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 ashermahonin/agentic-skills --skill pr-reviewgit clone --depth 1 https://github.com/ashermahonin/agentic-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/skills/ashermahonin/agentic-skills/pr-review)<a href="https://agentmods.dev/skills/ashermahonin/agentic-skills/pr-review"><img src="https://agentmods.dev/badge/skills/ashermahonin/agentic-skills/pr-review/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/ashermahonin/agentic-skills/pr-review"><img src="https://agentmods.dev/badge/skills/ashermahonin/agentic-skills/pr-review.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 | $0.00072 | $0.00460 |
| Opus 5 | $0.00036 | $0.00230 |
| Sonnet 5 | $0.00014 | $0.00092 |
| Haiku 4.5 | $0.00007 | $0.00046 |
Grade A, and why
pr-review 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 10d 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
PR Review
Purpose
Find defects and material maintenance risks before a change lands. Review behavior first; style matters only when it obscures correctness or raises change cost.
Change context
- Identify changed files and intent of the change.
- Find affected flows, contracts, data, security boundaries, and tests.
- Read the diff with the old behavior in mind.
- Look for missing validation and docs drift.
Change method
- Reconstruct the intended behavior from the request, diff, tests, and nearby contracts.
- Trace correctness, failure handling, concurrency, compatibility, migration, and rollback effects.
- Check authorization, secrets, privacy, untrusted input, and destructive operations where relevant.
- Use
engineering-qualitycriteria for responsibilities, dependencies, side effects, errors, and tests; do not turn preferences into findings. - Review performance and operations when shared or hot paths changed.
- Report findings by severity with a tight file/line reference, concrete impact, and fix direction. If none are found, state residual risk and checks not run.
Engineering constraints
- Keep review read-only unless the user also asks for fixes.
- Verify uncertain external behavior with current documentation before raising a finding.
- Do not approve behavior you could not reconstruct from code and evidence.
Evidence
- Prioritized findings with evidence
- Open questions and assumptions
- Missing or unrun validation
- Residual risk and merge recommendation
Ready when
- Findings lead the response and are ordered by impact.
- Every finding describes a plausible failure, not a hypothetical preference.
- Line references are as narrow as the evidence permits.
- A clean review still reports test gaps and residual risk.
Handoff
Hand off actionable findings to implementation or release decision with severity and evidence.
References
references/review-checklist.md: Use this checklist for reviews.
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.
- 10d ago First seen · 55 lines · 72 tokens per session scan A fdd3f5f91fca
pr-review is a skill published in the GitHub repository ashermahonin/agentic-skills (10 stars, last pushed 16d ago), licensed MIT. It adds 72 tokens to every session and 460 once invoked, about $0.0004 per session on Opus 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 2026-08-31.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…