An automated pull-request review workflow that examines code changes, sends files to focused reviewers, combines their findings, and can post comments on GitHub.

Use it when reviewing a pull request, checking changes before merge, or examining a new feature that has not received a second review.

It provides another check for correctness, security, and project patterns before a change is merged. Human approval remains part of the process before comments are posted.

How dancing-bear-show/dancing-bear configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to dancing-bear-show/dancing-bear. 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/dancing-bear-show/dancing-bear/main/.claude/skills/code-review/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/dancing-bear-show/dancing-bear

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/dancing-bear-show/dancing-bear/code-review/github.svg)](https://agentmods.dev/skills/dancing-bear-show/dancing-bear/code-review)

Your own site

<a href="https://agentmods.dev/skills/dancing-bear-show/dancing-bear/code-review"><img src="https://agentmods.dev/badge/skills/dancing-bear-show/dancing-bear/code-review/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/dancing-bear-show/dancing-bear/code-review"><img src="https://agentmods.dev/badge/skills/dancing-bear-show/dancing-bear/code-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,568 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.

Model	Per session	Once invoked
Fable 5.1	$0.00038	$0.01568
Opus 5.5	$0.00015	$0.00627
Sonnet 5.5	$0.00008	$0.00314
Haiku 4.5	$0.00004	$0.00157

Measured yesterday against content hash 706c48171b74, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

code-review 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 yesterday.

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/code-review/SKILL.md · 154 lines

How it starts

The opening of the file, as written. The whole thing — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Code Review

Runs an adversarial swarm review on a PR: fetch context, filter relevant concerns, fan out per-file validators in parallel, consolidate and fact-check findings, present for approval, then post inline GitHub comments.

When to Use

User says "review PR", "code review", or "review my changes"
Before merge when a second set of eyes is needed on correctness, security, or patterns
After implementing a domain or feature that hasn't had human review yet

How to Run

IMPORTANT: Use the /workflow skill — do NOT call ./bin/workflow run --execute directly. It only writes dispatch files and exits (status=pending). The /workflow skill is what actually spawns agents, waits for results, and handles human gates.

Skill(skill="workflow", args="--workflow workflows/code/code-review.yaml --params pr_number=314")

Or invoke directly as a skill — the orchestrator resolves the PR number from the current branch if pr_number is omitted.

Workflow Params

Param	Default	Description
`pr_number`	`""`	PR number to review (required; auto-detected from branch if blank)
`pr_size`	`"small"`	`small`: one consolidated reviewer; `large`: full per-guide fan-out
`local`	`"false"`	`true`: review the local branch before a PR exists (diff `merge-base(origin/main, HEAD)..HEAD`, no GitHub calls, nothing posted); `/open-pr` runs it this way

DAG Overview

G0:  init                     (inline)
G1:  fetch-pr-context         (researcher)
G2:  concern-sweep-dispatch   (inline)
G3:  concern-sweep × N        (haiku-reviewer, parallel — one per guide)
     review-consolidated      (inline, parallel with concern-sweep)
G4:  concern-sweep-merge      (inline)
G5:  enumerate-targets        (researcher)
G6:  validate-concerns × N    (unit-validator, parallel)
     cross-unit-check         (cross-unit-validator, parallel with validate-concerns)
G7:  consolidate              (doc-writer)
G8:  fact-check-findings      (fact-checker)
G9:  human-gate               (propose, human_gate: true)
G10: post-comments            (code-writer)

Read the full file on GitHub · 154 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

yesterday First seen · 154 lines · 38 tokens per session scan A 706c48171b74

Subscribe to this mod's changes

code-review is a skill published in the GitHub repository dancing-bear-show/dancing-bear (7 stars, last pushed yesterday), licensed MIT. It adds 38 tokens to every session and 1,568 once invoked, about $0.0002 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 2026-11-07.

Code review automation calendar cli gmail oauth2 outlook

code-review next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
code-reviewdancing-bear-show/dancing-bear	Skill	7	yesterday	MIT	A	38	Claude Code
gogolafkfreund/nixos_config	Skill	32	yesterday	GPL-3.0	A	125	Claude Code, Codex
google-workspace-authbobmatnyc/claude-mpm	Skill	158	2mo ago	none	A	22	Claude Code
find-simplificationsQwenLM/qwen-code	Skill	29k	today	Apache-2.0	C	103	Claude Code, Codex
swarm-pr-reviewZaxbyHub/opencode-swarm	Skill	518	today	MIT	A	91	Claude Code
code-reviewjrswab/axe	Skill	909	17d ago	Apache-2.0	A	0	Claude Code, Codex
agent-debug-ciNVIDIA/elements	Skill	115	yesterday	Apache-2.0	A	80	Claude Code, Codex

dancing-bear: Skill for Claude Code