review-staged

A code-review helper that examines staged changes and every commit on the branch since it split from the main branch.

In plain words
What is it for?
Use it before pushing to review the complete branch diff, assess architecture and scope, and generate structured review comments.
Why use it?
It provides a full branch-level review, so problems in earlier commits are not missed when only the latest staged files are checked.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/microsoft/agent365-devtools/review-staged
Any agent
npx skills add microsoft/Agent365-devTools --skill review-staged
Clone the repo
git clone --depth 1 https://github.com/microsoft/Agent365-devTools

Made for: Claude Code, Codex.

Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,526 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 $0.00032 $0.06526
Opus 5 $0.00016 $0.03263
Sonnet 5 $0.00006 $0.01305
Haiku 4.5 $0.00003 $0.00653

Measured 2d ago against content hash a00203ca73ad, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

review-staged 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 2d 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.

.claude/skills/review-staged/SKILL.md · 268 lines

How it starts

The opening of the file, as written. The whole thing — 268 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Review Staged Files Skill

Generate AI-powered code review comments covering both your currently staged changes and all commits on the branch since it diverged from main. This gives the same full-branch view that Copilot and other PR reviewers see — not just what you're about to commit.

Usage

/review-staged              # Review staged changes + full branch diff against main
/review-staged --verbose    # Show detailed analysis

Examples:

  • /review-staged - Review staged changes and all branch commits not yet on main
  • /review-staged --verbose - Show detailed analysis with full context

What this skill does

  1. Checks for staged files using git diff --staged --name-only
  2. Fetches staged changes using git diff --staged
  3. Fetches full branch diff using git diff $(git merge-base HEAD origin/main)...HEAD — covers all commits on the branch, not just staged files. This prevents issues in prior commits from going unreviewed.
  4. Combines both diffs for review: staged diff = what you're about to add; branch diff = full PR picture that Copilot will see
  5. Performs architectural review: Questions design decisions, checks for scope creep, validates use cases
  6. Analyzes changes for security, testing, design patterns, and code quality issues
  7. Differentiates contexts: CLI code vs GitHub Actions code (different standards)
  8. Creates actionable feedback: Specific refactoring suggestions based on file names and patterns
  9. Verifies documentation completeness — detects user-visible surface changes (new CLI flags, renamed public types, payload contract changes, etc.) and verifies CHANGELOG.md + relevant README.md/design.md are updated in the same diff. For renames, greps all *.md files for stale references. See the Documentation Completeness section in .claude/agents/pr-code-reviewer.md for detection rules and severity calibration.
  10. Runs the test suite and measures per-test timing — flags any test taking > 1 second as a performance regression
  11. Generates structured review document saved to a markdown file
  12. Shows summary of all issues found organized by severity

Read the full file on GitHub · 268 lines

Files

What ships with it

1 file 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. 2d ago First seen · 268 lines · 32 tokens per session scan A a00203ca73ad

Subscribe to this mod's changes

review-staged is a skill published in the GitHub repository microsoft/Agent365-devTools (61 stars, last pushed 5d ago), licensed MIT. It adds 32 tokens to every session and 6,526 once invoked, about $0.0002 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 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

agent-host-chat-contributions

Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.

microsoft/vscode · 56 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens