review-pr

review-pr is a skill for Claude Code, Codex from ardanlabs/service. It costs 88 tokens per session (2,180 once invoked), scanned A, original, Apache-2.0.

A read-only pull-request and code-diff reviewer that checks correctness, errors, tests, types, contracts, and simplification across many file types.

In plain words
What is it for?
Use it for pull-request, pre-commit, unstaged-diff, or selected-file reviews, with findings ranked from clear to merge-blocking.
Why use it?
It helps find bugs, security or data problems, missing tests, misleading comments, and reliability risks without changing the code.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents; installed under .agents/ (shared by several agents); mentions AGENTS.md.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is - Go: `make test-only`, or `go test ./path/...` for a single package..

Good fit Use it for pull-request, pre-commit, unstaged-diff, or selected-file reviews, with findings ranked from clear to merge-blocking.

Compare 6 skills from other repositories ↓
About the project

ardanlabs/service is a Go starter kit for building scalable web services designed to run in Kubernetes. It provides an organized starting structure based on domain-driven and data-oriented architecture, Go practices, and a small dependency set. The catalogue skills and instruction help coding agents work with services built from this starter kit.

ardanlabs/service · 4,110 stars · on GitHub · ardanlabs.com

Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/ardanlabs/service
agentmods
npx agentmods add skills/ardanlabs/service/review-pr

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.

agentmods badge for review-pr

README.md
[![agentmods](https://agentmods.dev/badge/skills/ardanlabs/service/review-pr/github.svg)](https://agentmods.dev/skills/ardanlabs/service/review-pr)
Your own site
<a href="https://agentmods.dev/skills/ardanlabs/service/review-pr"><img src="https://agentmods.dev/badge/skills/ardanlabs/service/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.

agentmods 80×15 button for review-pr

Your own site · 80×15
<a href="https://agentmods.dev/skills/ardanlabs/service/review-pr"><img src="https://agentmods.dev/badge/skills/ardanlabs/service/review-pr.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 88 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,180 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 2 findings, 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 Prompt Injection · line 22
    Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.
    Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
  • medium Prompt Injection · line 53
    Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.
    Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
How audits are shown
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00088 $0.02180
Opus 5 $0.00044 $0.01090
Sonnet 5 $0.00018 $0.00436
Haiku 4.5 $0.00009 $0.00218

Measured 9d ago against content hash cb5fb9a85101, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

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.

.agents/skills/review-pr/SKILL.md · 180 lines

How it starts

The opening of the file, as written. The whole thing — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Service Diffguard

Service Diffguard reviews a diff with six focused lenses. Each lens runs as a read-only Amp Task subagent, inspects the requested change, and returns findings graded on one shared scale. Lenses advise only — they never edit, stage, or commit code, never disable tests, and never bypass a failing check to make it pass.

Default scope is the unstaged git diff unless the caller names specific files, a branch, a commit range, or an existing PR.

Gate scale

Every finding carries a Gate. The run's overall Gate is the highest any lens returns.

Gate Name Meaning Action
G4 Stop Likely correctness, security, data-integrity, compile, boundary, or reliability failure. Block merge until fixed.
G3 Repair Likely user-visible bug, operational blind spot, real test gap, or misleading contract. Fix before the PR is ready.
G2 Tighten Locally safe but leaves avoidable risk, ambiguity, weak design, or brittleness. Address if reasonably scoped; otherwise acknowledge.
G1 Polish Low-risk clarity, naming, comment, or small test refinement. Optional; batch, don't spam.
G0 Clear No issue, or a positive observation. None.

Every G2 or higher finding must include: file:line, Proof (evidence from the diff), why it matters, a Patch direction (smallest safe fix), and how to verify. Weak or speculative observations go under Open checks, not as a finding. Cap G1 items at five per lens unless exhaustive polish is requested.

Read the full file on GitHub · 180 lines

Files

What ships with it

6 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.

  1. 9d ago First seen · 180 lines · 88 tokens per session scan A cb5fb9a85101

Subscribe to this mod's changes

review-pr is a skill published in the GitHub repository ardanlabs/service (4,110 stars, last pushed 10d ago), licensed Apache-2.0. It adds 88 tokens to every session and 2,180 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 2026-08-30.