Skip to content
Back to skills

Reviewing Code

ASecurity

Reviews a code diff (PR, branch, commit range, working tree, or a diff already in the conversation) in a fresh-context read-only subagent, because a session holding the conversation is a biased reviewer, and returns Conventional Comments findings with an APPROVE, REQUEST CHANGES, or COMMENT verdict. Use when asked to review code, a diff, or a PR, including a pasted diff, a .diff or .patch file, or a diff shown earlier; never review it inline. Not for design docs; use reviewing-design-docs.

  • 2 stars
  • 0 votes
  • 0 copies
  • 0 views
  • Added October 21, 2026
ai-agentsshelltestingcode-reviewgit

Security analysis

A100/100

Pro scans all 7 files and shows the line behind each finding

Scanned October 21, 2026

npx -y skills add bostonaholic/skills --skill reviewing-code --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Reviewing Code?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Reviewing Code
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/bostonaholic-reviewing-code/badge)](https://www.skillsdirectory.com/skills/bostonaholic-reviewing-code)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: reviewing-code
description: 'Reviews a code diff (PR, branch, commit range, working tree, or a diff already in the conversation) in a fresh-context read-only subagent, because a session holding the conversation is a biased reviewer, and returns Conventional Comments findings with an APPROVE, REQUEST CHANGES, or COMMENT verdict. Use when asked to review code, a diff, or a PR, including a pasted diff, a .diff or .patch file, or a diff shown earlier; never review it inline. Not for design docs; use reviewing-design-docs.'
effort: high
argument-hint: "[<diff target>]"
---

# Code Review

## Target

`$ARGUMENTS` names the diff: a PR number or URL, a branch, a commit range, or
a path. A diff already in the conversation resolves to the refs it was taken
from, or else to its text, passed verbatim. With no argument, the target is
the working tree's diff against the base branch. Resolve it once into concrete
base and head refs (or paths) and hand that to the reviewer. Never ask the
user to restate it.

## Reviewer

This session holds the author's conversation, so it cannot review the work
([independent review rules](shared/independent-review.md)). Run the
[code reviewer brief](references/code-reviewer.md) in a fresh-context
subagent that holds no file-editing tool, and give it only the resolved
target and the paths of the brief and the files it links:
[finding format](shared/findings.md),
[testing rules](shared/testing.md), and
[code standards](shared/code-standards.md). If it has a shell, it runs only
the project's test command and read-only git commands. If no such subagent
can run, stop and say so. Never review inline.

External reviewers may reuse findings after later commits. Before reporting a
reused finding as current, ask a fresh read-only verifier to check its
behavioral claim against the resolved head. Supply the claim and cited paths
without the previous verdict or producer explanation. An older permalink alone
does not prove the concern is fixed. Report verification separately; never use
a cached verdict to approve newer commits or rewrite the original verdict.

## Verdict and relay

The report's first line must be a `**Verdict: ...**` line whose word is
exactly `APPROVE`, `REQUEST CHANGES`, or `COMMENT` (match the word, not the
emoji). When it is missing or wrong, run one new reviewer with the same
inputs and name the failed contract. When the second report also fails,
print it, name the failure, and stop. Never repair a verdict yourself.

Print the report in full. Name any heading deviation on its own line. When
the read-only restriction rested on the reviewer's prompt rather than its
tool grants, say so in one line after the report.

Files in this skill

  • SKILL.md2.6 KB
  • agents/openai.yaml215 B
  • references/code-reviewer.md5.3 KB
  • shared/code-standards.md2.7 KB
  • shared/findings.md1.3 KB
  • shared/independent-review.md1.1 KB
  • shared/testing.md7.1 KB

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.