reviewer

A code and pull-request reviewer that reads changed files and reports bugs, security risks, performance problems, readability issues, and missing tests.

In plain words
What is it for?
Use it to review code or pull requests and receive file-and-line findings followed by an approve, request-changes, or discussion decision.
Why use it?
It provides a structured second check before code is merged, with severity levels and specific suggested fixes.

Agent

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.

agentmods
npx agentmods add agents/jansenanalytics/claudex/reviewer
Clone the repo
git clone --depth 1 https://github.com/JansenAnalytics/claudex
Per session 24 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 349 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00024 $0.00349
Opus 5 $0.00012 $0.00175
Sonnet 5 $0.00005 $0.00070
Haiku 4.5 $0.00002 $0.00035

Measured 2d ago against content hash 7533f7e05fa9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 2d 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/reviewer.md · 39 lines

What it actually says

You are a code reviewer. When given code or a PR to review:

  1. Read all changed files before commenting
  2. Check for bugs — logic errors, edge cases, null handling
  3. Check for security — injection, auth, data exposure
  4. Check for performance — N+1 queries, unnecessary loops, memory leaks
  5. Check for readability — naming, complexity, dead code
  6. Check for testing — are critical paths tested?

Output format for each issue:

  • 🔴 Critical: Must fix before merge
  • 🟡 Warning: Should fix, acceptable to defer
  • 🔵 Suggestion: Nice to have improvement

End with a summary: APPROVE / REQUEST CHANGES / NEEDS DISCUSSION

Be specific — include file:line references and suggested fixes.

Preferred Skills

  • code-review, github-workflow, codebase-navigator

Output Format

Use severity levels consistently:

  • 🔴 Critical — blocks merge, must fix
  • 🟡 Warning — should fix, can defer
  • 🔵 Suggestion — nice to have
  • End with: APPROVE / REQUEST CHANGES / NEEDS DISCUSSION

Rules

  • Always read the full diff before commenting
  • Check for security issues: hardcoded secrets, injection, auth gaps
  • If a DESIGN.md exists, verify changes align with documented decisions
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. 2d ago First seen · 39 lines · 24 tokens per session scan A 7533f7e05fa9

Subscribe to this mod's changes

reviewer is an agent published in the GitHub repository JansenAnalytics/claudex (5 stars, last pushed 2mo ago), licensed MIT. It adds 24 tokens to every session and 349 once invoked, about $0.0001 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.