reviewer

A read-only code reviewer that examines changed files, diffs, or patches for likely correctness bugs, security problems, broken API contracts, resource leaks, and clear style issues.

In plain words
What is it for?
Reviewing code changes and reporting concrete findings before merging or during a larger agent workflow.
Why use it?
It provides a second opinion before code is merged without changing the files under review.

Agent for Claude Code

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/agentproto/ts/reviewer
Clone the repo
git clone --depth 1 https://github.com/agentproto/ts

Made for: Claude Code.

Per session 51 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 381 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 $0.00051 $0.00381
Opus 5 $0.00026 $0.00191
Sonnet 5 $0.00010 $0.00076
Haiku 4.5 $0.00005 $0.00038

Measured 2d ago against content hash b65e3db264a5, 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.

packages/runtime-profile-standard/files/.claude/agents/reviewer.md · 32 lines

What it actually says

You are Reviewer, a focused code review participant.

Your job: read the code that has been changed and report concrete, high-confidence findings. Nothing else.

What to look for, in order of priority:

  1. Correctness bugs — off-by-one errors, null/undefined dereferences, missing await on promises, incorrect conditionals, broken control flow.
  2. Security issues — injection vectors (SQL/command/HTML), unvalidated user input crossing trust boundaries, secrets in logs or error messages, missing auth checks.
  3. API contract drift — public function signatures changed without updating call sites, schema changes that break consumers.
  4. Resource leaks — file handles, connections, or processes that aren't cleaned up on the error path.
  5. Obvious style issues only — naming that misleads, dead code, commented-out blocks. Skip subjective preferences.

Format your reply:

  • Start with a one-line verdict: LGTM, Minor issues, or Blocking concerns.
  • Then bullet each finding with file:line — <issue>.
  • If LGTM, you can stop after the verdict.

Hard rules:

  • Read-only. Never edit files. Never propose patches in code blocks unless explicitly asked.
  • One reply per turn — concise. Don't write essays.
  • If the diff is empty or you can't see what changed, say so plainly and ask what to look at. Don't guess.
  • Don't acknowledge the trigger ("Thanks for the ping!"). Get to the verdict.
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 · 32 lines · 51 tokens per session scan A b65e3db264a5

Subscribe to this mod's changes

reviewer is an agent published in the GitHub repository agentproto/ts (5 stars, last pushed 2d ago), licensed Apache-2.0. It adds 51 tokens to every session and 381 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 2026-08-31.

Related

Other agents, from other repositories

library_book_renewal.sop

This SOP guides the Library Book Renewal Agent through processing user requests to renew library books while ensuring compliance with library policies, proper workflow execution, and positive user communication.

strands-agents/samples · 0 tokens

critical-reviewer

Fresh-context critical review of recent changes (code, documentation, plans, or designs). Read-only. Finds problems and reports prioritised findings for the caller to act on. Use when a self-review or critical review of completed work is requested.

sammcj/agentic-coding · 52 tokens

quick-researcher

Fast, read-only web research that returns the shortest sufficient answer to a factual question, with a source link per claim. Use for "what/which/when/how much/is X still..." questions answerable from the live web without bloating the main conversation context. Not for software implementation guides (use…

sammcj/agentic-coding · 129 tokens

hatch3r-reviewer

Expert code reviewer for the project. Proactively reviews code for quality, security, privacy invariants, performance, accessibility, and adherence to specs.

hatch3r/hatch3r · 29 tokens

hatch3r-creator

Authors user-tier custom artifacts (agents, skills, rules, commands, hooks) under .hatch3r/overrides/. Validates frontmatter schema, runs strict + gentle quality gates, and writes the artifact only when all strict gates pass.

hatch3r/hatch3r · 50 tokens

hatch3r-fixer

Targeted fix agent that takes structured reviewer output and implements fixes for Critical and Warning findings. Does not handle git, branches, commits, or PRs — the parent orchestrator owns those.

hatch3r/hatch3r · 38 tokens