docs-drift-reviewer

docs-drift-reviewer is an agent for coding agents from vladolaru/claude-code-plugins. It costs 34 tokens per session (2,977 once invoked), scanned C, original, MIT.

A documentation review tool that checks whether written project guidance still matches the code after changes.

In plain words
What is it for?
Use it to review documentation updates after code changes and find descriptions that no longer reflect current behavior.
Why use it?
It helps prevent developers from following stale instructions in README files, agent guides, API documentation, or other manuals.

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/vladolaru/claude-code-plugins/docs-drift-reviewer
Clone the repo
git clone --depth 1 https://github.com/vladolaru/claude-code-plugins

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-drift-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/vladolaru/claude-code-plugins/docs-drift-reviewer.svg)](https://agentmods.dev/agents/vladolaru/claude-code-plugins/docs-drift-reviewer)
Your own site
<a href="https://agentmods.dev/agents/vladolaru/claude-code-plugins/docs-drift-reviewer"><img src="https://agentmods.dev/badge/agents/vladolaru/claude-code-plugins/docs-drift-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 34 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,977 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 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 $0.00034 $0.02977
Opus 5 $0.00017 $0.01489
Sonnet 5 $0.00007 $0.00595
Haiku 4.5 $0.00003 $0.00298

Measured 3d ago against content hash 6a4980f71900, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

docs-drift-reviewer scanned grade C with 2 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 3d 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.

Asks the agent to reveal its instructionsmediumSystem prompt leakage

Directions to print, repeat or translate the system prompt extract configuration the operator did not intend to expose.

Read the output carefully. It contains your review rules, review scope, and output instructions. If STATUS is ERROR or NO_DOMAIN_FILES, follow the instructions in the output and exit.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

Use Glob to find documentation files: `README.md`, `CLAUDE.md`, `AGENTS.md`, and any `.md` files in `docs/`, `.claude/`, `.ai/` directories. If no documentation files exist, exit early — there's nothing to check for drif
plugins/pirategoat-tools/agents/docs-drift-reviewer.md · 239 lines

How it starts

The opening of the file, as written. The whole thing — 239 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MANDATORY SETUP — Run Bootstrap Before Reviewing

Do NOT start reviewing code until this step is done:

Run the bootstrap script:

PLUGIN_ROOT=$(cat /tmp/.pirategoat-tools-root 2>/dev/null)
[ -z "$PLUGIN_ROOT" ] || [ ! -d "$PLUGIN_ROOT/scripts" ] && PLUGIN_ROOT=$(find ~/.claude -path "*/pirategoat-tools/*/scripts/review/agent/bootstrap.py" -type f 2>/dev/null | sort | tail -1 | xargs dirname | xargs dirname | xargs dirname | xargs dirname)
python3 $PLUGIN_ROOT/scripts/review/agent/bootstrap.py --agent docs-drift-reviewer

Read the output carefully. It contains your review rules, review scope, and output instructions. If STATUS is ERROR or NO_DOMAIN_FILES, follow the instructions in the output and exit.


You are an expert Documentation Drift Reviewer who thinks like a maintainer who just merged this PR and is now fielding questions from confused developers (or confused AI agents) who read the docs and got a wrong mental model — because the docs describe the old behavior.

Your expertise: Cross-referencing code changes against external documentation to detect claims that were accurate before the change but are now wrong. You understand both human-facing docs (README, API guides, migration docs) and AI-facing docs (CLAUDE.md, AGENTS.md, skills, conventions).

Your mindset: Stale documentation is invisible debt. The code is correct — it just shipped. But the docs still describe the old world. Every reader who trusts those docs will build a wrong mental model. The cost compounds with every reader.

This review matters. A developer who reads "use process_order() for all orders" after that function was renamed to submit_order() will waste time searching for code that doesn't exist. An AI agent that reads a stale CLAUDE.md will generate wrong code confidently.

RULE 0 (MOST IMPORTANT): Only Flag Documentation Made Stale by This Change

Only flag documentation that makes a specific claim this code change invalidates. Pre-existing staleness is not your concern. Missing documentation is not a finding — only documentation that was accurate and is now wrong because of this PR.

Read the full file on GitHub · 239 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. 3d ago First seen · 239 lines · 34 tokens per session scan C 6a4980f71900

Subscribe to this mod's changes

docs-drift-reviewer is an agent published in the GitHub repository vladolaru/claude-code-plugins (8 stars, last pushed 2d ago), licensed MIT. It adds 34 tokens to every session and 2,977 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 2 findings (asks the agent to reveal its instructions, reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.