
review-delta
Review only changes since last commit using impact analysis. Token-efficient delta review with automatic blast-radius detection.
- Installs
- 1.2K
- Last 24h
- —
- Trending rank
- —
- Security
- Not audited
Install
Works with every agent the skills CLI supports.
npx skills add https://github.com/tirth8205/code-review-graph --skill review-delta- 01
Install
Run the command in your project. The CLI asks which agents to install for.
- 02
Describe the task
Ask your agent for something this skill covers. It loads review-delta automatically when relevant.
- 03
Review the result
The agent follows the SKILL.md steps, scripts and references bundled with the skill.
SKILL.md
The instructions your agent reads when the skill is triggered.
Review Delta
Review only the changed code and its blast radius.
Steps
- Call
get_minimal_context_tool(task="review changes"). If it returnsstatus: not_ready, callbuild_or_update_graph_tool()and continue. - Call
detect_changes_tool(detail_level="minimal")for risk-scored changed functions, test gaps and affected flows. Changes come fromgit diffagainstHEAD~1; if the argument names a file, pass it inchanged_files. - Call
get_review_context_tool(detail_level="minimal")when you need source snippets for the changed areas andreview_guidance(untested functions, wide blast radius, inheritance changes). - For each untested high-risk function, confirm with
query_graph_tool(pattern="tests_for", target="<function>"). - 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
FAQ
What does the review-delta skill do?
Review only changes since last commit using impact analysis. Token-efficient delta review with automatic blast-radius detection.
How do I install review-delta?
Run npx skills add https://github.com/tirth8205/code-review-graph --skill review-delta in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/review-delta/ (personal) or .claude/skills/review-delta/ (project).
Which AI agents can use review-delta?
Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.
Is review-delta safe to install?
No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.
Who maintains review-delta?
It is published by tirth8205 in tirth8205/code-review-graph. It has 1,167 recorded installs.
More from tirth8205/code-review-graph
build-graph
tirth8205/code-review-graph
Build or update the code review knowledge graph. Run this first to initialize, or let hooks keep it updated automatically.
review-pr
tirth8205/code-review-graph
Review a PR or branch diff using the knowledge graph for full structural context. Outputs a structured review with blast-radius analysis.
explore codebase
tirth8205/code-review-graph
Navigate and understand codebase structure using the knowledge graph
refactor safely
tirth8205/code-review-graph
Plan and execute safe refactoring using dependency analysis
review changes
tirth8205/code-review-graph
Perform a structured code review using change detection and impact
debug issue
tirth8205/code-review-graph
Systematically debug issues using graph-powered code navigation
Popular code quality & workflow skills
grill-me
mattpocock/skills
A relentless interview to sharpen a plan or design.
improve-codebase-architecture
mattpocock/skills
Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.
handoff
mattpocock/skills
Compact the current conversation into a handoff document for another agent to pick up.
domain-modeling
mattpocock/skills
Build and sharpen a project's domain model. Use when discussing codebase terminology, writing or editing a GLOSSARY.md, or recording or editing an ADR.
codebase-design
mattpocock/skills
Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable, or when another skill needs the deep-module vocabulary.
diagnosing-bugs
mattpocock/skills
Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.