band: Skill for Claude Code

.claude/skills/review-and-apply/SKILL.md

review-and-apply is a skill for Claude Code from band-app/band. It costs 127 tokens per session (1,454 once invoked), scanned A, original, MIT.

A review-and-fix workflow that runs a pull-request review, applies the reported changes, and verifies them with linting and tests.

In plain words
What is it for?
Preparing a branch for review by running coding, testing, security, and performance checks, applying each finding’s suggested fix, and running verification commands.
Why use it?
It turns review findings into concrete edits and checks the result before code is pushed. Linting checks code style and common mistakes.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions CLAUDE.md.

This is band-app/band's own configuration. It tells Claude Code how to work on band itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything band configures →

Reuse

Borrowing it

Nothing to install: this file belongs to band-app/band. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/band-app/band/main/.claude/skills/review-and-apply/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/band-app/band

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for review-and-apply

README.md
[![agentmods](https://agentmods.dev/badge/skills/band-app/band/review-and-apply/github.svg)](https://agentmods.dev/skills/band-app/band/review-and-apply)
Your own site
<a href="https://agentmods.dev/skills/band-app/band/review-and-apply"><img src="https://agentmods.dev/badge/skills/band-app/band/review-and-apply/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for review-and-apply

Your own site · 80×15
<a href="https://agentmods.dev/skills/band-app/band/review-and-apply"><img src="https://agentmods.dev/badge/skills/band-app/band/review-and-apply.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 127 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,454 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00127 $0.01454
Opus 5 $0.00063 $0.00727
Sonnet 5 $0.00025 $0.00291
Haiku 4.5 $0.00013 $0.00145

Measured 11d ago against content hash 9a56cdf7d08a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

review-and-apply 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 11d 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-and-apply/SKILL.md · 129 lines

How it starts

The opening of the file, as written. The whole thing — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Review and Apply — Review → Fix → Verify

Two-phase flow:

  1. Review — invoke the review-changes skill. It already knows how to gather context, dispatch the four specialist reviewers in parallel, and return sectioned findings plus a single Verdict: line. You just tell it what to review.
  2. Fix — read the findings, apply each one's Fix: with Edit/Write, verify with lint/clippy/tests. Don't re-review; trust the specialists unless a finding is clearly wrong.

Step 1 — Identify the change set

Gather the facts the reviewer needs. Don't make it re-derive them.

# Refresh remote refs so the base comparison isn't stale.
git fetch origin --quiet

# Base ref (merge target). Default origin/main; fall back if HEAD ref points elsewhere.
BASE=$(git symbolic-ref --quiet refs/remotes/origin/HEAD 2>/dev/null | sed 's|^refs/remotes/||' || echo origin/main)
HEAD=$(git rev-parse --short HEAD)

# Open PR? (If yes, the reviewer will prefer `gh pr diff/view`.)
gh pr view --json number,headRefName,baseRefName 2>/dev/null || echo "no PR yet"

# Linked issues: PR body, commit messages, branch name.
{
  gh pr view --json body --jq .body 2>/dev/null
  git log "$BASE..HEAD" --format='%s%n%b'
  git rev-parse --abbrev-ref HEAD
} | grep -iEoh '(closes|fixes|resolves) +#[0-9]+|#[0-9]+' | sort -u

If you find no linked issue, pass issues=none detected. The reviewer still runs against the diff; linked-issue context is just additional input for the specialists when present.

Step 2 — Invoke review-changes

Use the Skill tool to invoke the review-changes skill. The skill is self-contained — it loads its specialists, fetches the diff/issue context itself, and produces the sectioned report.

Skill(skill="review-changes", args="
Review this change set.

- Base:   <BASE ref>
- Head:   <HEAD short sha>
- PR:     <number, or 'no PR yet'>
- Issues: <comma-separated list of #N, or 'none detected'>
")

The skill returns a sectioned report with four fixed-order domain headers (Coding → Testing → Security → Performance), each with a status emoji, followed by a single overall Verdict line:

Read the full file on GitHub · 129 lines

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. 11d ago First seen · 129 lines · 127 tokens per session scan A 9a56cdf7d08a

Subscribe to this mod's changes

review-and-apply is a skill published in the GitHub repository band-app/band (5 stars, last pushed yesterday), licensed MIT. It adds 127 tokens to every session and 1,454 once invoked, about $0.0006 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 2026-08-31.

Related

Other skills, from other repositories

adversarial-reviewer

Adversarial code review that assumes bugs exist and hunts for them. Use when asked to review code, find bugs, audit for correctness, stress-test a PR, or when someone says "tear this apart" or "what's wrong with this". Give no benefit of the doubt — every line is guilty until proven innocent.

emdash-cms/emdash · 71 tokens

adk-go-self-review

Review an ADK Go change the way a maintainer will — a fresh-context pass over the whole diff, five lenses (correctness and tests, scope, simplicity, style, adk-python parity), and the mutation check that proves your tests pin the change. Use before opening a PR, before any later push that changes code, and when asked…

google/adk-go · 87 tokens

go-testing

Trigger: Go tests, go test coverage, Bubbletea teatest, golden files. Apply focused Go testing patterns.

Gentleman-Programming/gentle-ai · 26 tokens

semgrep-rule-variant-creator

Creates language variants of existing Semgrep rules. Use when porting a Semgrep rule to specified target languages. Takes an existing rule and target languages as input, produces independent rule+test directories for each language.

waybarrios/opencode-power-pack · 50 tokens

brooks-sweep

Full-sweep mode: runs a unified analysis across all quality dimensions — code decay, architecture, tech debt, and test quality — then applies fixes directly to the codebase. Safe changes are auto-applied; risky changes are confirmed before execution. Drawing on twelve classic engineering books. Triggers when: user…

hyhmrright/brooks-lint · 178 tokens

include-test-files-that-assert-on-behavior-being-changed-in-decl

When delegating a task affected by this skill, include.

ZaxbyHub/opencode-swarm · 29 tokens