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 tomzx/agents --skill review-prgit clone --depth 1 https://github.com/tomzx/agentsWrote 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/tomzx/agents/review-pr)<a href="https://agentmods.dev/skills/tomzx/agents/review-pr"><img src="https://agentmods.dev/badge/skills/tomzx/agents/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/tomzx/agents/review-pr"><img src="https://agentmods.dev/badge/skills/tomzx/agents/review-pr.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
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 →
- high Prompt Injection · line 283 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
- high Tool Misuse · line 449 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
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 | $0.00061 | $0.04928 |
| Opus 5 | $0.00030 | $0.02464 |
| Sonnet 5 | $0.00012 | $0.00986 |
| Haiku 4.5 | $0.00006 | $0.00493 |
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 6d 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 — 450 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review Pull Request
Answers the craft question: "is this code well-built?" Covers code quality, architecture, security, tests, and operational concerns as static inspection. It does not build or run the code (that is /verify-pr's conformance role) and does not judge whether the target is the right product (that is /validate-pr's validation role). Findings about whether the criteria are met go to /verify-pr; findings about whether the right problem is solved go to /validate-pr. Writes findings to a structured markdown file.
Prerequisites
- Apply the shared SDLC conventions in
skills/sdlc/references/shared.md. - If no argument is provided, target the pull request from
$PR_NUMBER(and$REPO). ghCLI authenticated with read access to the target repositorygit worktreeavailable- PR number (
$1) identifying an open pull request
Skill attribution (GitHub)
Before posting to GitHub, read ../github-post-attribution/SKILL.md and append the footer for SKILL_DIR = review-pr.
Workflow
Fetch PR metadata + comments ($1)
|
v
Create git worktree on PR branch
|
v
Pre-Review Checklist
(build, metadata, objective)
|
v
Code Review Checklist
(quality, tests, architecture,
ops, security, docs)
|
v
Context-Specific Review
(feature / bug fix / DB / API?)
|
v
Write review-pr.$SHORT_SHA.md
(create or update)
|
v
Post review file
as PR comment
(gated by should-post-to-github)
Setup
Fetch PR information by piping the raw ghx output directly to a file (do not generate or summarize the content). PR review reports resolve to $HOME/.sdlc/$REPO/pull-requests/$PR_NUMBER/ per sdlc/references/shared.md (PR Review Reports):
PR_REVIEW_DIR="$HOME/.sdlc/$REPO/pull-requests/$PR_NUMBER"
mkdir -p "$PR_REVIEW_DIR"
ghx pr view $1 --repo "$REPO" --comments --refresh > "$PR_REVIEW_DIR/gh-pr-view.md"
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.
- 6d ago First seen · 450 lines · 61 tokens per session scan A dd0eed9c2803
review-pr is a skill published in the GitHub repository tomzx/agents (6 stars, last pushed yesterday), licensed MIT. It adds 61 tokens to every session and 4,928 once invoked, about $0.0003 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 2026-09-03.
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.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.