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.
git clone --depth 1 https://github.com/rlespinasse/agent-skillsWrote 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/plugins/rlespinasse/agent-skills/marketplace)<a href="https://agentmods.dev/plugins/rlespinasse/agent-skills/marketplace"><img src="https://agentmods.dev/badge/plugins/rlespinasse/agent-skills/marketplace/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/plugins/rlespinasse/agent-skills/marketplace"><img src="https://agentmods.dev/badge/plugins/rlespinasse/agent-skills/marketplace.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
agent-skills marketplace 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 20d 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
{
"name": "agent-skills",
"owner": "rlespinasse",
"description": "A collection of Agent Skills for AI coding assistants",
"repository": "https://github.com/rlespinasse/agent-skills",
"skills": [
{
"name": "conventional-commit",
"path": "skills/conventional-commit",
"description": "Guides committing staged (indexed) git files using the Conventional Commits specification and commit message best practices. Use when user mentions commit, git commit, conventional commit, commit message, staged files, indexed files, fixup, fixup commit, amend, or squash. Helps craft well-structured, meaningful commit messages including fixup commits with optional autosquash. For an overview of local branches, see local-branches-status."
},
{
"name": "diataxis",
"path": "skills/diataxis",
"description": "Helps maintain documentation pages based on the Diataxis method. Analyzes existing docs, classifies pages into tutorials/how-to/explanation/reference categories, identifies gaps, and helps create or restructure documentation following Diataxis principles. Use when user mentions documentation structure, Diataxis, doc categories, tutorials vs how-to guides, or reorganizing docs. For checking README claims against code, see verify-readme-features."
},
{
"name": "drawio-export-tools",
"path": "skills/drawio-export-tools",
"description": "Decision guide for the third-party Draw.io export ecosystem by @rlespinasse. Covers docker-drawio-desktop-headless (base Docker), drawio-exporter (Rust backend), drawio-export (enhanced Docker), and drawio-export-action (GitHub Actions). Use when user mentions diagram export, CI/CD automation, batch processing, or Draw.io files. Helps select the right tool based on context. For pinning the export action in workflows, see pin-github-actions."
},
{
"name": "french-language",
"path": "skills/french-language",
"description": "Ensures all project content isWhat 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.
- 20d ago Changed f3295b6d6241
- 1mo ago Changed fc7f4e9e9da1
- 2mo ago First seen · 54 lines scan A 8620761b5eec
agent-skills marketplace is a plugin published in the GitHub repository rlespinasse/agent-skills (13 stars, last pushed yesterday), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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.
agent-skills marketplace compared with plugins from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| agent-skills marketplacerlespinasse/agent-skills | Plugin | 13 | yesterday | MIT | A | — | Claude Code |
| rosetta-lightgriddynamics/rosetta | Plugin | 375 | today | Apache-2.0 | A | — | Claude Code |
| personalanton-abyzov/vskill | Plugin | 47 | yesterday | MIT | A | — | Claude Code |
| skillsanton-abyzov/vskill | Plugin | 47 | yesterday | MIT | A | — | Claude Code |
| securityanton-abyzov/vskill | Plugin | 47 | yesterday | MIT | A | — | Claude Code |
| mem-foreverilang-ai/Mem-Forever | Plugin | 21 | yesterday | MIT | A | — | Gemini CLI |
| specopssanmak/specops | Plugin | 56 | 3mo ago | MIT | A | — | Claude Code |