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 PolicyEngine/policyengine-claude --skill policyengine-github-agentgit clone --depth 1 https://github.com/PolicyEngine/policyengine-claudeWrote 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/policyengine/policyengine-claude/policyengine-github-agent)<a href="https://agentmods.dev/skills/policyengine/policyengine-claude/policyengine-github-agent"><img src="https://agentmods.dev/badge/skills/policyengine/policyengine-claude/policyengine-github-agent/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/policyengine/policyengine-claude/policyengine-github-agent"><img src="https://agentmods.dev/badge/skills/policyengine/policyengine-claude/policyengine-github-agent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00091 | $0.00547 |
| Opus 5.5 | $0.00036 | $0.00219 |
| Sonnet 5.5 | $0.00018 | $0.00109 |
| Haiku 4.5 | $0.00009 | $0.00055 |
Grade A, and why
policyengine-github-agent 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.
What it actually says
PolicyEngine GitHub agent
For Users
The PolicyEngine GitHub agent is an automated bot that can be invoked on GitHub issues and pull requests using @policyengine mentions. It helps with code reviews, bug fixes, and implementing features across PolicyEngine repositories.
For Contributors
Critical: Avoiding Doom Loops
NEVER use '@policyengine' or '@policyengine-auto' in bot responses. These mentions trigger the bot and create infinite loops where the bot repeatedly responds to itself.
Why This Matters
When the bot posts a comment containing @policyengine, GitHub notifies the bot account, which triggers another invocation. This creates a chain reaction of bot responses that can generate dozens or hundreds of comments before being stopped. See PR #22 for a real example of this issue.
Safe Alternatives
Instead of mentioning the bot directly:
❌ Don't do this:
- "Thanks @policyengine for the suggestion!"
- "I've addressed @policyengine's feedback"
- "cc @policyengine-auto"
✅ Do this instead:
- "I've implemented the suggested changes"
- "The feedback has been addressed"
- "Updated based on the review comments"
- Simply refer to "the bot" or "the agent" without the @ mention
Bot Invocation
The bot can only be invoked by members of the PolicyEngine/core-developers team. Non-members will receive a permission error.
Response Style
When the bot responds to issues or PRs:
- Keep responses concise and actionable
- Focus on the technical task at hand
- Avoid unnecessary pleasantries or acknowledgments
- Never include @ mentions of the bot usernames
Resources
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 · 59 lines · 91 tokens per session scan A 4f7f3d22bf07
policyengine-github-agent is a skill published in the GitHub repository PolicyEngine/policyengine-claude (31 stars, last pushed yesterday), licensed MIT. It adds 91 tokens to every session and 547 once invoked, about $0.0004 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 2026-08-30.
policyengine-github-agent compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| policyengine-github-agentPolicyEngine/policyengine-claude | Skill | 31 | yesterday | MIT | A | 91 | Claude Code |
| imagegenopenai/codex | Skill | 134k | today | Apache-2.0 | A | 113 | Codex |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 2d ago | MIT | A | 200 | Claude Code, Codex |
| playwright-climicrosoft/playwright | Skill | 100k | today | Apache-2.0 | A | 19 | Claude Code |
| browser-automationopenclaw/openclaw | Skill | 394k | today | MIT | A | 36 | Claude Code |
| systematic-debuggingobra/superpowers | Skill | 315k | 6d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 95 | Claude Code |