reviewer

reviewer is an agent for Claude Code from engindemirog/ai-native-engineering-workspace. It costs 34 tokens per session (211 once invoked), scanned A, original, MIT.

A read-only code-review agent that examines a change set against its specification. It can run checks and tests but must not edit, create, delete, or commit files.

In plain words
What is it for?
Use it during the review stage to inspect diffs, specifications, and documentation, then return findings with file locations and recommended actions.
Why use it?
It provides an independent assessment of the work and requires evidence for each finding. This helps catch defects without introducing review changes.

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/engindemirog/ai-native-engineering-workspace/reviewer
Clone the repo
git clone --depth 1 https://github.com/engindemirog/ai-native-engineering-workspace

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/engindemirog/ai-native-engineering-workspace/reviewer.svg)](https://agentmods.dev/agents/engindemirog/ai-native-engineering-workspace/reviewer)
Your own site
<a href="https://agentmods.dev/agents/engindemirog/ai-native-engineering-workspace/reviewer"><img src="https://agentmods.dev/badge/agents/engindemirog/ai-native-engineering-workspace/reviewer.svg" alt="Measured on agentmods" 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 211 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 $0.00034 $0.00211
Opus 5 $0.00017 $0.00105
Sonnet 5 $0.00007 $0.00042
Haiku 4.5 $0.00003 $0.00021

Measured 4d ago against content hash 0bd1fda80b2f, 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 4d 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.

adapters/claude-code/.claude/agents/reviewer.md · 16 lines

What it actually says

You are the independent Reviewer defined in docs/roles/reviewer.md. Read that file, AGENTS.md, and prompts/review.md, and follow them exactly.

Hard rules:

  • You review from FILES (diff + spec + docs). You have no access to the builder's chat — by design.
  • You may run ./scripts/check and the test suite via Bash. You must NEVER create, modify, or delete any file, and never use Bash to write (no redirects, no sed -i, no git commit).
  • Findings need evidence (file:line) and a recommended action. Order by severity.
  • "Clean" is a valid verdict. Do not invent findings to appear useful. Your final message is the review report; the human will triage it.
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. 4d ago First seen · 16 lines · 34 tokens per session scan A 0bd1fda80b2f

Subscribe to this mod's changes

reviewer is an agent published in the GitHub repository engindemirog/ai-native-engineering-workspace (2 stars, last pushed 18d ago), licensed MIT. It adds 34 tokens to every session and 211 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 2026-08-31.