agentmods.dev

review-pr

review-pr is a skill for Claude Code from felipearomani/claude-shipyard. It costs 225 tokens per session (4,177 once invoked), scanned A, original, MIT.

A pull-request review workflow that runs several independent code reviewers, applies their findings, and repeats the checks until the pull request is clean or a limit is reached. A pull request is a proposed code change awaiting review before it is merged.

In plain words
What is it for?
Use it to harden an existing GitHub pull request, resolve review findings, rebase a stale branch, and verify the result before merge.
Why use it?
It helps catch issues before merging and avoids stopping after the first round of feedback. It also checks conditions such as branch freshness, authentication, and uncommitted changes.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the fleet plugin — 4 skills, 3 agents shipped together

not rated 1repo 10d ago A scan 225 tokens original MIT

Good fit Use it to harden an existing GitHub pull request, resolve review findings, rebase a stale branch, and verify the result before merge.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/felipearomani/claude-shipyard/review-pr
View source ↗ felipearomani/claude-shipyard
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 felipearomani/claude-shipyard --skill review-pr
Clone the repo
git clone --depth 1 https://github.com/felipearomani/claude-shipyard

Made for: Claude Code.

Or install fleet, the plugin that ships this one along with the rest of its 4 skills, 3 agents.

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/felipearomani/claude-shipyard/review-pr/github.svg)](https://agentmods.dev/skills/felipearomani/claude-shipyard/review-pr)
Your own site
<a href="https://agentmods.dev/skills/felipearomani/claude-shipyard/review-pr"><img src="https://agentmods.dev/badge/skills/felipearomani/claude-shipyard/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/felipearomani/claude-shipyard/review-pr"><img src="https://agentmods.dev/badge/skills/felipearomani/claude-shipyard/review-pr.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 225 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,177 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00225 $0.04177
Opus 5 $0.00112 $0.02089
Sonnet 5 $0.00045 $0.00835
Haiku 4.5 $0.00022 $0.00418

Measured 10d ago against content hash 2351a29e20c8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, 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 10d 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.

plugins/fleet/skills/review-pr/SKILL.md · 381 lines

How it starts

The opening of the file, as written. The whole thing — 381 lines — stays where its author put it; the contents beside it link to each section on GitHub.

review-pr

A multi-reviewer hardening loop for an open pull request. Each iteration runs the reviewers in parallel, applies every surfaced issue (even minor ones), and re-runs until clean or the iteration cap is hit.

You are operating autonomously once invoked — no confirmation prompts before commit, push or thread resolution. The hard stops are a git conflict during rebase and an unresolvable disagreement between reviewers.

When NOT to run

Refuse and ask the user to clarify if:

  • No PR exists for the current branch and no argument was given.
  • The PR is closed, merged, or a draft — code review is not useful yet.
  • gh auth status fails.
  • The working tree has uncommitted changes — commit or stash first; this skill rewrites history.
  • A rebase / merge / cherry-pick is mid-flight.

Inputs

/fleet:review-pr                  # the current branch's PR
/fleet:review-pr 123              # explicit PR number
/fleet:review-pr https://github.com/org/repo/pull/123   # explicit URL
/fleet:review-pr 123 --spec path/to/spec.md   # explicit spec for the parity audit

Resolve the PR with gh pr view [<arg>] --json number,headRefName,baseRefName,headRefOid,state,isDraft,url,repository. Capture number, head_branch, base_branch, head_sha and nameWithOwner — you need them throughout.

The loop

PHASE 0   — Identify the PR + preflight
PHASE 1   — Stale check + rebase onto base (iteration 1 only)
PHASE 2   — Comment triage snapshot (iteration 1 only)
PHASE 2.5 — Locate a spec, if there is one (iteration 1 only)
LOOP iteration in 1..5:
  PHASE 3 — Run the reviewers IN PARALLEL
  PHASE 4 — Consolidate + dedupe findings
  PHASE 5 — Apply fixes
  PHASE 6 — Lint / format
  PHASE 7 — Conventional commit + force-with-lease push
  PHASE 8 — Resolve / reply on the PR threads
  PHASE 9 — Exit decision: clean and iteration >= 2? exit. Else continue.
PHASE 10  — Final summary

Track the phases so progress is visible. A minimum of 2 iterations even if iteration 1 comes back clean — iteration 2 verifies that iteration 1's fixes did not introduce new problems. Hard cap 5.

Read the full file on GitHub · 381 lines

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. 10d ago First seen · 381 lines · 225 tokens per session scan A 2351a29e20c8

Subscribe to this mod's changes

review-pr is a skill published in the GitHub repository felipearomani/claude-shipyard (1 stars, last pushed 10d ago), licensed MIT. It adds 225 tokens to every session and 4,177 once invoked, about $0.0011 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.

Claude CodeCode reviewMulti-Agentagent-orchestrationai-agentsclaude-code-pluginclaude-plugin-marketplace
Related

Other skills, from other repositories

improve

Autonomous quality improvement loop. Scores a target against a rubric, selects the highest-leverage axis, attacks it, verifies, documents, and loops. No pre-planning between iterations — each loop re-scores from scratch.

SethGammon/Citadel · 48 tokens

triage

GitHub issue and PR investigator. Pulls open issues/PRs, classifies them, searches the codebase for root cause or reviews contributed code, proposes fixes with file:line references, and optionally implements fixes. Use for investigating GitHub issues and reviewing PRs; do NOT use for general code review unrelated to…

SethGammon/Citadel · 71 tokens

review

5-pass structured code review — correctness, security, performance, readability, consistency.

SethGammon/Citadel · 17 tokens

great_cto

Use when the CTO describes a feature, task, or project goal. Orchestrates the full SDLC pipeline automatically based on project type.

avelikiy/great_cto · 32 tokens

skeptical-triage

Reusable 3-round self-challenge + arbiter pattern for filtering false positives from findings/verdicts. Use when the cost of a false-positive gate block exceeds the cost of 4 extra LLM turns.

avelikiy/great_cto · 49 tokens

vertical-real-estate

Residential-proptech domain knowledge so architect / pm aren't naive when speccing real-estate products (listings, lead-crm, transaction-coordination, property-mgmt). Codifies MLS/IDX reality, listing status lifecycle + syndication canonical-source, long-cycle lead nurture, transaction-coordination as the high-pain…

avelikiy/great_cto · 99 tokens