reviewer

reviewer is an agent for coding agents from queelius/claude-anvil. It costs 325 tokens per session (1,351 once invoked), scanned A, original, MIT.

A coordinator that asks four specialist reviewers to examine technical textbook sections and combines their findings into one report. The reviewers check requirements, quality, mathematics and links between sections.

In plain words
What is it for?
Reviewing selected sections or a complete technical non-fiction textbook, including later review rounds that carry forward unresolved findings.
Why use it?
It helps find different kinds of editorial problems in one review pass and keeps the results together. It reports issues without changing the source text.

Agent

Part of the bookwright plugin — 3 skills, 11 commands, 11 agents, 1 hook shipped together

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/queelius/claude-anvil/reviewer
Clone the repo
git clone --depth 1 https://github.com/queelius/claude-anvil

Or install bookwright, the plugin that ships this one along with the rest of its 3 skills, 11 commands, 11 agents, 1 hook.

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/queelius/claude-anvil/reviewer.svg)](https://agentmods.dev/agents/queelius/claude-anvil/reviewer)
Your own site
<a href="https://agentmods.dev/agents/queelius/claude-anvil/reviewer"><img src="https://agentmods.dev/badge/agents/queelius/claude-anvil/reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 325 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,351 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 5.1 $0.00325 $0.01351
Opus 5 $0.00162 $0.00675
Sonnet 5 $0.00065 $0.00270
Haiku 4.5 $0.00032 $0.00135

Measured 5d ago against content hash 8a01a3629139, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, 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 5d 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.

bookwright/agents/reviewer.md · 132 lines

How it starts

The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You orchestrate multi-agent editorial review for technical non-fiction textbooks. You read the in-scope content, dispatch all four review specialists simultaneously, gather their findings, deduplicate and categorize them, and save a unified report. You do not auto-fix anything: the report is your only output artifact.

Delta-Scoped Review (iterate rounds 2+)

When the launch prompt includes <sections> (a list of section files) and optionally <carry-forward-findings> (a prior round's findings in files OUTSIDE that list):

  • Treat <sections> as the scope: auditors receive only those files as the audit target, but still get the chapter context they normally need (plan spec, chapter directory for label scanning).
  • Merge the carry-forward findings into the unified report unchanged, each marked "carried forward (file untouched since round N)". Re-validate any carried finding that references a <sections> file before including it; drop it if the delta edits resolved it.
  • Finding counts cover the merged set (fresh plus carried), so round-over-round counts stay comparable.

Without <sections>, resolve scope as below.

Scope Resolution

Parse the scope from the prompt. Valid scopes:

  • section <label>: one .tex file
  • chapter <N> or chapter <label>: all .tex files in that chapter directory
  • book: all .tex files under book/

If scope is ambiguous, use Glob to list candidate files and confirm with the user before dispatching auditors.

Read book/CLAUDE.md for the repo layout and the plan file for the relevant chapter (under docs/superpowers/plans/) so you can pass the correct plan path to spec-auditor.

Parallel Dispatch

Dispatch all four auditors simultaneously via four Task calls in the same turn. Pass each auditor exactly what it needs:

Auditor What to pass
bookwright:spec-auditor drafted file path(s) + plan task spec
bookwright:quality-auditor drafted file path(s) only (reads cold, no plan)
bookwright:math-auditor drafted file path(s)
bookwright:cross-ref-auditor drafted file path(s) + chapter directory for label scanning

Read the full file on GitHub · 132 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. 5d ago First seen · 132 lines · 325 tokens per session scan A 8a01a3629139

Subscribe to this mod's changes

reviewer is an agent published in the GitHub repository queelius/claude-anvil (2 stars, last pushed 1mo ago), licensed MIT. It adds 325 tokens to every session and 1,351 once invoked, about $0.0016 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

interview-prep

Use this agent for interview preparation, mock interviews, behavioral question coaching, technical interview practice, and company-specific research. Invoke when the user has an upcoming interview, wants to practice STAR stories, needs technical prep, or wants to understand a company's interview process. Context: User…

Aznatkoiny/zAI-Skills · 242 tokens

mentor

Expert educator specializing in teaching programming concepts, code walkthroughs, and best practices through clear explanations. Japanese: メンター.

Fujigo-Software/f5-framework-claude · 0 tokens

edtech-reviewer

Education-technology specialist pre-implementation reviewer for edtech archetype. Specialises in COPPA verifiable parental consent, FERPA student-data handling, GDPR-K (digital age of consent), Section 508 + WCAG 2.2 AA accessibility, child-safety content moderation (CSAM hash, NCMEC reporting), and US state…

avelikiy/great_cto · 112 tokens

ia-database-guardian

Reviews database schema, constraints, and migration code for safety. Use when PRs touch migrations, data models, ID mappings, enum conversions, backfills, or persistent data.

iliaal/whetstone · 41 tokens

ia-best-practices-researcher

Researches external framework docs, version-specific constraints, and industry conventions for any technology. Use when you need authoritative external documentation.

iliaal/whetstone · 34 tokens

reviewer-opus

Deeply reviews code for bugs, logic errors, and security vulnerabilities using comprehensive reasoning to catch subtle, high-impact issues that require careful analysis.

Joncik91/ucai · 32 tokens