Skip to content
Agentmart
Submit a tool

bounds-review

Review a pinned diff or change for correctness, requirement compliance, and maintainability, separating actionable findings from preferences and unverified…

Skill by boundsj

IndexedMIT
Write a review

Chalk Labs

Need help deploying bounds-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/boundsj-bounds-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 a pinned diff or change for correctness, requirement compliance, and maintainability, separating actionable findings from preferences and unverified assumptions.

Use cases: security

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. 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/bounds-review

What's inside

Skill name
bounds-review
Description
Review a pinned diff or change for correctness, requirement compliance, and maintainability, separating actionable findings from preferences and unverified assumptions.
License
MIT
Instructions
19 lines in SKILL.md · view on GitHub

Files (4)

  • LICENSE.txt
  • NOTICE.md
  • SKILL.md
  • protocol.md · references/

SKILL.md (first lines)

# Bounds review

Resolve the requested base and head to commit SHAs before reviewing. For a branch or PR, record the merge-base and review `git diff <merge-base-sha> <head-sha>`; if the user requested a literal endpoint comparison, use that instead. Validate refs and note an empty diff. Infer the base from the PR or repository when clear; ask only if the choice changes the review materially.

For uncommitted work, capture the staged and unstaged diff plus relevant untracked files as a fixed snapshot outside the change. Record its identity and HEAD; do not pretend HEAD includes local edits. Read [review protocol](references/protocol.md) for snapshot details or delegated review.

Find the applicable request/spec and project conventions. If requirements are unavailable, state that limitation and still review the code. Check:

- **Correctness:** failing inputs, state transitions, error paths, compatibility, and tests that could miss a real defect.
- **Requirements:** missing behavior, unintended scope, and retained behavior at risk.
- **Maintainability:** concrete costs in the changed paths, judged against the project's conventions. Preferences are optional observations.

Use one independent reviewer for consequential changes when delegation is available and permitted by existing user and host instructions. Reuse authorization already granted; do not ask for it again. Add another only for consequential uncertainty or disputed findings. Discover capabilities and follow the linked protocol. Never silently swap a requested provider/model. Timeout, failure, or silence is not approval. If no reviewer can start, supply the protocol’s review packet and label any local review accurately.

Assign stable finding IDs across rounds. Use **blocker** for a broken intended case or critical safety failure, **should** for a concrete in-scope defect, and **nit** for optional improvements. Give severity, file/line, trigger, consequence, evidence, and a focused correction. Distinguish executed checks, source-based reasoning, and assumptions. Evaluate findings on their evidence rather than reviewer agreement. State “no actionable findings” when appropriate, with coverage limits.

A review request returns findings; it does not authorize edits or publishing comments. When fixes are authorized, rerun affected checks and review the changed head. Bound the process to two fix/review cycles unless the user specifies otherwise; report unresolved issues at the limit.

From boundsj/bounds-skills, MIT.

More from boundsj/bounds-skills

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Oct 4, 2026 (26 days ago)

From GitHub (fetched Oct 24, 2026).

Details

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

More from boundsj

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 bounds-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 bounds-review?

CallGet help
Cite this page

bounds-review skill. Agent Mart. https://agentmart.dev/skills/boundsj-bounds-review (last updated 2026-10-24)