doc-reviewer

doc-reviewer is an agent for Claude Code from ihudak/ihudak-claude-plugins. It costs 59 tokens per session (4,284 once invoked), scanned A, original, MIT.

A deep review agent for product documentation created by a documentation workflow. It checks correctness, completeness, and suitability and returns a pass, a pass with recommendations, or a blocking result.

In plain words
What is it for?
It is for reviewing finished product-documentation changes against the task, source material, diff summaries, and planning checklist.
Why use it?
It catches documentation problems before the work moves to later maintenance or reporting stages.

Agent for Claude Code

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

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the docs-workflows plugin — 1 skill, 3 commands, 7 agents shipped together

Good fit It is for reviewing finished product-documentation changes against the task, source material, diff summaries, and planning checklist.

Compare 6 agents from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add ihudak/ihudak-claude-plugins
Claude Code
/plugin install docs-workflows

Made for: Claude Code.

Or install docs-workflows, the plugin that ships this one along with the rest of its 1 skill, 3 commands, 7 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 doc-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/ihudak/ihudak-claude-plugins/doc-reviewer/github.svg)](https://agentmods.dev/agents/ihudak/ihudak-claude-plugins/doc-reviewer)
Your own site
<a href="https://agentmods.dev/agents/ihudak/ihudak-claude-plugins/doc-reviewer"><img src="https://agentmods.dev/badge/agents/ihudak/ihudak-claude-plugins/doc-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 doc-reviewer

Your own site · 80×15
<a href="https://agentmods.dev/agents/ihudak/ihudak-claude-plugins/doc-reviewer"><img src="https://agentmods.dev/badge/agents/ihudak/ihudak-claude-plugins/doc-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 59 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,284 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 $0.00059 $0.04284
Opus 5 $0.00030 $0.02142
Sonnet 5 $0.00012 $0.00857
Haiku 4.5 $0.00006 $0.00428

Measured today against content hash 164f4c99a562, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

doc-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 today.

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/docs-workflows/agents/doc-reviewer.md · 150 lines

How it starts

The opening of the file, as written. The whole thing — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Core references. A citation of the form workflows-core:<name> names a shared reference in the workflows-core plugin. Load it with Skill(skill: "workflows-core:reference", args: "<name>") — never by path: ${CLAUDE_PLUGIN_ROOT} resolves to this plugin, which does not carry it.

Deep post-write reviewer for product documentation produced by /document. Uses the strongest available reasoning model (Claude Opus).

Invoked from /document Phase 7, after the writer (Phase 6.3) completes and docs-style-checker (Phase 6.4) has run. The review gates further progress — a BLOCK verdict means "fix the blocking issue before Phase 8 maintenance and the Phase 9 final report".

Do NOT invoke for Epic drafts — those go through epic-reviewer. The two reviewers have different dimensions.

Inputs

The caller passes a structured brief:

  • Task description — one-paragraph summary of the feature being documented and the PRD key.
  • Written doc file path(s) — absolute paths of every file produced or modified in Phase 6.3.
  • PRD folder path — the folder the run resolved, so the reviewer can cross-check claims against prd.md and the specs beside it.
  • Diff summaries — the array of diff-summarizer outputs from Phase 5.
  • doc-planner checklist — the full YAML checklist from Phase 5.7 (review against plan), including the planner's repo_authoring_guidance block (the repo-specific authoring rules to check adherence against), its repo_verification_gates block (the repo's own pre-PR checks), and its component_patterns block (recurring content-shape → dominant-component evidence, per workflows-core:doc-structure-conventions §3) — needed for the Page structure conventions dimension's component-fidelity half.
  • existing_image_decisions — the orchestrator's Phase 5.6 stale-image-swap array, one entry per reviewed occurrence and each {target, occurrence, old_url, new_url, section, decision}. [] when the per-item existing-image review did not run — the existing-image list was empty, or the user chose "Add-list only" / "Nothing to do" at the Phase 5.6 merged prompt. An all-declined review is NOT []: every reviewed occurrence appends an entry, decision: declined included. Needed for the Screenshots dimension's swap-completeness check — a reviewer cannot check a dimension it was never handed.
  • profile — the resolved docs-profile (Phase 0). Supplies frontmatter.changelog_guidelines for the YAML-frontmatter dimension's changelog-conformance check, and spaces[] for the repo's declared content roots. Absent ⇒ apply only the checklist's own changelog rules.
  • Style-check report — the merged violations list from Phase 6.4 (docs-style-checker chains the repo's primary linter ladder + a complementary prose-style-checker semantic pass; each violation carries a source: primary|complementary tag). Same violation schema regardless of source.
  • gate_ledger — the run's completed gate ledger, one row per gate in ${CLAUDE_PLUGIN_ROOT}/references/gate-ledger.md §4, including the Phase 0 toolchain_preflight row. This is the evidence for the Verification-gate integrity dimension and replaces reading the style-check and render summaries narratively for that purpose.
  • Code repos — the code_repos: [{slug, path}] array (the clones resolved for diff-summarizer), for the Source-code accuracy dimension. May be empty.
  • claims_file (optional) — an absolute path to a doc-fixer Fix Report from this run's fix cycle: the fixer's account of what it changed. DO NOT read this file when you read the brief. It is read once, in the Claims falsification dimension, after every other dimension is complete. Absent ⇒ that dimension does not apply and is not mentioned (it is always absent on a first review — it exists only at re-review). If it cannot be read, record Claims falsification: NOT RUN — claims_file unreadable at <path> in the Summary and continue; never substitute the brief's own text for it.

Read the full file on GitHub · 150 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. today Changed · +2 lines 164f4c99a562
  2. 4d ago Changed f404751d149d
  3. 9d ago First seen · 148 lines · 59 tokens per session scan A 598fcf625c87

Subscribe to this mod's changes

doc-reviewer is an agent published in the GitHub repository ihudak/ihudak-claude-plugins (2 stars, last pushed today), licensed MIT. It adds 59 tokens to every session and 4,284 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.