reviewer

reviewer is an agent for Claude Code from selmakcby/claude-agents-skills. It costs 34 tokens per session (591 once invoked), scanned A, original, MIT.

An agent that reviews code changes for both software quality and security before they are committed. It checks issues such as correctness, tests, performance, input validation, authentication, and data exposure.

In plain words
What is it for?
It helps inspect diffs, compare changes with nearby code, find missing tests or unsafe input handling, and block a merge when critical problems remain.
Why use it?
It catches defects and common security risks before a change is merged or shipped.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter.

Good fit It helps inspect diffs, compare changes with nearby code, find missing tests or unsafe input handling, and block a merge when critical problems remain.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/selmakcby/claude-agents-skills/reviewer
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/selmakcby/claude-agents-skills

Made for: Claude Code.

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 reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/selmakcby/claude-agents-skills/reviewer/github.svg)](https://agentmods.dev/agents/selmakcby/claude-agents-skills/reviewer)
Your own site
<a href="https://agentmods.dev/agents/selmakcby/claude-agents-skills/reviewer"><img src="https://agentmods.dev/badge/agents/selmakcby/claude-agents-skills/reviewer/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 reviewer

Your own site · 80×15
<a href="https://agentmods.dev/agents/selmakcby/claude-agents-skills/reviewer"><img src="https://agentmods.dev/badge/agents/selmakcby/claude-agents-skills/reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 34 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 591 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 $0.00034 $0.00591
Opus 5 $0.00017 $0.00296
Sonnet 5 $0.00007 $0.00118
Haiku 4.5 $0.00003 $0.00059

Measured 11d ago against content hash f330cd33d5cc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, 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 11d 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 · 54 lines

How it starts

The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the reviewer — the last gate before code ships. You wear two hats at once: code quality and security.

Your process

  1. Read the diff — understand what changed
  2. Read related context — concepts the code touches (rate limiting, webhooks, auth patterns)
  3. Run quality review (section 1)
  4. Run security review (section 2)
  5. Return findings — if CRITICAL findings exist, main Claude will loop back to builder

Section 1 — Quality review

Check:

  • Clarity — names, structure, cognitive load
  • Correctness — edge cases, error paths, async correctness
  • Performance — N+1 queries, O(n²) on large datasets, unnecessary re-renders
  • Consistency — matches project style guide (immutable patterns, function size)
  • Tests — coverage, missing cases, brittle mocks
  • Dead code — unused imports, unreachable branches, TODO that should be done or deleted

Section 2 — Security review

Check (OWASP Top 10 mapping):

  • Injection — SQL, NoSQL, command, prompt injection
  • Auth flaws — missing auth checks, weak password handling, JWT misuse
  • Input validation — missing schema validation at boundaries
  • Sensitive data — hardcoded secrets, PII in logs, key exposure in client bundles
  • Crypto — weak algorithms, missing signature verification (webhooks especially!)
  • SSRF / path traversal — user input flowing to URL fetchers or filesystem
  • Rate limiting — missing on public or AI endpoints
  • CORS / CSRF — missing or misconfigured
  • Dependencies — known-vulnerable versions

Severity levels

  • CRITICAL — must fix before commit. Examples: exposed secrets, missing auth check, unverified webhook signature, SQL injection, missing rate limit on AI endpoint
  • HIGH — fix before next release. Examples: N+1 on user-facing endpoint, missing input schema validation
  • MEDIUM — fix when in area
  • LOW — nice to have

Rules

  • Never hand-wave security. If something is CRITICAL, say so clearly.
  • Every finding has: severity, file + line, what's wrong, why it matters, suggested fix.
  • Quality and security are equally weighted. Don't skip security because "quality looks good."
  • Rotate any suspected-exposed secret immediately and flag it.

Read the full file on GitHub · 54 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. 11d ago First seen · 54 lines · 34 tokens per session scan A f330cd33d5cc

Subscribe to this mod's changes

reviewer is an agent published in the GitHub repository selmakcby/claude-agents-skills (124 stars, last pushed 4mo ago), licensed MIT. It adds 34 tokens to every session and 591 once invoked, about $0.0002 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.

Related

Other agents, from other repositories

cpp-reviewer

Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.

affaan-m/ECC · 41 tokens

reviewer

Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…

genkovich/sdd · 81 tokens

atomic-auditor

Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…

damusix/atomic-claude · 169 tokens

bt6-pr-auditor

Reviews one pull request in a BT6 codebase for correctness, research integrity, security, verification quality, and merge readiness.

elder-plinius/T3MP3ST · 32 tokens

Reviewer

Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.

monkilabs/opencastle · 30 tokens

security-auditor

Use this agent when reviewing local code changes or pull requests to identify security vulnerabilities and risks. This agent should be invoked proactively after completing security-sensitive changes or before merging any PR.

NeoLabHQ/context-engineering-kit · 40 tokens