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/EvilFreelancer/rpa-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/evilfreelancer/rpa-skills/marketplace)<a href="https://agentmods.dev/plugins/evilfreelancer/rpa-skills/marketplace"><img src="https://agentmods.dev/badge/plugins/evilfreelancer/rpa-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/evilfreelancer/rpa-skills/marketplace"><img src="https://agentmods.dev/badge/plugins/evilfreelancer/rpa-skills/marketplace.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
rpa-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 7d 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 — 206 lines — stays where its author put it; the contents beside it link to each section on GitHub.
{
"name": "rpa-skills",
"owner": {
"name": "Pavel Rykov",
"email": "[email protected]"
},
"metadata": {
"description": "Pavel Rykov's agent-skills marketplace for Claude Code, OpenAI Codex, Cursor, Kimi Code CLI and other agents.",
"version": "2.8.2"
},
"plugins": [
{
"name": "rpa-init",
"source": {
"source": "url",
"url": "https://github.com/EvilFreelancer/rpa-init.git",
"ref": "main"
},
"description": "Warm up context on a repository: optionally git pull first, then study code, docs and tests, set up the dev environment, run tests, write a short report. No extra brief required.",
"version": "1.0.2",
"category": "workflow",
"license": "MIT"
},
{
"name": "rpa-gen-rules",
"source": {
"source": "url",
"url": "https://github.com/EvilFreelancer/rpa-gen-rules.git",
"ref": "main"
},
"description": "Use when the user invokes /rpa-gen-rules or asks to create, refresh, audit, or synchronize project instructions such as root AGENTS.md, Cursor .cursor/rules, or Claude Code .claude/rules, especially when existing rule trees have drifted.",
"version": "1.3.4",
"category": "workflow",
"license": "MIT"
},
{
"name": "rpa-feat",
"source": {
"source": "url",
"url": "https://github.com/EvilFreelancer/rpa-feat.git",
"ref": "main"
},
"description": "Add a feature strictly by BDD: plan, red tests, green implementation, full suite, docs and examples, linter at the end. Requires a clear feature description.",
"version": "1.0.1",
"category": "workflow",
"license": "MIT"
},
{
"name": "rpa-bugfix",
"source": {
"source": "url",
"url": "https://github.com/EvilFreelancer/rpa-bugfix.git",
"ref": "main"
},
"description": "Fix a bug with a reproduction test first, then the fix, then the full suite, theWhat 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.
- 7d ago Changed · +12 lines 1ad49af4e66f
- 10d ago Changed 25daaa6b5930
- 18d ago Changed 3b51c656e659
- 21d ago Changed c6cb40ea6026
- 22d ago Changed · +36 lines 1de8942ac705
- 29d ago Changed · +12 lines 573f7785feba
- 1mo ago Changed a0bd7a44cf13
- 1mo ago Changed · +12 lines ab50c1c2bd2f
- 1mo ago Changed 6ad0cb539d4c
- 1mo ago First seen · 134 lines scan A 10fdc225fa4b
rpa-skills marketplace is a plugin published in the GitHub repository EvilFreelancer/rpa-skills (40 stars, last pushed 8d ago), 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 2026-08-30.
rpa-skills marketplace compared with plugins from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| rpa-skills marketplaceEvilFreelancer/rpa-skills | Plugin | 40 | 8d ago | MIT | A | — | Claude Code |
| xcode-build-skillsAvdLee/Xcode-Build-Optimization-Agent-Skill | Plugin | 1.3k | 1mo ago | MIT | A | — | Claude Code |
| anycapanycap-ai/anycap | Plugin | 51 | 19d ago | MIT | A | — | Claude Code |
| svixsvix/ai | Plugin | 18 | 6d ago | MIT | A | — | Claude Code |
| bench-creatorEvanLuo42/bench-creator | Plugin | 5 | 3mo ago | MIT | A | — | Claude Code |
| skills-analyticshardness1020/claude-skills-management | Plugin | 5 | 7mo ago | MIT | A | — | Claude Code |
| iconsFortAwesome/fontawesome-agent-tools | Plugin | 4 | 4mo ago | none | A | — | Claude Code |