review-pr-ci

review-pr-ci is a command for Claude Code from joris887/exosuit. It costs 0 tokens per session (460 once invoked), scanned A, original, MIT.

A read-only pull-request review command for continuous integration, the automated system that tests code changes. It examines changed files, tests, code quality, and common security issues, then posts a structured comment on the pull request.

In plain words
What is it for?
Use it in CI to review a branch against the main branch, check its tests and dependencies, scan for vulnerabilities, and publish findings with severity and confidence.
Why use it?
It gives a repeatable review of proposed changes without editing the repository, helping teams catch missing tests, weakened checks, complexity, and security mistakes.

Command for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions Claude Code.

Part of the exosuit plugin — 44 skills, 1 command, 9 agents, 10 hooks shipped together

Good fit Use it in CI to review a branch against the main branch, check its tests and dependencies, scan for vulnerabilities, and publish findings with severity and confidence.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/joris887/exosuit/review-pr-ci
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.

Clone the repo
git clone --depth 1 https://github.com/joris887/exosuit

Made for: Claude Code.

Or install exosuit, the plugin that ships this one along with the rest of its 44 skills, 1 command, 9 agents, 10 hooks.

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-ci

README.md
[![agentmods](https://agentmods.dev/badge/commands/joris887/exosuit/review-pr-ci/github.svg)](https://agentmods.dev/commands/joris887/exosuit/review-pr-ci)
Your own site
<a href="https://agentmods.dev/commands/joris887/exosuit/review-pr-ci"><img src="https://agentmods.dev/badge/commands/joris887/exosuit/review-pr-ci/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-ci

Your own site · 80×15
<a href="https://agentmods.dev/commands/joris887/exosuit/review-pr-ci"><img src="https://agentmods.dev/badge/commands/joris887/exosuit/review-pr-ci.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 460 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 $0.00000 $0.00460
Opus 5 $0.00000 $0.00230
Sonnet 5 $0.00000 $0.00092
Haiku 4.5 $0.00000 $0.00046

Measured 9d ago against content hash ab4c774cf981, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

review-pr-ci 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.

.claude/commands/review-pr-ci.md · 67 lines

What it actually says

CI PR Review

Non-interactive PR review for CI/CD context. Read-only analysis — no edits.

Process

  1. Discover PR scope:

    git diff --stat main...HEAD
    git diff --name-only main...HEAD
    git log main..HEAD --oneline
    
  2. Code quality analysis:

    • Check cyclomatic complexity of changed functions (flag >10)
    • Identify duplicated code blocks (>10 lines)
    • Verify pattern consistency with existing codebase
    • Check error handling in new code paths
  3. Test validation:

    • Verify test files exist for new source files
    • Check for weakened assertions (toBeTruthy replacing specific checks)
    • Check for deleted or skipped tests
    • Verify assertion density (≥1.5 per test)
  4. Security scan:

    • Scan changed files for hardcoded secret patterns
    • Check imported packages exist in dependency files
    • Verify input validation on user-facing code
    • Check CWE top 10 patterns (injection, XSS, path traversal)
  5. Post structured review as PR comment:

## Claude Code Review

### Summary
[1-3 sentences on overall quality]

### Findings
| Severity | File | Line | Issue | Confidence |
|----------|------|------|-------|------------|
| [HIGH/MED/LOW] | [path] | [line] | [description] | [0-100] |

### Test Coverage
- New files with tests: [X/Y]
- Assertion density: [X.X]
- Degradation detected: [yes/no]

### Security
- Secret patterns: [PASS/findings]
- Dependency check: [PASS/findings]
- Input validation: [PASS/findings]

### Verdict: [APPROVE / REQUEST_CHANGES / COMMENT]
[One-line rationale]

Only report findings with confidence ≥80 as actionable. Lower confidence goes in a Notes section.

Rules

  • NEVER edit files or create commits
  • NEVER approve PRs that fail security checks (≥80 confidence)
  • ALWAYS provide file:line references for findings
  • ALWAYS run fresh analysis — never use cached results
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 · 67 lines · 0 tokens per session scan A ab4c774cf981

Subscribe to this mod's changes

review-pr-ci is a command published in the GitHub repository joris887/exosuit (4 stars, last pushed 20d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 460 tokens. 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.

Related

Other commands, from other repositories

audit-agents-skills

Audit quality of agents, skills, and commands in a Claude Code project.

FlorianBruniaux/claude-code-ultimate-guide · 20 tokens

review

Command "review" from owainlewis/youtube-tutorials, covering review, target, instructions, simplicity and clarity.

owainlewis/youtube-tutorials · 0 tokens

review

Run a code review on changed files (or a path you pass).

wesammustafa/opencode-primer · 14 tokens

pr-review

Revisión automatizada de Pull Requests con análisis de coverage, seguridad y conformidad con specs. Usa cuando el usuario dice "revisar PR", "PR review", "pull request review", "review this PR", "analizar PR", "GitHub PR", "merge request", "code review PR", "checar PR antes de merge". Analiza coverage diff, security…

doncheli/don-cheli-sdd · 86 tokens

revisar

Peer review estricto de código con análisis de rendimiento, arquitectura, seguridad y cumplimiento. Usa cuando el usuario dice "revisar código", "code review", "peer review", "revisame este archivo", "review my code", "analizar código", "revisar PR", "revisar feature". Incluye análisis de performance, security OWASP…

doncheli/don-cheli-sdd · 82 tokens

tech-debt

Detectar y cuantificar deuda técnica con clasificación. Usa cuando el usuario dice "deuda técnica", "technical debt", "code smells", "refactorizar", "tech debt", "code rot", "spaghetti code", "duplicación", "complejidad ciclomática", "mantenibilidad". Incluye clasificación especial para AI slop. Genera reporte con…

doncheli/don-cheli-sdd · 84 tokens