Skill Compose is an open-source platform for building and running AI agents that use modular skills. It is intended for creating skill-powered agents without workflow graphs or a command-line interface, and the catalogue skills are examples of those agent capabilities.
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 agentmods add skills/dp-archive/archive/skill-findernpx skills add dp-archive/archive --skill skill-findergit clone --depth 1 https://github.com/dp-archive/archiveWrote 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/dp-archive/archive/skill-finder)<a href="https://agentmods.dev/skills/dp-archive/archive/skill-finder"><img src="https://agentmods.dev/badge/skills/dp-archive/archive/skill-finder.svg" alt="Measured on agentmods" 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 | $0.00064 | $0.01136 |
| Opus 5 | $0.00032 | $0.00568 |
| Sonnet 5 | $0.00013 | $0.00227 |
| Haiku 4.5 | $0.00006 | $0.00114 |
Grade A, and why
skill-finder 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 6d 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 — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Finder
Discover and install agent skills from the skills.sh open ecosystem into Skill Compose.
When to Use This Skill
Activate when users:
- Ask "how do I do X?" where an existing skill might help
- Request "find a skill for X" or "is there a skill for X?"
- Ask "can you do X?" for specialized tasks (poster design, data analysis, etc.)
- Want to search for tools, templates, or workflows
- Mention needing help with a specific domain that might have a community skill
Available Scripts
1. Search Skills — find_skills.py
Search the skills.sh ecosystem for skills matching a query.
python scripts/find_skills.py <query> [--limit N]
Example:
python scripts/find_skills.py "react performance"
python scripts/find_skills.py "docker" --limit 5
Output: JSON array of matching skills with name, source (owner/repo), installs count, and url (skills.sh link).
2. Install Skill — add_skill.py
Download a skill from GitHub and register it in Skill Compose.
python scripts/add_skill.py <owner/repo@skill-name>
Example:
python scripts/add_skill.py "vercel-labs/agent-skills@vercel-react-best-practices"
What it does:
- Parses the
owner/repo@skill-nameidentifier - Tries multiple GitHub paths to locate the skill (
skills/<name>/,<name>/, root) - Downloads all skill files (SKILL.md, scripts/, references/, assets/)
- Saves to the local
skills/directory - Registers the skill in Skill Compose via the import-local API
- The skill is immediately available for use in Agent Presets
CRITICAL: Never Combine Questions with Tool Calls
When you ask the user a question or present results for them to review, your response MUST end with text only. Do NOT include any tool call (execute_code, bash, etc.) in the same response. The user needs a chance to read and reply. If you combine a question with a tool call, the tool executes immediately without waiting — this breaks the conversation flow.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 6d ago First seen · 120 lines · 64 tokens per session scan A 8f7ac62bcf72
skill-finder is a skill published in the GitHub repository dp-archive/archive (1,106 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 64 tokens to every session and 1,136 once invoked, about $0.0003 per session on Opus 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
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…
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…