doc-review

doc-review is a skill for Claude Code from GoogilyBoogily/googilyboogily-claude-power-tools. It costs 49 tokens per session (4,415 once invoked), scanned A, original, MIT.

A review workflow for architecture documents in GitHub pull requests. It collects reviewer comments on Architecture Decision Records, High-Level Designs, or Low-Level Designs and tracks decisions about them locally.

In plain words
What is it for?
Use it to review PR comments interactively, record review decisions, draft replies for manual posting, and resume a review when new comments appear.
Why use it?
It keeps review feedback, unresolved points, and follow-up sessions organized without losing the status of individual comments.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: model in frontmatter; names the AskUserQuestion tool.

Part of the architecture-docs plugin — 19 skills shipped together

Good fit Use it to review PR comments interactively, record review decisions, draft replies for manual posting, and resume a review when new comments appear.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/googilyboogily/googilyboogily-claude-power-tools/doc-review
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.

Any agent
npx skills add GoogilyBoogily/googilyboogily-claude-power-tools --skill doc-review
Clone the repo
git clone --depth 1 https://github.com/GoogilyBoogily/googilyboogily-claude-power-tools

Made for: Claude Code.

Or install architecture-docs, the plugin that ships this one along with the rest of its 19 skills.

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-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/googilyboogily/googilyboogily-claude-power-tools/doc-review/github.svg)](https://agentmods.dev/skills/googilyboogily/googilyboogily-claude-power-tools/doc-review)
Your own site
<a href="https://agentmods.dev/skills/googilyboogily/googilyboogily-claude-power-tools/doc-review"><img src="https://agentmods.dev/badge/skills/googilyboogily/googilyboogily-claude-power-tools/doc-review/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-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/googilyboogily/googilyboogily-claude-power-tools/doc-review"><img src="https://agentmods.dev/badge/skills/googilyboogily/googilyboogily-claude-power-tools/doc-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,415 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 $0.00049 $0.04415
Opus 5 $0.00024 $0.02207
Sonnet 5 $0.00010 $0.00883
Haiku 4.5 $0.00005 $0.00441

Measured 12d ago against content hash 1f083acd6cf1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

doc-review 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 12d 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/architecture-docs/skills/doc-review/SKILL.md · 409 lines

How it starts

The opening of the file, as written. The whole thing — 409 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PR-Aware Architecture Document Review

Pull open GitHub PR comments on architecture documents (ADR, HLD, LLD), identify grey areas across reviewer feedback, capture review decisions as R-XX entries, and walk through each comment interactively. Produces a REVIEW.md state file per document with resume capability.

This skill is local-only — it reads from GitHub via gh CLI and edits document files locally. It NEVER posts anything to GitHub. The user handles all GitHub replies manually by copy-pasting drafted replies.

When to Use

Use when an architecture document is in a PR with reviewer comments that need to be addressed. Works with any ADR, HLD, or LLD document that has open review feedback. Also useful for re-reviewing after pushing changes — --resume detects new comments since last session.

Input

$ARGUMENTS — PR number or URL, and optionally --resume to continue a previous review session.

Parse Arguments

Extract from $ARGUMENTS:

  • PR identifier: Number (e.g., 42) or URL (e.g., https://github.com/org/repo/pull/42)
  • Resume flag: --resume (optional, triggers Phase 7 at startup)

If --resume is present, jump to Phase 7 before anything else.

Process

Human-in-the-loop: Never proceed past a decision point without user approval.

Phase 7: Resume Handler (runs first if --resume)

This phase fires ONLY when --resume is present in $ARGUMENTS. It restores state from a previous review session.

  1. Find existing REVIEW.md files:

    Glob for docs/context/review/*-PR-*-REVIEW.md
    
  2. If none found: Inform user "No review state found" and fall through to Phase 1. Strip --resume from arguments.

  3. If multiple found: Distinguish between multiple PRs and same-PR multi-document reviews:

    • Same PR, multiple documents: Present all docs together with per-doc completion status. Let the user pick which document to resume. After completing the resumed document, prompt: "Documents B and C from this PR still need review. Continue with the next one?"
    • Different PRs: Present the list via AskUserQuestion — show PR number, document name, status, and last activity for each. Ask which to resume.

Read the full file on GitHub · 409 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 12d ago First seen · 409 lines · 49 tokens per session scan A 1f083acd6cf1

Subscribe to this mod's changes

doc-review is a skill published in the GitHub repository GoogilyBoogily/googilyboogily-claude-power-tools (2 stars, last pushed 4mo ago), licensed MIT. It adds 49 tokens to every session and 4,415 once invoked, about $0.0002 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.