Skip to content
Agentmart
Submit a tool

bob-code-review

Review changes without modifying them; report findings and draft remediation plans or comments.

Skill by mattdurham

IndexedMIT★ 10
Write a review

Chalk Labs

Need help deploying bob-code-review?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/mattdurham-bob-code-review

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Review changes without modifying them; report findings and draft remediation plans or comments.

Use cases: documents

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md and code. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/bob-code-review

What's inside

Skill name
bob-code-review
Description
Review changes without modifying them; report findings and draft remediation plans or comments.
License
MIT
Instructions
34 lines in SKILL.md · view on GitHub

Files (3)

  • SKILL.goose.md
  • SKILL.md
  • SKILL.simple.md

SKILL.md (first lines)

# Review Changes

Review the requested changes and relevant surrounding code against the request,
repository standards, and documented contracts. Inspect the current verification
configuration, including ignored `.bob/config`, for ineffective checks; missing
custom checks alone are not a defect. Use the specified diff, branch,
PR, or revision range; without one, inspect staged, unstaged, and untracked
work. Record the scope and current revision in the report. Check correctness,
edge cases, security, resource ownership, concurrency, tests, and
maintainability; apply Go guidance only to relevant Go changes. Distinguish
demonstrated defects from suggestions and cite exact locations and evidence.

This skill is read-only for the codebase and external systems. Read files and
use inspection commands only. Do not edit source, tests, configuration, or
project documentation; run builds, tests, formatters, or fixes; commit, push,
create PRs; or publish comments. A request to fix findings produces a proposed
remediation plan. Draft comments for the user to review. Review directly or use
bounded read-only reviewers when independent checks justify them. Give every
reviewer these same restrictions and consolidate their findings; never delegate
to coding, testing, commit, or publication agents.

Write findings to `.bob/state/review.md`, ordered by severity, with proposed
remedies and any limits on the review. When useful or requested, draft comments
in `.bob/state/review-comments.md` or an actionable plan in
`.bob/state/review-plan.md`, including affected files, dependencies, and
proposed verification. These review artifacts are the only permitted file
writes; keep existing implementation plans intact. Write
`.bob/state/code-review-status.md` with `COMPLETE` for no findings,
`NEEDS_BRAINSTORM` for CRITICAL/HIGH findings, `NEEDS_EXECUTE` for MEDIUM/LOW
findings, or `FAILED` for incomplete review. Include the reason and report path.
`COMPLETE` means review complete, with no implementation or publication
performed; the caller owns subsequent actions.

From mattdurham/bob, MIT.

More from mattdurham/bob

Signals

Stars
10
Forks
3
Open issues
1
Last commit (this folder)
Oct 13, 2026 (17 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from mattdurham

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get bob-code-review running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying bob-code-review?

CallGet help
Cite this page

bob-code-review skill. Agent Mart. https://agentmart.dev/skills/mattdurham-bob-code-review (last updated 2026-10-24)