Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/PolicyEngine/policyengine-claudenpx agentmods add skills/policyengine/policyengine-claude/policyengine-plugin-maintenanceWrote 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-plugin-maintenance)<a href="https://agentmods.dev/skills/policyengine/policyengine-claude/policyengine-plugin-maintenance"><img src="https://agentmods.dev/badge/skills/policyengine/policyengine-claude/policyengine-plugin-maintenance/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-plugin-maintenance"><img src="https://agentmods.dev/badge/skills/policyengine/policyengine-claude/policyengine-plugin-maintenance.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 | $0.00126 | $0.01776 |
| Opus 5.5 | $0.00050 | $0.00710 |
| Sonnet 5.5 | $0.00025 | $0.00355 |
| Haiku 4.5 | $0.00013 | $0.00178 |
Grade C, and why
policyengine-plugin-maintenance scanned grade C with 1 finding 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf ~/.claude/plugins/cache/policyengine-claude How it starts
The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Maintaining the PolicyEngine skills catalog
This skill is for maintaining the skills SOURCE repo and the Claude wrapper — not for using PolicyEngine.
Repository shape (rebuilt)
Flat, category-tagged skills compiled into install profiles, then rendered into per-target wrappers.
skills/<name>/SKILL.md— one flat directory per skill (nodomain-knowledge/,tools-and-apis/nesting). Frontmatter isname(equal to the dir name), adescription:block that carries trigger phrases and stays under 1024 characters (hard Codex limit), andmetadata.category. Supporting files sit beside SKILL.md — e.g.skills/policyengine-content/templates/social-image.html.bundles/*.json— install profiles. Each lists the skills, commands, and agents it ships by path.complete.jsonis the recommended everything bundle; the rest are scoped (essential, country-models, analysis-tools, app-development, api-development, data-science, dashboard-builder, content).targets/claude/— the Claude wrapper source:marketplace.template.json,agents/,commands/,hooks/hooks.json,lessons/.targets/codex/is the Codex target.scripts/build_claude_wrapper.py— compiles the bundles and marketplace template into the generatedpolicyengine-claudemarketplace, validating that every referenced skill, command, and agent path exists (and normalizing plugin entries for the current Claude Code schema).presets/,analyses/,dashboard/,mcp/— analysis infrastructure consumed by the commands and agents.
Build and publish
CI (.github/workflows/test.yml) runs uv run pytest and smoke-builds the wrapper on every PR.
On merge to main, sync-claude.yml builds the wrapper and rsyncs it into
PolicyEngine/policyengine-claude — the marketplace repo users actually install — committing as
the sync bot. Build and test locally with:
uv run pytest # full lint + unit suite
python3 scripts/build_claude_wrapper.py --source-root . --output-root build/policyengine-claude
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 · 136 lines · 126 tokens per session scan C 07c496bb8d3b
policyengine-plugin-maintenance is a skill published in the GitHub repository PolicyEngine/policyengine-claude (31 stars, last pushed yesterday), licensed MIT. It adds 126 tokens to every session and 1,776 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
policyengine-plugin-maintenance compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| policyengine-plugin-maintenancePolicyEngine/policyengine-claude | Skill | 31 | yesterday | MIT | C | 126 | 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 |