create-review-guide

create-review-guide is a skill for Claude Code from atman-33/workhub. It costs 87 tokens per session (1,121 once invoked), scanned A, original, MIT.

A self-contained HTML guide that explains a code change before a reviewer reads the full diff. It includes the affected architecture, file and class responsibilities, and an annotated walkthrough.

In plain words
What is it for?
Documenting uncommitted changes, branch comparisons, commits, or pull requests with an architecture diagram, responsibility map, and change explanation.
Why use it?
It gives reviewers a big-picture map of the implementation, which can make a change easier to understand. The guide is generated for the current review scope.

Skill for Claude Code

Written for Claude Code: allowed-tools 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 engineering plugin — 18 skills, 4 agents, 2 MCP servers shipped together

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 atman-33/workhub
Claude Code
/plugin install engineering

Made for: Claude Code.

Or install engineering, the plugin that ships this one along with the rest of its 18 skills, 4 agents, 2 MCP servers.

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 create-review-guide

README.md
[![agentmods](https://agentmods.dev/badge/skills/atman-33/workhub/create-review-guide.svg)](https://agentmods.dev/skills/atman-33/workhub/create-review-guide)
Your own site
<a href="https://agentmods.dev/skills/atman-33/workhub/create-review-guide"><img src="https://agentmods.dev/badge/skills/atman-33/workhub/create-review-guide.svg" alt="Measured on agentmods" height="20"></a>
Per session 87 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,121 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 5.1 $0.00087 $0.01121
Opus 5 $0.00044 $0.00561
Sonnet 5 $0.00017 $0.00224
Haiku 4.5 $0.00009 $0.00112

Measured 6d ago against content hash 0c2ca91f34ee, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

create-review-guide 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 6d 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/engineering/skills/create-review-guide/SKILL.md · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Create Review Guide

Produce one self-contained HTML file that lets a reviewer understand the implementation top-down — purpose, architecture, where each piece lives, and what changed — before (and while) reading the diff.

1. Resolve the output directory

The output directory is per-installer configuration, resolved in this order:

  1. ${CLAUDE_PLUGIN_ROOT}/config.jsonoutputDir (shared across this plugin's skills)
  2. config.json next to this SKILL.md → outputDir (skill-level override)
  3. Neither exists → read config.example.json for the expected shape, ask the user for a real absolute path, then write it to the skill-level config.json (git-ignored) so the question is never asked again.

Honor openAfterGenerate (default true) from the same file.

2. Determine the review scope

Pick the first that applies; confirm with the user only if ambiguous:

  • The user named a branch, PR, or commit range → use exactly that (git diff <base>...<head>).
  • The working tree is dirty → uncommitted changes (git diff HEAD, plus git diff --staged if partially staged).
  • On a feature branch → git diff $(git merge-base main HEAD)...HEAD and git log for that range. (Fall back to master/develop if main is absent.)
  • On the default branch with a clean tree → ask the user what to review.

3. Gather real content — never fabricate

  • Run git log --oneline for the range and git diff --stat for the shape of the change.
  • Read every changed file in full — not just hunks — so responsibilities and class/function roles are described accurately.
  • Trace the key entry points and callers of changed code (Grep/Glob) so the architecture diagram reflects actual dependencies, not guesses.
  • Note anything you could not verify; mark it "unverified" in the guide rather than inventing it.

4. Generate the HTML guide

One self-contained .html file: inline <style>, <script>, and SVG — no CDN, no external assets. Write prose in the language the user is conversing in; keep identifiers, paths, and code as-is. Required sections, in order:

Read the full file on GitHub · 92 lines

Files

What ships with it

2 files 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. 6d ago First seen · 92 lines · 87 tokens per session scan A 0c2ca91f34ee

Subscribe to this mod's changes

create-review-guide is a skill published in the GitHub repository atman-33/workhub (2 stars, last pushed yesterday), licensed MIT. It adds 87 tokens to every session and 1,121 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

gonavi-cli

Operate databases through the GoNavi headless CLI — the gonavi executable shipped in verified GitHub Release archives. Covers listing/adding/importing saved connections, running SQL queries against saved connections or ad-hoc connection files, exporting result sets to csv/json/md/html/xlsx, batch-executing SQL files…

Syngnat/GoNavi · 144 tokens

superbrain-distill

Internal SuperBrain skill — run by the detached capture child to distill a session-event delta into routed Obsidian notes. Not for direct user invocation.

m3talux/superbrain · 36 tokens

memory

Use this skill when Pioneer should proactively use durable memory or recalled context: decide whether memory can improve a turn, answer from remembered user/project facts, request memory tools, search/list/get stored memories, save durable preferences or project decisions, forget memories, audit or clean up memory, or…

pioneerdotai/pioneer · 64 tokens

trellis-break-loop

Deep bug analysis to break the fix-forget-repeat cycle. Analyzes root cause category, why fixes failed, prevention mechanisms, and captures knowledge into specs. Use after fixing a bug to prevent the same class of bugs.

fy-agent/fyagent · 50 tokens

trellis-channel

Use Trellis channel for live multi-agent collaboration, spawned workers, cross-agent review, progress inspection, forum channels, and channel log debugging.

fy-agent/fyagent · 32 tokens

memo-writing

How to write effective session memos — format, frontmatter schema, observation extraction, topic-signal append. Trigger on /memex:save, "save this for later", "remember this", "save what we discussed", "document this session", "create a memo", or when the [memex] activity nudge appears in context. Do NOT trigger for…

linxule/memex-plugin · 125 tokens