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.
curl -O https://raw.githubusercontent.com/band-app/band/main/.claude/skills/review-changes/SKILL.mdgit clone --depth 1 https://github.com/band-app/bandWrote 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.
[](https://agentmods.dev/skills/band-app/band/review-changes)<a href="https://agentmods.dev/skills/band-app/band/review-changes"><img src="https://agentmods.dev/badge/skills/band-app/band/review-changes/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.
<a href="https://agentmods.dev/skills/band-app/band/review-changes"><img src="https://agentmods.dev/badge/skills/band-app/band/review-changes.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00136 | $0.02544 |
| Opus 5.5 | $0.00054 | $0.01018 |
| Sonnet 5.5 | $0.00027 | $0.00509 |
| Haiku 4.5 | $0.00014 | $0.00254 |
Grade A, and why
review-changes 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 25d 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.
How it starts
The opening of the file, as written. The whole thing — 208 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review Changes
This skill orchestrates Band's four-specialist PR review. It is read-only — the caller decides what to do with the output.
You are the orchestrator. Your job is to:
- Gather context (changed files, linked issues, PR details, repo conventions).
- Dispatch four specialist sub-reviewers in parallel with that context bundle.
- Aggregate findings per section (one section per specialist).
- Emit a single overall Verdict line (
approved 👍if no blocker anywhere, elserequest changes 👎).
You never modify files yourself. You never paraphrase findings. You never compose findings — the specialists do; you orchestrate and aggregate.
Specialists
| Specialist | Criteria | Scope |
|---|---|---|
coding-reviewer |
.claude/coding-criteria.md (CODE-1…CODE-19) |
production source code |
testing-reviewer |
.claude/testing-criteria.md (TEST-1…TEST-35) |
tests, fixtures, page objects |
security-reviewer |
.claude/security-criteria.md (SEC-1…SEC-15) |
source, tests, config, scripts |
performance-reviewer |
.claude/performance-criteria.md (PERF-1…PERF-10) |
production source, hot paths |
Each specialist also applies cross-cutting concerns (correctness, pattern drift) inside its scope, tagged correctness: / pattern: instead of a rule ID. Specialists do not compose the Verdict — that's your job.
Step 1 — Gather context
The caller supplies, at minimum, REPO and one of (PR NUMBER) or (BASE + HEAD refs).
Diff
- Open PR:
gh pr diff <num>for the diff;gh pr view <num> --json title,body,headRefName,baseRefNamefor metadata. - No PR yet (local pre-push):
git diff <base>...<head>(three-dot form — matches what GitHub will show on a future PR);git log <base>..<head> --format='%h %s%n%b'for commit history.
Do not truncate.
Linked issues
Look for, in order:
closes #<n>/fixes #<n>/resolves #<n>in PR body or commit messages.- A leading number in the branch name (
123-fix-foo→ issue 123).
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.
- 25d ago Changed b68cf23c205f
- 26d ago Changed 4ac8279bbecf
- 2mo ago First seen · 208 lines · 136 tokens per session scan A b44632eb2d8e
review-changes is a skill published in the GitHub repository band-app/band (5 stars, last pushed today), licensed MIT. It adds 136 tokens to every session and 2,544 once invoked, about $0.0005 per session on Opus 5.5. 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.
Other skills, from other repositories
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…