Review Changes

What it does

When your agent uses it

• The user asks to review my changes
• Look at my diff
• Check my staged changes
• Code review my working tree

Example prompts

• “review my changes”
• “look at my diff”
• “check my staged changes”
• “/review-changes”

Requirements

• Pre-approved tools (allowed-tools): Read, Glob, Grep, Bash(git:*)

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

1. 1No em dashes. Hyphens with spaces, commas, or periods only.
2. 2Never use "ask" as a noun. "A heavy ask" is a rewrite.
3. 3No AWS references. Not in code, not in comments, not in docs.
4. 4No hardcoded secrets. Flag any string that looks like an API key, token, or password.
5. 5No console.log in shipped JS/TS. Test files and demos in segment_*/ are fine.

What it can do on your machine

Read from SKILL.md and the folder at commit cb80eae. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves these tools, so the agent can use them without asking each time:

  • Read
  • Glob
  • Grep
  • Bash(git:*)

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Shell commands in SKILL.md call:

  • git

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Review Changes loads about 506 tokens when it runs. Until then it costs about 105 tokens; SKILL.md has 195 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~105

When it runs · the whole SKILL.md, loaded when a task matches

~506

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from timothywarner-org/claude-code at commit cb80eae, republished under its MIT licence (© timothywarner-org). 195 words, ~506 tokens.

name

review-changes

description

Review uncommitted local changes in the current git working tree for bugs, smells, missing tests, and CLAUDE.md voice violations. Use when the user asks to "review my changes", "look at my diff", "check my staged changes", "code review my working tree", or wants a sanity check before committing or opening a PR. Do NOT use for already-open pull requests on GitHub (that's the separate `review` command).

allowed-tools

Read, Glob, Grep, Bash(git:*)

git diff HEAD

git status --short

git log -5 --oneline

## Blockers
- file:line - issue - proposed fix

## Soft findings
- file:line - note

## What's working
- one or two things the diff got right (keep it brief, no glazing)

© timothywarner-org, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .claude/skills/review-changes of timothywarner-org/claude-code.

Open the folder on GitHubat commit cb80eae