Agent skill

Review Delta

by tirth8205 in tirth8205/code-review-graph

Reviews only the code changed since the last commit, using a code-graph MCP server to find risk-scored changes, test gaps and the blast radius, then writes a short report.

MITAuto-check passedDevelopment

Install Review Delta

skills CLI
$ npx skills add tirth8205/code-review-graph --skill review-delta -a claude-code

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

GitHub CLI
$ gh skill install tirth8205/code-review-graph review-delta --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/tirth8205/code-review-graph.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/review-delta .claude/skills/review-delta && 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
review-delta
GitHub stars
32k
Token cost
~325 tokens
SKILL.md length
134 words
Files
1
Skills in repo
7
Repo updated
First seen
Licence
MIT

At a glance

Reviews only the code changed since the last commit, using a code-graph MCP server to find risk-scored changes, test gaps and the blast radius, then writes a short report.

  • Works in 5 steps: Call… → Call… → Call… → …
  • Reviewing the changes in the latest commit before pushing
  • SKILL.md covers Steps and Report
  • Calls git

What it does

This skill reviews the diff against `HEAD~1` instead of whole files. The agent first calls `get_minimal_context_tool` and, if the graph is not ready, builds it with `build_or_update_graph_tool`. It then calls `detect_changes_tool` for risk-scored changed functions, test gaps and affected flows, and `get_review_context_tool` when it needs source snippets and review guidance such as untested functions or a wide blast radius.

For each untested high-risk function it confirms the gap with `query_graph_tool` using a tests_for pattern, and it moves from minimal to standard detail only for a high-risk item that stays unclear, avoiding whole-file loads. The report has a one-line summary, a low, medium or high risk rating based on blast radius, issues (bugs, missing tests, style), the impacted files and functions, and recommendations.

When your agent uses it

  • Reviewing the changes in the latest commit before pushing
  • Finding which functions a change affects and whether they have tests
  • Keeping a code review short on tokens in a large repository

Example prompts

  • “Review my last commit and tell me what it could break.”
  • “Run a delta review and list any high-risk functions that have no tests.”
  • “What is the blast radius of the changes I just made?”

Requirements

  • The code-review-graph MCP tools such as `detect_changes_tool`
  • A git repository with a previous commit to compare against

Workflow steps

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

  1. Call get_minimal_context_tool(task="review changes"). If it returns status: not_ready, call build_or_update_graph_tool() and continue.
  2. Call detect_changes_tool(detail_level="minimal") for risk-scored changed functions, test gaps and affected flows. Changes come from git…
  3. Call get_review_context_tool(detail_level="minimal") when you need source snippets for the changed areas and review_guidance (untested…
  4. For each untested high-risk function, confirm with query_graph_tool(pattern="tests_for", target="").
  5. Use detail_level="standard" only for a high-risk item the minimal output leaves unclear. Do not load whole files unless a snippet is not…

What it can do on your machine

Read from SKILL.md and the folder at commit 6b12d11. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    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 Delta loads about 325 tokens when it runs. Until then it costs about 35 tokens; SKILL.md has 134 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~35
When it runs · the whole SKILL.md, loaded when a task matches
~325

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 passed

The automated check found no risky patterns in SKILL.md.

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 tirth8205/code-review-graph at commit 6b12d11, republished under its MIT licence (© tirth8205). 134 words, ~325 tokens.

Download SKILL.mdSave it as .claude/skills/review-delta/SKILL.md (or your agent's skills folder).
name
review-delta
description
Review only changes since last commit using impact analysis. Token-efficient delta review with automatic blast-radius detection.
argument-hint
[file or function name]

Review Delta

Review only the changed code and its blast radius.

Steps

  1. Call get_minimal_context_tool(task="review changes"). If it returns status: not_ready, call build_or_update_graph_tool() and continue.
  2. Call detect_changes_tool(detail_level="minimal") for risk-scored changed functions, test gaps and affected flows. Changes come from git diff against HEAD~1; if the argument names a file, pass it in changed_files.
  3. Call get_review_context_tool(detail_level="minimal") when you need source snippets for the changed areas and review_guidance (untested functions, wide blast radius, inheritance changes).
  4. For each untested high-risk function, confirm with query_graph_tool(pattern="tests_for", target="<function>").
  5. Use detail_level="standard" only for a high-risk item the minimal output leaves unclear. Do not load whole files unless a snippet is not enough.

Report

  • Summary: one line
  • Risk: low, medium or high, from the blast radius
  • Issues: bugs, missing tests, style
  • Blast radius: impacted files and functions
  • Recommendations

© tirth8205, 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 skills/review-delta of tirth8205/code-review-graph.

Open the folder on GitHubat commit 6b12d11

Compare with similar skills

Review Delta 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.

Review Delta compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Review Delta this skilltirth8205/code-review-graph32k—~325Automated safety check: PassMIT
Liveagent Code ReviewStack-Cairn/LiveAgent2.2k—~2kAutomated safety check: PassMIT
PR Review Feedback Handlergittower/git-flow-next458—~2.9kAutomated safety check: NotesCustom licence
Code Review ChecklistshareAI-lab/learn-claude-code78k4 repos~1.1kAutomated safety check: PassMIT
Open Code Review CLIalibaba/open-code-review46k—~3.1kAutomated safety check: PassApache-2.0
Understand Diff AnalysisEgonex-AI/Understand-Anything86k—~1.4kAutomated safety check: PassMIT

Similar skills

  • Liveagent Code Review

    Stack-Cairn/LiveAgent

    Review an open GitHub pull request or the current local branch and working tree with parallel, independent reviewers and evidence-based validation.

    2.2k GitHub stars~2k tokensUpdated today
    DevelopmentAuto-check passed
  • PR Review Feedback Handler

    gittower/git-flow-next

    Fetches review comments on a pull request, judges each one, writes the evaluation to a plan file and implements accepted changes, waiting for approval before anything public.

    458 GitHub stars~2.9k tokensUpdated 1 mo ago
    DevelopmentAuto-check: notes
  • Code Review Checklist

    shareAI-lab/learn-claude-code

    Reviews code against a five-part checklist covering security, correctness, performance, maintainability and testing, and reports findings in a fixed format.

    78k GitHub starsUsed in 4 repos~1.1k tokens
    DevelopmentAuto-check passed
  • Open Code Review CLI

    alibaba/open-code-review

    Runs the ocr command-line tool to review Git changes, a commit or a branch comparison with an AI model, returning line-level comments and optionally applying fixes.

    46k GitHub stars~3.1k tokensUpdated today
    DevelopmentAuto-check passed
  • Understand Diff Analysis

    Egonex-AI/Understand-Anything

    Reads your git changes or a pull request against a prebuilt knowledge graph of the project to explain what changed, which components are affected and what is risky.

    86k GitHub stars~1.4k tokensUpdated yesterday
    DevelopmentAuto-check passed
  • Open Code Review Delegate

    alibaba/open-code-review

    Has the host agent do the code review itself while the ocr CLI handles file selection and rule lookup, covering workspace changes, branch ranges or single commits.

    46k GitHub stars~2.3k tokensUpdated today
    DevelopmentAuto-check passed

More from tirth8205/code-review-graph

  • Knowledge Graph PR Review

    tirth8205/code-review-graph

    Reviews a pull request or branch diff with a code knowledge graph and produces a structured review that includes blast-radius analysis.

    32k GitHub stars~452 tokensUpdated 3 days ago
    Auto-check passed
  • Graph-Based Bug Tracing

    tirth8205/code-review-graph

    Traces a bug through a code knowledge graph, following callers, callees and execution flow before opening source files, within a small token budget.

    32k GitHub starsUsed in 1 repo~287 tokens
    Auto-check passed
  • Explore Codebase with Graph

    tirth8205/code-review-graph

    Navigates a codebase through the code-review-graph MCP tools: architecture overview, symbol search, caller and callee tracing, flows and oversized functions.

    32k GitHub starsUsed in 1 repo~335 tokens
    Auto-check passed
  • Graph-Guided Safe Refactoring

    tirth8205/code-review-graph

    Plans a refactor from a code dependency graph, previews renames before applying them and checks that the final impact matches the plan.

    32k GitHub starsUsed in 1 repo~332 tokens
    Auto-check passed
  • Graph-Based Change Review

    tirth8205/code-review-graph

    Reviews a change set using a code knowledge graph for risk scores, blast radius and test gaps, and ends with a merge recommendation.

    32k GitHub starsUsed in 1 repo~331 tokens
    Auto-check passed
  • Code Review Graph Builder

    tirth8205/code-review-graph

    Builds or incrementally updates the code-review knowledge graph for a repository and reports whether the build succeeded, partly or failed.

    32k GitHub stars~295 tokensUpdated 3 days ago
    Auto-check passed

Categories

Questions about Review Delta

What does Review Delta do?

Reviews only the code changed since the last commit, using a code-graph MCP server to find risk-scored changes, test gaps and the blast radius, then writes a short report. This skill reviews the diff against `HEAD~1` instead of whole files. The agent first calls `get_minimal_context_tool` and, if the graph is not ready, builds it with `build_or_update_graph_tool`.

When should I use Review Delta?

Review Delta fits situations like: reviewing the changes in the latest commit before pushing; finding which functions a change affects and whether they have tests; keeping a code review short on tokens in a large repository.

How do I install Review Delta in Claude Code?

Run `npx skills add tirth8205/code-review-graph --skill review-delta -a claude-code`. Or copy the skill folder (skills/review-delta in tirth8205/code-review-graph) into .claude/skills/review-delta in your project. Claude Code loads it when a task matches its description.

How do I install Review Delta in Codex?

Run `npx skills add tirth8205/code-review-graph --skill review-delta -a codex`. Or copy the skill folder (skills/review-delta in tirth8205/code-review-graph) into .agents/skills/review-delta in your project. Codex loads it when a task matches its description.

Can I use Review Delta 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 tirth8205/code-review-graph --skill review-delta -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/review-delta, .gemini/skills/review-delta, .github/skills/review-delta and .opencode/skills/review-delta in your project.

What does Review Delta need to run?

Going by SKILL.md and its folder, Review Delta needs the command-line tools its instructions call (git). Our summary lists: The code-review-graph MCP tools such as `detect_changes_tool`; A git repository with a previous commit to compare against.

Does Review Delta access the network?

SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Review Delta safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Review Delta use?

Review Delta 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 Review Delta use?

About 325 tokens (SKILL.md is roughly 1.3k 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 Review Delta?

Skills that share tags, products or a category with Review Delta: Liveagent Code Review (Stack-Cairn/LiveAgent, 2.2k stars), PR Review Feedback Handler (gittower/git-flow-next, 458 stars), Code Review Checklist (shareAI-lab/learn-claude-code, 78k stars) and Open Code Review CLI (alibaba/open-code-review, 46k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Review Delta?

tirth8205 (a GitHub user) maintains it in tirth8205/code-review-graph, which has 32,014 GitHub stars. The repository holds 7 skills in this directory. The repository was last updated on October 6, 2026.

Source: tirth8205/code-review-graph on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.