A pull-request review guide for checking changes against the angry-bear project's architecture and coding rules. A pull request is a proposed code change submitted for review before merging.

Use it to review pull requests, audit architecture compliance, and validate changes against the project's required tests and conventions.

It catches agent-specific code in the wrong places, hardcoded paths or names, formatting and lint problems, and insufficient test coverage.

pr-review — Skill for Claude Code by bluebear-io

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add bluebear-io/angry-bear --skill pr-review

Clone the repo

git clone --depth 1 https://github.com/bluebear-io/angry-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/bluebear-io/angry-bear/pr-review/github.svg)](https://agentmods.dev/skills/bluebear-io/angry-bear/pr-review)

Your own site

<a href="https://agentmods.dev/skills/bluebear-io/angry-bear/pr-review"><img src="https://agentmods.dev/badge/skills/bluebear-io/angry-bear/pr-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/bluebear-io/angry-bear/pr-review"><img src="https://agentmods.dev/badge/skills/bluebear-io/angry-bear/pr-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 616 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	$0.00032	$0.00616
Opus 5	$0.00016	$0.00308
Sonnet 5	$0.00006	$0.00123
Haiku 4.5	$0.00003	$0.00062

Measured 10d ago against content hash a856ce7ff449, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

pr-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 10d 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/pr-review/SKILL.md · 60 lines

How it starts

The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PR Review — angry-bear Guidelines

Architecture Rules (NON-NEGOTIABLE)

1. All agent-specific logic lives in adapters

internal/adapter/ is the ONLY place for agent-specific code
if agent == "claude" or if agent == "cursor" outside adapter/ = REJECT
The engine, TUI, CLI commands, and state manager are agent-agnostic

2. HookAdapter interface is the extension point

Every piece of agent knowledge belongs in the adapter:

ExitCodeForDeny() — not hardcoded in hook.go
GlobalConfigPath() — not hardcoded in resolve.go
InstallHook() / UninstallHook() — adapter manages its own hooks

3. No hardcoded agent names/paths outside adapters

Badge health checks use the adapter registry, not hardcoded lists
Hook installation iterates over registered adapters
Config file detection uses adapter.GlobalConfigPath()

4. All data under ~/.angry-bear/

No project-level .angry-bear/ directories
Config, state, logs all under ~/.angry-bear/repos/{hash}/
ResolveProjectRoot uses .git/ only (not .angry-bear/)

Code Standards

From CLAUDE.md

gofmt + golangci-lint must pass with 0 issues
80% minimum test coverage (CI enforced)
No shorthand if — separate assignment from condition
Octal format: 0o755 not 0755
Never swallow errors — wrap with context or log
Table-driven tests, t.TempDir() for filesystem tests

From CONTRIBUTING.md

All exported types and functions must have doc comments
One function, one responsibility
Adapters contain ALL agent knowledge
Fail-open on config/state errors (never block developers due to angry-bear bugs)
Fail-hard on user mistakes (malformed JSON, bad config versions)

Review Checklist

No agent-specific code outside internal/adapter/
No hardcoded paths to ~/.claude/ or ~/.cursor/ outside adapters
All new exported symbols have doc comments
Tests included for new/changed code
Coverage stays >= 80%
No silent error swallowing (wrap or log)
README/HIGHLEVEL updated if user-facing behavior changed
HookAdapter interface updated if new adapter capability added
ScrollView used for any scrollable list (no ad-hoc scroll logic)
Shared constants in tui/constants.go (not duplicated)

Read the full file on GitHub · 60 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.

10d ago First seen · 60 lines · 32 tokens per session scan A a856ce7ff449

Subscribe to this mod's changes

pr-review is a skill published in the GitHub repository bluebear-io/angry-bear (17 stars, last pushed 4d ago), licensed MIT. It adds 32 tokens to every session and 616 once invoked, about $0.0002 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 2026-08-30.

Code review coding-agent-skills

code-review

Structured code review with SOLID, security, and quality checks.

dineshdb/pie · 16 tokens

code-refactoring

Simplify and refactor code while preserving behavior, improving clarity, and reducing complexity. Use when simplifying complex code, removing duplication, or applying design patterns. Handles Extract Method, DRY principle, SOLID principles, behavior validation, and refactoring patterns.

autohandai/community-skills · 55 tokens

code-review

Conduct thorough, constructive code reviews for quality and security. Use when reviewing pull requests, checking code quality, identifying bugs, or auditing security. Handles best practices, SOLID principles, security vulnerabilities, performance analysis, and testing coverage.

autohandai/community-skills · 49 tokens

pr-review

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

PR Review — angry-bear Guidelines

Architecture Rules (NON-NEGOTIABLE)

1. All agent-specific logic lives in adapters

2. HookAdapter interface is the extension point

3. No hardcoded agent names/paths outside adapters

4. All data under ~/.angry-bear/

Code Standards

From CLAUDE.md

From CONTRIBUTING.md

Review Checklist

What this file has done since we first saw it

Other skills, from other repositories

code-review

code-refactoring

code-review

autoreview

rework-rate

omh-code-review