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 flurdy/agent-skills --skill review-prgit clone --depth 1 https://github.com/flurdy/agent-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/flurdy/agent-skills/review-pr)<a href="https://agentmods.dev/skills/flurdy/agent-skills/review-pr"><img src="https://agentmods.dev/badge/skills/flurdy/agent-skills/review-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/flurdy/agent-skills/review-pr"><img src="https://agentmods.dev/badge/skills/flurdy/agent-skills/review-pr.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 95 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00031 | $0.02299 |
| Opus 5 | $0.00015 | $0.01149 |
| Sonnet 5 | $0.00006 | $0.00460 |
| Haiku 4.5 | $0.00003 | $0.00230 |
Grade A, and why
review-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 9d 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 — 266 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review Pull Request
Review one immutable GitHub pull-request snapshot. The workflow is read-only: it never submits a GitHub review, approval, change request, comment, Slack message, Jira mutation, checkout change, or other external action. No GitHub review is ever submitted by this skill.
Usage
/review-pr # current branch
/review-pr 123 # current-repository shorthand
/review-pr owner/repo#123 # repository-qualified
/review-pr https://github.com/owner/repo/pull/123 # PR URL
/review-pr owner/repo#123 --automation --premium-established --expected-head SHA
Accept a PR URL, owner/repo#number, a numeric current-repository shorthand, or no selector. A
qualified selector never derives repository identity from the current working directory.
Optional controls:
--expected-headSHA — require the selected immutable head.--checkoutPATH — consider this local checkout, but use it only after exact verification.--automation— return the machine-readable contract below and never ask a question.--premium-established— assert that the caller selected the premium route before automation.--deadline-seconds N— total attended review budget; default 300 seconds. Record one absolute stop deadline at invocation, pass only the remaining seconds to each collector call, and return partial evidence when the budget expires.
1. Establish the premium route
This skill is model-tier: premium.
For a manual invocation below the premium tier, use AskUserQuestion once:
- Continue here — accept reduced depth for this run.
- Stop — switch model or rerun in a premium session.
Skip the question when the user explicitly selected the current model.
For --automation, the skill must not prompt. Require --premium-established and confirm the
current route satisfies the premium tier. If either condition fails, return status: failed,
reason: premium-route-unavailable, and no verdict. Frontmatter alone is not route attestation.
What ships with it
9 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.
- scripts/gh-pr-checks.sh 817 B runs code
- scripts/gh-pr-comments.sh 2.2 KB runs code
- scripts/gh-pr-current-number.sh 60 B runs code
- scripts/gh-pr-diff.sh 278 B runs code
- scripts/gh-pr-snapshot.py 30 KB runs code
- scripts/gh-pr-view.sh 495 B runs code
- tests/test_snapshot.py 23 KB runs code
- tests/test-skill-contract.sh 1.5 KB runs code
- tests/test-wrappers.sh 2.1 KB runs code
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.
- 9d ago First seen · 266 lines · 31 tokens per session scan A 94d649612d3c
review-pr is a skill published in the GitHub repository flurdy/agent-skills (9 stars, last pushed 2d ago), licensed MIT. It adds 31 tokens to every session and 2,299 once invoked, about $0.0002 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…