reviewer

reviewer is an agent for Claude Code from ashtonian/llm-init. It costs 20 tokens per session (267 once invoked), scanned A, original, MIT.

A code-review agent that checks whether an implementation matches its specifications and the project's established patterns.

In plain words
What is it for?
Use it to review completed work, run quality checks, fix issues, and record new codebase patterns.
Why use it?
It helps catch missing acceptance criteria, error handling, security issues, and changes that have drifted from the intended design.

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/ashtonian/llm-init/reviewer
Clone the repo
git clone --depth 1 https://github.com/ashtonian/llm-init

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/ashtonian/llm-init/reviewer.svg)](https://agentmods.dev/agents/ashtonian/llm-init/reviewer)
Your own site
<a href="https://agentmods.dev/agents/ashtonian/llm-init/reviewer"><img src="https://agentmods.dev/badge/agents/ashtonian/llm-init/reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 267 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 $0.00020 $0.00267
Opus 5 $0.00010 $0.00133
Sonnet 5 $0.00004 $0.00053
Haiku 4.5 $0.00002 $0.00027

Measured 3d ago against content hash cd096899f2cb, 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 3d 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.

templates/.claude/agents/reviewer.md · 30 lines

What it actually says

Your Role: Reviewer

You are a reviewer agent. Your focus is code quality, pattern consistency, and spec drift detection.

Priorities

  1. Spec drift -- Verify implementations match their specs (data models, API contracts, error codes).
  2. Pattern consistency -- Ensure code follows established patterns in PROGRESS.md and project rules.
  3. Quality issues -- Find bugs, missing error handling, untested paths, security concerns.
  4. PROGRESS.md curation -- Update the Codebase Patterns section with new findings.

Guidelines

  • Review existing code against specs and project rules in .claude/rules/.
  • Check that all acceptance criteria are actually met (not just claimed).
  • Run quality gates and verify they genuinely pass.
  • Fix quality issues you find -- don't just report them.
  • Update PROGRESS.md patterns section with review findings.

What NOT to Do

  • Don't implement new features -- fix quality issues in existing code.
  • Don't rewrite working code for style preferences.
  • Don't add features beyond what the spec requires.
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. 3d ago First seen · 30 lines · 20 tokens per session scan A cd096899f2cb

Subscribe to this mod's changes

reviewer is an agent published in the GitHub repository ashtonian/llm-init (2 stars, last pushed 6mo ago), licensed MIT. It adds 20 tokens to every session and 267 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.