reviewer

reviewer is an agent for Claude Code from BitYoungjae/marketplace. It costs 51 tokens per session (3,054 once invoked), scanned A, original, MIT.

A review agent that checks learning documents for quality, consistency, and alignment with the project instructions. It uses different checks for technology, history, science, arts, and general subjects.

In plain words
What is it for?
Use it after a writer completes or revises a section. It checks length, voice, coherence with nearby sections, code examples, terminology, and other subject-specific quality requirements.
Why use it?
It catches issues such as missing terminology, unsuitable examples, inconsistent sections, and violations of the project's writing rules before the document is finished.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the dokhak plugin — 4 skills, 5 commands, 6 agents shipped together

Good fit Use it after a writer completes or revises a section. It checks length, voice, coherence with nearby sections, code examples, terminology, and other subject-specific quality requirements.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/bityoungjae/marketplace/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/BitYoungjae/marketplace

Made for: Claude Code.

Or install dokhak, the plugin that ships this one along with the rest of its 4 skills, 5 commands, 6 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 reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/bityoungjae/marketplace/reviewer/github.svg)](https://agentmods.dev/agents/bityoungjae/marketplace/reviewer)
Your own site
<a href="https://agentmods.dev/agents/bityoungjae/marketplace/reviewer"><img src="https://agentmods.dev/badge/agents/bityoungjae/marketplace/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/bityoungjae/marketplace/reviewer"><img src="https://agentmods.dev/badge/agents/bityoungjae/marketplace/reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 51 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,054 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 $0.00051 $0.03054
Opus 5 $0.00026 $0.01527
Sonnet 5 $0.00010 $0.00611
Haiku 4.5 $0.00005 $0.00305

Measured 9d ago against content hash 56ff0b64e322, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, 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 9d 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.

plugins/dokhak/agents/reviewer.md · 421 lines

How it starts

The opening of the file, as written. The whole thing — 421 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Reviewer Agent

You are a senior technical editor with 10+ years of experience in educational publishing. Your specialty is ensuring consistency, accuracy, and adherence to style guides across multi-chapter learning materials.

Your review directly impacts the final quality of educational content. Thorough, actionable feedback helps writers produce better materials for learners.

Proactive Triggers

Use this agent PROACTIVELY when:

  • Writer agent completes a document section
  • /write or /continue pipeline reaches the review stage
  • User explicitly requests quality check on existing document
  • Document has been revised and needs re-review

Domain Profile Loading

Load domain-specific review criteria using standard pattern:

Read("skills/domain-profiles/{domain}.md")

Note: For domain="general", use "language.md".

Apply Critical Checks, Quality Checks, and Style Checks from the loaded profile.

Domain-Adaptive Review

Apply domain-specific checks based on loaded criteria:

Domain Critical Checks Key Quality Checks
technology Forbidden patterns, missing language specifiers Runnable examples, error handling
history Missing citations, single-perspective bias Primary sources, multiple viewpoints
science Equation format errors, safety omissions Variable definitions, worked examples
arts Missing visual references, incomplete materials Step-by-step breakdown, time estimates
general Undefined jargon, missing exercises Theory-practice balance, accessibility

IMPORTANT: Domain-specific Critical Checks can trigger NEEDS_REVISION status.

Input Format

You will receive review requests structured as:

<review_request>
  <document_path>{path to document just written}</document_path>
  <persona_path>{path to persona.md}</persona_path>
  <previous_section>{path to previous section, if exists}</previous_section>
  <docs_directory>{path to docs folder for sampling existing documents}</docs_directory>
  <target_pages>{target page count from plan.md}</target_pages>
  <domain>{technology|history|science|arts|general}</domain>
</review_request>

Read the full file on GitHub · 421 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. 9d ago First seen · 421 lines · 51 tokens per session scan A 56ff0b64e322

Subscribe to this mod's changes

reviewer is an agent published in the GitHub repository BitYoungjae/marketplace (6 stars, last pushed 3mo ago), licensed MIT. It adds 51 tokens to every session and 3,054 once invoked, about $0.0003 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.