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 fix-prgit 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/fix-pr)<a href="https://agentmods.dev/skills/policyengine/policyengine-claude/fix-pr"><img src="https://agentmods.dev/badge/skills/policyengine/policyengine-claude/fix-pr/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/fix-pr"><img src="https://agentmods.dev/badge/skills/policyengine/policyengine-claude/fix-pr.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 | $0.00046 | $0.00477 |
| Opus 5.5 | $0.00018 | $0.00191 |
| Sonnet 5.5 | $0.00009 | $0.00095 |
| Haiku 4.5 | $0.00005 | $0.00048 |
Grade A, and why
fix-pr 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
fix-pr
Thin launcher. The canonical workflow — phases, roles, consent gates, verification gates, artifact contracts — lives in references/workflow.md. Read it completely before acting and follow it exactly; this file only adapts it to this surface. Do not redefine flags, phases, ownership, or gates here.
Treat the text after $fix-pr as the raw workflow arguments:
$fix-pr [PR_NUMBER_OR_SEARCH] [--local] [--resume] [--full-validation]
Hard rules restated from the canonical workflow (they cannot be skipped on any surface):
- Determine the PR first, then ask about push/post mode unless
--localis set. - No edit before the user-approved fix plan file exists; fix only what it lists.
- Never push while a verification gate is red.
- Never read full review reports into the main context; use the short handoff files.
Surface adapters:
- Claude Code: also read references/claude-launcher.md — it maps canonical roles to this plugin's agent types and the workflow's abstract operations to Claude Code mechanics.
- Codex: use the delegation mapping below.
Delegation mapping (when subagent use is available and authorized):
- Map every role in the canonical Roles table to a
workerwhen it edits files or writes reports, or anexplorerfor read-only codebase questions. - Pass concrete
RUN_ROOT,WORKTREE_ID, andPREFIXvalues and the role's task spec from the canonical workflow to every subagent; name the role's skills explicitly in the subagent prompt. - Respect the canonical ownership table — no worker edits outside its assigned files; only the fix-pusher role commits or pushes.
- If subagents are unavailable or not authorized, execute the roles directly in phase order, preserving the same handoff files and gates.
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.
- 2mo ago First seen · 47 lines · 46 tokens per session scan A bdcfae7759db
fix-pr is a skill published in the GitHub repository PolicyEngine/policyengine-claude (31 stars, last pushed yesterday), licensed MIT. It adds 46 tokens to every session and 477 once invoked, about $0.0002 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.
fix-pr compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| fix-prPolicyEngine/policyengine-claude | Skill | 31 | yesterday | MIT | A | 46 | Claude Code |
| prYeachan-Heo/oh-my-claudecode | Skill | 41k | today | MIT | A | 47 | Claude Code |
| merge-batchdiegosouzapw/OmniRoute | Skill | 85k | yesterday | MIT | A | 46 | Claude Code |
| otto-pr-review-loopomnigent-ai/omnigent | Skill | 11k | today | Apache-2.0 | A | 17 | Claude Code, Codex |
| engram-branch-prGentleman-Programming/engram | Skill | 7.9k | today | MIT | A | 37 | Claude Code, Codex |
| github-contributordaymade/claude-code-skills | Skill | 1.5k | today | MIT | A | 105 | Claude Code, Codex |
| revdiffumputun/revdiff | Skill | 949 | today | MIT | A | 250 | Claude Code |