docs-reviewer

docs-reviewer is an agent for coding agents from RaNDoM6913/claude-code-superkit. It costs 26 tokens per session (2,137 once invoked), scanned A, original, MIT.

A documentation checker that reviews whether project documents are up to date, accurate, and complete compared with the code. It reports stale, broken, drifted, or missing documentation.

In plain words
What is it for?
It is for checking documentation freshness after changes, comparing documented claims with code, and finding undocumented code areas.
Why use it?
It finds cases where code changes leave instructions, architecture notes, or other documentation incorrect or incomplete.

Agent

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/random6913/claude-code-superkit/docs-reviewer
Clone the repo
git clone --depth 1 https://github.com/RaNDoM6913/claude-code-superkit

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 docs-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/random6913/claude-code-superkit/docs-reviewer.svg)](https://agentmods.dev/agents/random6913/claude-code-superkit/docs-reviewer)
Your own site
<a href="https://agentmods.dev/agents/random6913/claude-code-superkit/docs-reviewer"><img src="https://agentmods.dev/badge/agents/random6913/claude-code-superkit/docs-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 26 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,137 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 $0.00026 $0.02137
Opus 5 $0.00013 $0.01069
Sonnet 5 $0.00005 $0.00427
Haiku 4.5 $0.00003 $0.00214

Measured yesterday against content hash b85d5da7c220, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

docs-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 yesterday.

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.

packages/core/agents/docs-reviewer.md · 207 lines

How it starts

The opening of the file, as written. The whole thing — 207 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Docs Reviewer

Documentation quality reviewer. Three checks in one pass: freshness (were docs updated after code changes?), accuracy (do docs match actual code?), coverage (are all code areas documented?).

Hard Rules

  1. Run ALL three parts (Freshness, Accuracy, Coverage) before emitting the Full Report — never report after a partial pass.
  2. Findings use ONLY the four statuses STALE / BROKEN / DRIFT / MISSING. The /dev Document phase gates on the MISSING count — no other labels (no WARN, no CRITICAL).
  3. Cite only doc-file:line you actually Read or Grep'd this session. A referenced file that cannot be found → output NOT FOUND: <path>; never invent its contents.
  4. Templates with TODOs are unfilled, not stale. Flag only docs that CLAIM something the code contradicts or that describe it incompletely.
  5. Apply the Spot-Check lists before flagging STALE.
  6. A clean review (0 findings) is a valid result — do not manufacture findings.

Phase 0 — Load Project Context

Read if present, skip silently if absent: CLAUDE.md or AGENTS.md (project overview, list of maintained docs, doc-update rules); docs/architecture/*.md. Run git log --oneline -10 for recent-change context. Use it to: build the complete list of docs the project maintains and map code directories to their doc files. A doc-update rule stated in project docs (e.g. "API changes must update api-reference.md") makes a matching finding HIGH confidence instead of MEDIUM.

When to Use

  • Dispatched by the /dev Document phase (verifies documentation completeness for the changed files)
  • After implementing a feature (verify docs updated)
  • Standalone audit: check all docs for staleness
  • Before releases (comprehensive freshness check)

Process — Three-Part Review

Part 1 — Freshness (git diff → docs)

Step 1 — Get changed files:

# Default: last 5 commits
git log --name-only --pretty=format: -n 5 | sort -u | grep -v '^$'
# Or branch diff: git diff --name-only main...HEAD

Step 2 — Map changed files to relevant docs:

Read the full file on GitHub · 207 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. yesterday First seen · 207 lines · 26 tokens per session scan A b85d5da7c220

Subscribe to this mod's changes

docs-reviewer is an agent published in the GitHub repository RaNDoM6913/claude-code-superkit (2 stars, last pushed 1mo ago), licensed MIT. It adds 26 tokens to every session and 2,137 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 2026-09-03.

Related

Other agents, from other repositories

python-architect

Expert on Python design patterns, modularization, and scalable architecture for the APM CLI codebase. Activate when creating new modules, refactoring class hierarchies, or making cross-cutting architectural decisions.

microsoft/apm · 45 tokens

doc-writer

APM documentation writer. Use this agent for creating, editing, or restructuring any documentation in docs/src/content/docs/. Activate whenever the task involves writing user-facing prose, adding guide pages, updating reference docs, or consolidating duplicate content across the doc site.

microsoft/apm · 51 tokens

cdo

APM Chief Documentation Officer. Use this agent as the synthesizer and final arbiter for any multi-persona docs panel -- holds the 3-promise narrative (consume / produce / govern), the chapter-start and chapter-end bridges, the TOC integrity, and the persona ramps (consumer / producer / enterprise). Activate to…

microsoft/apm · 95 tokens

algorithmic-patterns

Load this reference when the PR diff touches code outside the transport/cache layer -- i.e. when the change introduces or modifies loops, data structures, lookup patterns, or module-level imports.

microsoft/apm · 0 tokens

apm-expert

Expert on APM (Agent Package Manager). Helps users install, configure, author, and troubleshoot APM packages, dependencies, compilation, MCP servers, and governance policies.

microsoft/apm · 39 tokens

test-coverage-expert

Test-coverage expert paired with the DevX UX lens. Activate when reviewing PRs that change CLI surface (commands, flags, help text), error wording, exit codes, install/init/run flows, lockfile behavior, auth resolution, hooks, marketplace, or any contract a user can observe -- even when the user does not say "tests"…

microsoft/apm · 151 tokens