A pull-request review workflow for checking team-specific coding style, naming, and code structure. A pull request is a proposed change to a codebase that teammates inspect before merging.

It helps review GitHub pull requests or local diffs and produce structured comments about style and structure before code is merged.

It provides a second review focused on a team's conventions, including rules that generic bug-finding or security tools may not know. It is not intended to replace bug hunting, security scanning, or performance review.

pr-reviewer — Skill for Claude Code and Codex by AndrewNgGirl

Install

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.

Any agent

npx skills add AndrewNgGirl/SkillLens --skill pr-reviewer

Clone the repo

git clone --depth 1 https://github.com/AndrewNgGirl/SkillLens

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/andrewnggirl/skilllens/pr-reviewer/github.svg)](https://agentmods.dev/skills/andrewnggirl/skilllens/pr-reviewer)

Your own site

<a href="https://agentmods.dev/skills/andrewnggirl/skilllens/pr-reviewer"><img src="https://agentmods.dev/badge/skills/andrewnggirl/skilllens/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/andrewnggirl/skilllens/pr-reviewer"><img src="https://agentmods.dev/badge/skills/andrewnggirl/skilllens/pr-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 65 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,509 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00065	$0.01509
Opus 5	$0.00032	$0.00754
Sonnet 5	$0.00013	$0.00302
Haiku 4.5	$0.00006	$0.00151

Measured 7d ago against content hash a8a0ece73f02, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

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 7d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/fetch_pr.py, scripts/validate_review.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/skill-scorer/examples/pr-reviewer/SKILL.md · 128 lines

How it starts

The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.

pr-reviewer

When to use

When the user asks to review / audit / comment / 评审 / 审查 a GitHub PR by URL or local diff. Trigger phrases include:

"帮我 review 这个 PR"
"review https://github.com/.../pull/123"
"check this diff before I merge"

Not suitable for: bug-hunting (use Copilot Code Review), security scans (use CodeQL), runtime performance review.

Target users

Open-source maintainers handling 5–20 PRs/week
Small dev teams (3–8 engineers) without a dedicated reviewer
Solo developers who want a second pair of eyes on style and structure

Estimated frequency: per-PR (high-frequency, daily for active repos).

Why this skill

Unlike GitHub Copilot Code Review (focuses on bugs) or CodeQL (focuses on security), pr-reviewer focuses on team-specific style and structural conventions — the kind of rules that are written down in your team handbook but no off-the-shelf tool knows about.

Quantified value: cuts the average human "first-pass review" from ~30 min to ~5 min per PR — saves about 25 min/PR × 10 PRs/week ≈ 4 h/week per reviewer.

Inputs

Field	Type	Required	Notes
`pr_url`	string	yes	e.g. `https://github.com/owner/repo/pull/123`
`team_rules`	string	optional	path to team convention markdown; defaults to `references/default-rules.md`
`language`	enum	optional	one of `python`, `typescript`, `go`; auto-detect if omitted

Cache key: SHA-256 of (pr_url, head_sha, team_rules_hash) — same PR + same head SHA reuses cached review without re-calling the LLM.

Workflow

Fetch diff: call scripts/fetch_pr.py with pr_url → returns unified diff + file list.
Static lint: run language-specific linter (ruff / eslint / golangci-lint) for objective issues.
Style review (LLM): feed diff + team_rules to the LLM, ask for ≤ 5 most impactful style issues with line refs.
Compose comments: merge linter issues + LLM issues into JSON, deduplicated by (file, line, message_first_30_chars).
Validate output: pass through scripts/validate_review.py against assets/review.schema.json; on fail, regenerate once, then escalate to user.
Output: structured JSON ready for gh pr review --comment or copy-paste into a GitHub review.

Read the full file on GitHub · 128 lines

Files

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.

Changes

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.

7d ago First seen · 128 lines · 65 tokens per session scan A a8a0ece73f02

Subscribe to this mod's changes

pr-reviewer is a skill published in the GitHub repository AndrewNgGirl/SkillLens (75 stars, last pushed 3mo ago), licensed MIT. It adds 65 tokens to every session and 1,509 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.

Claude Code Code review Git and workflow agent-skills ai-agents ci claude cursor developer-tools github

gentle-ai-collab-perfect

Trigger: contributing to Gentleman-Programming/gentle-ai as an external collaborator. Strict issue-first workflow, honest PR bodies, contributor-vs-maintainer scope, chained-PR strategy, verification protocol, docstring coverage. Load whenever the active repo is Gentleman-Programming/gentle-ai and any part of the…

Gentleman-Programming/gentle-ai · 106 tokens

pr-reviewer

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

pr-reviewer

When to use

Target users

Why this skill

Inputs

Workflow

What ships with it

What this file has done since we first saw it

Other skills, from other repositories

gentle-ai-collab-perfect

branch-pr

work-unit-commits

chained-pr

resolve-pr-comments

review-pr