Agent skill

Git Review

by umputun in umputun/cc-thingz

Interactive git diff annotation review. An agent skill from umputun/cc-thingz.

MITAuto-check: notesDevelopment

Install Git Review

skills CLI
$ npx skills add umputun/cc-thingz --skill git-review -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install umputun/cc-thingz git-review --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/umputun/cc-thingz.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/review/skills/git-review .claude/skills/git-review && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
git-review
GitHub stars
484
Token cost
~1k tokens
SKILL.md length
425 words
Files
2 (incl. scripts)
Skills in repo
16
Repo updated
First seen
Licence
MIT

At a glance

Interactive git diff annotation review. An agent skill from umputun/cc-thingz.

  • Works in 6 steps: Run the script → Process annotations → Plan changes → …
  • Tasks that involve Git workflow
  • SKILL.md covers Activation Triggers, How It Works, Workflow and Script Arguments, plus 2 more sections
  • Runs Python scripts from its folder

What it does

Git Review is an agent skill from umputun/cc-thingz. Interactive git diff annotation review. Generates a cleaned-up diff, opens in editor for user annotations, and addresses feedback in a loop. Activates on "git review", "review changes", "review my changes", "annotate changes", "interactive review".

Its SKILL.md is about 1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including scripts (for example `scripts/git-review.py`).

It sits in Development, covering Git workflow. It works with Git. The repository describes itself as: various things for claude code. The licence is MIT.

When your agent uses it

  • Tasks that involve Git workflow

Example prompts

  • “git review”
  • “review changes”
  • “review my changes”
  • “/git-review”

Requirements

  • Python 3
  • Pre-approved tools (allowed-tools): Bash, Read, Edit, Write, Grep, Glob

Workflow steps

6 steps, taken from the step headings in SKILL.md.

  1. Run the script
  2. Process annotations
  3. Plan changes
  4. Address annotations
  5. Loop
  6. Done

What it can do on your machine

Read from SKILL.md and the folder at commit 99e1c8d. 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:

    • Bash
    • Read
    • Edit
    • Write
    • Grep
    • Glob

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 1 file in scripts/ (Python), which the agent can run.

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

  • Network

    No URLs in SKILL.md.

    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

Git Review loads about 1k tokens when it runs. Until then it costs about 65 tokens; SKILL.md has 425 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~65
When it runs · the whole SKILL.md, loaded when a task matches
~1k

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

Auto-check: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NotePre-approves every shell command (allowed-tools: Bash)SKILL.md
    allowed-tools: Bash, Read, Edit, Write, Grep, Glob

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); the scripts in this folder are not scanned.

SKILL.md

The full file from umputun/cc-thingz at commit 99e1c8d, republished under its MIT licence (© umputun). 425 words, ~1,004 tokens.

Download SKILL.mdSave it as .claude/skills/git-review/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
git-review
description
Interactive git diff annotation review. Generates a cleaned-up diff, opens in editor for user annotations, and addresses feedback in a loop. Activates on "git review", "review changes", "review my changes", "annotate changes", "interactive review".
allowed-tools
Bash, Read, Edit, Write, Grep, Glob

Git Review

Interactive annotation-based code review using editor overlays.

Activation Triggers

  • "git review", "review changes", "review my changes"
  • "annotate changes", "interactive review"
  • "review diff", "annotate diff"

How It Works

  1. Script generates a cleaned-up diff file (friendly headers, no technical noise)
  2. Opens in $EDITOR via agterm overlay, tmux popup, kitty overlay, or wezterm split-pane
  3. User adds annotations (comments, change requests) directly in the file
  4. Script returns user's annotations as a git diff
  5. Claude reads annotations, fixes code in the real repo
  6. Script regenerates fresh diff (reflecting fixes), opens again
  7. Loop until user closes editor without changes

Workflow

Step 1: Run the script
bash
${CLAUDE_PLUGIN_ROOT}/skills/git-review/scripts/git-review.py [base_ref]
  • No arguments: auto-detects uncommitted changes or branch vs default branch
  • With argument: diffs against the specified ref (branch, tag, commit, HEAD~3)
Step 2: Process annotations

If the script produces output (stdout), the user made annotations. The output is a git diff showing what the user added/changed in the review file.

Read the diff carefully:

  • Added lines (+): user's annotations, comments, or change requests
  • Removed lines (-): user wants something removed or changed
  • Modified lines (- then +): user replaced text to show desired change

Each annotation is in context — the surrounding === file headers and diff content show which file and code area the annotation refers to.

Step 3: Plan changes

Enter plan mode (EnterPlanMode) to analyze annotations and design the fix approach:

  • list each annotation and which file/code area it refers to
  • describe the planned changes for each annotation
  • get user approval before modifying any code
Show full SKILL.md (175 more words)Show less
Step 4: Address annotations

After plan approval, fix the actual source code in the real repository. Each annotation is a directive — treat it as a code review comment that must be addressed.

Step 5: Loop

After fixing code, run the script again. It regenerates a fresh diff reflecting the fixes and opens the editor. The user can:

  • Add more annotations → go back to step 2 (plan + fix again)
  • Close without changes → review complete (no stdout output)
Step 6: Done

When the script produces no output, the review is complete. Inform the user.

Script Arguments

ArgumentDescription
(none)auto-detect: uncommitted changes if present, otherwise branch vs default branch
<ref>diff against specific ref: master, main, HEAD~5, v1.2.0, etc.
--cleanremove the review tracking repo from /tmp
--testrun embedded unit tests

Example Session

User: "review my changes"
→ run: git-review.py
→ editor opens with cleaned diff
→ user adds "this should validate input" next to a handler
→ user closes editor
→ stdout shows the annotation
→ enter plan mode: "annotation requests input validation in handler.go, plan: add validate() call"
→ user approves plan
→ Claude adds input validation to the handler
→ run: git-review.py (again)
→ editor opens with updated diff (validation now visible)
→ user closes without changes
→ no stdout → review complete
→ "review complete, all annotations addressed"

Requirements

  • agterm, tmux, kitty, or wezterm terminal (for editor overlay)
  • $EDITOR set (defaults to vi)
  • git
  • agterm users: needs agtermctl on PATH (bundled with agterm); no extra config; pane-scoped overlays need agterm 0.20.0+
  • kitty users: kitty.conf must have allow_remote_control yes and listen_on unix:/tmp/kitty-$KITTY_PID

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

Files

SKILL.md and 1 other file (scripts) in plugins/review/skills/git-review of umputun/cc-thingz.

  • SKILL.md
  • scripts/git-review.py

Open the folder on GitHubat commit 99e1c8d

Compare with similar skills

Git Review next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Git Review compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Git Review this skillumputun/cc-thingz484—~1kAutomated safety check: NotesMIT
Finishing a Development Branchobra/superpowers296k5 repos~1.9kAutomated safety check: PassMIT
Code Design Rationale Investigatorcursor/plugins10k9 repos~2.6kAutomated safety check: PassNone
Contributor-First PR MergeHKUDS/OpenHarness16k1 repos~847Automated safety check: PassMIT
Migrate Internal Package into GhostTryGhost/Ghost55k—~3.8kAutomated safety check: PassMIT
Create Pull Requestcline/cline70k1 repos~1.6kAutomated safety check: PassApache-2.0

Similar skills

  • Walks the last step of a branch: confirm tests pass, detect the git environment, ask how to integrate, carry out your choice and clean up the worktree.

    296k GitHub starsUsed in 5 repos~1.9k tokens
    DevelopmentAuto-check passed
  • Official

    Digs into why code is shaped the way it is by checking git history, pull requests and connected tools in parallel, then reporting a cited read on the tradeoffs.

    10k GitHub starsUsed in 9 repos~2.6k tokens
    DevelopmentAuto-check passed
  • Merges external GitHub pull requests while keeping the original author credited, and fixes conflicts after the merge instead of rewriting the contribution.

    16k GitHub starsUsed in 1 repo~847 tokens
    DevelopmentAuto-check passed
  • Moves a package from another TryGhost repository into Ghost as an internal workspace package while keeping its Git history, with checkpoints for the steps that need an administrator.

    55k GitHub stars~3.8k tokensUpdated today
    DevelopmentAuto-check passed
  • Opens a GitHub pull request from your current branch with the gh CLI, after reviewing the commits and diff and gathering the details the PR needs.

    70k GitHub starsUsed in 1 repo~1.6k tokens
    DevelopmentAuto-check passed
  • Git Merge Conflict Resolver

    tailcallhq/forgecode

    Resolves Git merge conflicts with a plan-first workflow that keeps both sides' intent, regenerates lock files and backs up deleted-but-modified files.

    7.6k GitHub starsUsed in 1 repo~4.5k tokens
    DevelopmentAuto-check passed

More from umputun/cc-thingz

All 16 skills in this repo
  • Exec

    umputun/cc-thingz

    Execute plan tasks sequentially using subagents. An agent skill from umputun/cc-thingz.

    484 GitHub stars~8k tokensUpdated 3 days ago
    Auto-check passed
  • New

    umputun/cc-thingz

    A skill your agent uses when user asks to create a release, cut a release, or publish a version.

    484 GitHub stars~1.9k tokensUpdated 3 days ago
    Auto-check: notes
  • Root Cause Investigator

    umputun/cc-thingz

    Systematic root cause analysis for errors, bugs, and unexpected behaviors using 5-Why methodology.

    484 GitHub stars~879 tokensUpdated 3 days ago
    Auto-check passed
  • Ask Codex

    umputun/cc-thingz

    Consult OpenAI Codex for investigation, debugging, or code review.

    484 GitHub stars~2.6k tokensUpdated 3 days ago
    Auto-check: notes
  • Backlog

    umputun/cc-thingz

    Read, work, and maintain a Git repo's deferred-work items in docs/backlog/, one file per item.

    484 GitHub stars~3.4k tokensUpdated 3 days ago
    Auto-check: notes
  • Brainstorm

    umputun/cc-thingz

    Use before any creative work or significant changes. An agent skill from umputun/cc-thingz.

    484 GitHub stars~1.7k tokensUpdated 3 days ago
    Auto-check: notes

Works with

Categories

Questions about Git Review

What does Git Review do?

Interactive git diff annotation review. An agent skill from umputun/cc-thingz. Git Review is an agent skill from umputun/cc-thingz. Interactive git diff annotation review.

When should I use Git Review?

Git Review fits situations like: tasks that involve Git workflow.

How do I install Git Review in Claude Code?

Run `npx skills add umputun/cc-thingz --skill git-review -a claude-code`. Or copy the skill folder (plugins/review/skills/git-review in umputun/cc-thingz) into .claude/skills/git-review in your project. Claude Code loads it when a task matches its description.

How do I install Git Review in Codex?

Run `npx skills add umputun/cc-thingz --skill git-review -a codex`. Or copy the skill folder (plugins/review/skills/git-review in umputun/cc-thingz) into .agents/skills/git-review in your project. Codex loads it when a task matches its description.

Can I use Git Review in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add umputun/cc-thingz --skill git-review -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/git-review, .gemini/skills/git-review, .github/skills/git-review and .opencode/skills/git-review in your project.

What does Git Review need to run?

Going by SKILL.md and its folder, Git Review needs Python for the scripts in its folder. Our summary lists: Python 3. Its frontmatter pre-approves these tools: Bash, Read, Edit, Write, Grep, Glob.

Does Git Review access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Git Review safe to install?

Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Git Review use?

Git Review is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Git Review use?

About 1k tokens (SKILL.md is roughly 4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Git Review?

Skills that share tags, products or a category with Git Review: Finishing a Development Branch (obra/superpowers, 296k stars), Code Design Rationale Investigator (cursor/plugins, 10k stars), Contributor-First PR Merge (HKUDS/OpenHarness, 16k stars) and Migrate Internal Package into Ghost (TryGhost/Ghost, 55k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Git Review?

umputun (a GitHub user) maintains it in umputun/cc-thingz, which has 484 GitHub stars. The repository holds 16 skills in this directory. The repository was last updated on October 5, 2026.

Source: umputun/cc-thingz on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.