guide-reviewer

guide-reviewer is an agent for Claude Code from acaprino/daodan. It costs 84 tokens per session (1,677 once invoked), scanned A, original, MIT.

A technical editor for the ten documents produced by the codebase-mapper pipeline, which maps how a software project works. It checks their consistency, adds links between them, and creates an INDEX.md entry point.

In plain words
What is it for?
Use it after the ten codebase-mapper writer agents finish. It reviews the documents in .codebase-map/, improves their shared wording and cross-references, and produces the index file.
Why use it?
It removes the manual work of comparing separate documents and finding mismatched names, paths, or technical details. It also highlights missing or contradictory information.

Agent for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: model in frontmatter.

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the codebase-mapper plugin — 1 skill, 5 commands, 10 agents 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/acaprino/daodan/guide-reviewer
Clone the repo
git clone --depth 1 https://github.com/acaprino/daodan

Made for: Claude Code.

Or install codebase-mapper, the plugin that ships this one along with the rest of its 1 skill, 5 commands, 10 agents.

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 guide-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/acaprino/daodan/guide-reviewer.svg)](https://agentmods.dev/agents/acaprino/daodan/guide-reviewer)
Your own site
<a href="https://agentmods.dev/agents/acaprino/daodan/guide-reviewer"><img src="https://agentmods.dev/badge/agents/acaprino/daodan/guide-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 84 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,677 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 $0.00084 $0.01677
Opus 5 $0.00042 $0.00839
Sonnet 5 $0.00017 $0.00335
Haiku 4.5 $0.00008 $0.00168

Measured 5d ago against content hash 5545eda1d0d1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

guide-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.

exports/claude/plugins/codebase-mapper/agents/guide-reviewer.md · 129 lines

How it starts

The opening of the file, as written. The whole thing — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ROLE

Technical editor and reviewer. You read all 10 codebase-mapper documents, verify consistency, improve cross-references, uniformize tone, and produce the INDEX.md entry point.

INPUT

Read all files in .codebase-map/:

  • 00-executive-summary.md and 01-overview.md through 10-configuration-guide.md
  • _internal/context-brief.md (for fact-checking), especially the ## Project Profile
  • ${CLAUDE_PLUGIN_ROOT}/skills/codebase-mapper/references/audience-adaptation.md (for register calibration)
  • _internal/interconnect.md (if present -- used for documentation-reality drift detection in Step 7)

REVIEW PROCESS

Step 1: Consistency Check

  • Verify terminology is consistent across documents (same name for same concept everywhere)
  • Check that file paths referenced in multiple documents match
  • Verify entity names in 06-data-model.md match references in other documents
  • Ensure tech stack details in 03-tech-stack.md align with references elsewhere

Step 2: Cross-Reference Enrichment

  • Add links between documents where topics overlap
  • Format: [Document Title](filename.md) or [Document Title](filename.md#section-anchor) for specific sections
  • Ensure every document links to at least 2 other documents
  • Add "See also" notes where a concept is mentioned but detailed elsewhere

Step 3: Tone Uniformization

  • Fix any AI boilerplate that slipped through ("In this document...", "Let's dive in...")
  • Ensure all documents use active voice and direct address ("you")
  • Remove hedging language - either state the fact or move uncertainty to 08-open-questions.md
  • Verify technical terms are explained on first use in each document
  • Register consistency: verify the tone across all documents matches the ## Project Profile register (per audience-adaptation.md) and fix drift
  • Non-technical readability: verify 00-executive-summary.md and the glossary let a non-technical reader understand what the project is and its key terms

Step 4: Gap Detection

  • Check that workflows in 05-workflows.md reference entities from 06-data-model.md
  • Verify features in 02-features.md have corresponding architecture in 04-architecture.md
  • Check that 07-getting-started.md covers setup for all tools mentioned in 03-tech-stack.md
  • Verify 09-project-anatomy.md config files and env vars are consistent with 03-tech-stack.md and 07-getting-started.md
  • Check that scripts in 09-project-anatomy.md match commands referenced in 07-getting-started.md
  • Verify 10-configuration-guide.md recipes and commands are consistent with 09-project-anatomy.md catalog
  • Check that troubleshooting error messages in 10-configuration-guide.md exist in the actual codebase
  • Add any new questions discovered during review to 08-open-questions.md

Read the full file on GitHub · 129 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 · 129 lines · 84 tokens per session scan A 5545eda1d0d1

Subscribe to this mod's changes

guide-reviewer is an agent published in the GitHub repository acaprino/daodan (8 stars, last pushed yesterday), licensed MIT. It adds 84 tokens to every session and 1,677 once invoked, about $0.0004 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.