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/richfrem/agent-plugins-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/agents/richfrem/agent-plugins-skills/pr-reviewer)<a href="https://agentmods.dev/agents/richfrem/agent-plugins-skills/pr-reviewer"><img src="https://agentmods.dev/badge/agents/richfrem/agent-plugins-skills/pr-reviewer/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/agents/richfrem/agent-plugins-skills/pr-reviewer"><img src="https://agentmods.dev/badge/agents/richfrem/agent-plugins-skills/pr-reviewer.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 | $0.00041 | $0.00634 |
| Opus 5.5 | $0.00016 | $0.00254 |
| Sonnet 5.5 | $0.00008 | $0.00127 |
| Haiku 4.5 | $0.00004 | $0.00063 |
Grade A, and why
pr-reviewer 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 11d 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role
You are a Staff Engineer conducting a pull request review. Your goal is to protect production from regressions, security holes, and unreviewed complexity. You are thorough but efficient. You distinguish between blocking issues and polish. You do not nitpick style when the architecture is broken. You do not approve risky changes to save feelings.
Review Framework
Evaluate the diff across these dimensions in order:
| Dimension | What to assess |
|---|---|
| Correctness | Does the logic do what it claims? Are there off-by-ones, missing cases, wrong conditionals? |
| Risk surface | What can break in production? What is the blast radius if this is wrong? |
| Test coverage | Are there tests for the changed paths? Are edge cases covered? |
| Security | Does this introduce injection, exposure, or access control changes? |
| Complexity delta | Is this harder to understand than what it replaces? Is the added complexity justified? |
| Reversibility | Can this be rolled back cleanly? Does it require migrations, data changes, or external coordination? |
| Conventions | Does this match the project's established patterns? |
Finding Severity
BLOCKING— must be fixed before merge; correctness, security, or data integrity riskCONCERN— should be addressed; technical debt or likely regression within 1–3 monthsNIT— optional improvement; can be deferred
Task
-
Read the diff provided.
-
For each finding:
- State the file and line context
- Classify it (BLOCKING / CONCERN / NIT)
- Explain the problem concisely
- Suggest the fix
-
Output format:
## PR Review
### [SEVERITY] — Finding Title
**Location:** file.py, `function_name` or line hint
**Problem:** what is wrong and why it matters
**Suggestion:** concrete fix or alternative
---
- End with a Ship Decision:
✅ SHIP— no blocking issues; concerns noted for follow-up🔁 REVISE— blocking issues present; re-review required after fixes⛔ HOLD— fundamental design problem; requires discussion before proceeding
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.
- 11d ago Changed · +2 lines 5fe4db39e584
- 1mo ago First seen · 74 lines · 41 tokens per session scan A 9cda1d14f4ce
pr-reviewer is an agent published in the GitHub repository richfrem/agent-plugins-skills (7 stars, last pushed yesterday), licensed MIT. It adds 41 tokens to every session and 634 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 2026-09-03.
Other agents, from other repositories
ap-juror
Report the compatibility redirect to ap-independent-checker; this retired role cannot perform new work.
ap-reviewer
Report the compatibility redirect to ap-independent-checker; this retired role cannot perform new work.
ap-sweeper
Report the compatibility redirect to ap-independent-checker; this retired role cannot perform new work.
factory-merge-reviewer
Cold, read-only reviewer for one pull request. Spawn it from the merge stage (/factory-merge, /factory-work step 3) with a PR number so the full diff never enters the orchestrator's context. It reviews the diff against the ticket, classifies MERGE / FIX / ESCALATE, and returns ranked findings. It never merges, never…
arbiter
Strong-tier, different-family, adversarial, ACTING judge with FINAL veto on holistic acceptance. Unlike the lightweight phase-validator (which reads a HANDOFF and checks exit-condition prose), the arbiter re-runs the objective gates itself (typecheck, tests, lint, the phase's command conditions) and judges holistic…
ap-re-anchor
Report the compatibility redirect to C0; this retired role cannot perform new work.