
decompose upspawns a background daemon that manages all processes. The CLI is a thin client that talks to the daemon over a local Unix socket.- Each environment is identified by a hash of the config directory + files, or by
--session NAME(the name is used as the ID). - Config is discovered automatically:
decompose.yml>decompose.yaml>compose.yml>compose.yaml. Use-f FILEto override (can be repeated for overlay merging). - Output modes:
--json(machine),--table(human), or auto-detect (TTY/CI/LLM -> table, pipe -> JSON).
When the user asks to start/debug their environment
- Check if a compose file exists in the working directory. Look for
decompose.yml,decompose.yaml,compose.yml, orcompose.yaml. - Check if a daemon is already running:
decompose ps --json. If it returns"running": true, services are already up. - Start services:
decompose up -dfor detached mode. - Check status:
decompose psto verify everything is running. - View logs:
decompose logs -f SERVICEto debug startup issues. - Look for errors: Check if processes are in
stoppedorexitedstatus. Use logs to find the root cause.
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.
- yesterday First seen · 95 lines · 35 tokens per session scan A 60815c82d57f
decompose is a skill published in the GitHub repository sciyoshi/decompose (7 stars, last pushed 12d ago), licensed Apache-2.0. It adds 35 tokens to every session and 936 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 2026-11-07.
decompose compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| decomposesciyoshi/decompose | Skill | 7 | 12d ago | Apache-2.0 | A | 35 | Claude Code |
| imagegenopenai/codex | Skill | 134k | today | Apache-2.0 | A | 113 | Codex |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | yesterday | MIT | A | 200 | Claude Code, Codex |
| playwright-climicrosoft/playwright | Skill | 100k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| browser-automationopenclaw/openclaw | Skill | 394k | today | MIT | A | 36 | Claude Code |
| systematic-debuggingobra/superpowers | Skill | 314k | 4d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 95 | Claude Code |