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 pavelzw/skill-forge --skill pr-reviewgit clone --depth 1 https://github.com/pavelzw/skill-forgeWrote 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/pavelzw/skill-forge/pr-review)<a href="https://agentmods.dev/skills/pavelzw/skill-forge/pr-review"><img src="https://agentmods.dev/badge/skills/pavelzw/skill-forge/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/pavelzw/skill-forge/pr-review"><img src="https://agentmods.dev/badge/skills/pavelzw/skill-forge/pr-review.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 | $0.00068 | $0.01092 |
| Opus 5 | $0.00034 | $0.00546 |
| Sonnet 5 | $0.00014 | $0.00218 |
| Haiku 4.5 | $0.00007 | $0.00109 |
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 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PR Review
Use this skill when the user asks you to review a pull request. The workflow is interactive: you draft, the human refines, and only after explicit approval do you push the inline comments to GitHub as a pending review. You never submit the review — the human adds the summary and submits in the GitHub UI.
Follow the four phases in order.
Phase 1 — Review the PR as a senior engineer
Before forming opinions, read all existing comments so you don't duplicate, contradict, or ignore prior discussion:
- Conversation and inline review comments:
gh pr view <number> --comments - Existing reviews:
gh api repos/<owner>/<repo>/pulls/<number>/reviews - Pending review drafts authored by the current user:
gh pr view <number> --json reviews. If a pending review exists, treat its drafts as prior context — do not silently overwrite them.
Then review the diff (gh pr diff <number>) as a senior engineer would. Focus on:
- Logic errors — wrong conditions, off-by-one, wrong operators, missing branches.
- Edge cases — empty inputs, concurrency, partial failures, unusual but valid states.
- Maintainability — leaky abstractions, code that will be hard to evolve, missing tests for risky paths.
For each issue, articulate why it matters and propose a concrete fix, not a vague concern. Label uncertain findings as such. Skip style nits that a formatter or linter would catch.
Phase 2 — Write findings to a markdown file
Create .review/<pr-number>.md. Group findings into three sections, sorted by impact within each:
## Blocking— must be fixed before merge (correctness, security, data loss).## Important— should be addressed but not merge-blocking.## Nits— take-it-or-leave-it.
Each finding needs a stable kebab-case ID, as short as possible while still being unambiguous (e.g. commit-race, not possible-race-condition-on-commit), that the human can reference across iterations.
Template per finding:
### <id>
`path/to/file.ext:LINE` — <why it matters, one or two sentences>
> <literal comment text to post on GitHub>
What ships with it
1 file 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.
- 9d ago First seen · 80 lines · 68 tokens per session scan A b4f01c636a45
pr-review is a skill published in the GitHub repository pavelzw/skill-forge (24 stars, last pushed 2d ago), licensed BSD-3-Clause. It adds 68 tokens to every session and 1,092 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 2026-08-30.
Other skills, from other repositories
review-implement-phase
Implements triaged review actions, commits focused fixes, and posts Done plus resolves threads. Use when the user wants only the implementation phase of the review-framework workflow.
engram-branch-pr
PR creation workflow for Engram following the issue-first enforcement system. Trigger: When creating a pull request, opening a PR, or preparing changes for review.
verify-behavior
Verify or reproduce visible product behavior by driving the real UI with pi-computer-use's checked tools, requiring verified expect postconditions and durable state evidence for meaningful UI flows. Use when triage needs visual reproduction, implementation needs behavioral proof, review needs interactive confirmation…
github-contributor
End-to-end playbook for shipping high-quality pull requests to open-source projects you don't maintain — discovery, CONTRIBUTING compliance, PR-size check, minimal-diff implementation, PR description with AI-assisted disclosure, conflict resolution, and post-submission maintainer interaction. Use whenever creating…
revdiff
Review diffs, files, and documents with inline annotations in a TUI overlay, or answer questions about revdiff usage, configuration, themes, and keybindings. Opens revdiff in agterm/tmux/zellij/herdr/kitty/wezterm/cmux/ghostty/iterm2/emacs-vterm, captures annotations, and addresses them. Works in git, hg, and jj repos…
write-pr
Reference standards for writing pull request titles and descriptions in the tldraw repository, plus the pre-flight comment sweep over the diff. Use as supporting guidance when another skill or workflow needs PR content standards, not as the user-facing create/update PR workflow.