agentmods.dev

angry-review

angry-review is a command for Claude Code from Custos/angry-ralph. It costs 17 tokens per session (545 once invoked), scanned A, original, MIT.

A command for reviewing a plan, the codebase, or one named section with an intentionally skeptical eye. It checks the selected work against its plan or specification.

In plain words
What is it for?
Use it to review an implementation plan, check code against that plan, or inspect a specific section against its requirements.
Why use it?
It helps find missing steps, flaws, and differences between what was planned and what was built before the work is considered complete.

Command for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: mentions subagents.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the angry-ralph plugin — 1 skill, 8 commands, 1 agent, 2 hooks shipped together

not rated 5repo 6mo ago A scan 17 tokens original MIT

Good fit Use it to review an implementation plan, check code against that plan, or inspect a specific section against its requirements.

Compare 6 commands from other repositories ↓
View source ↗ Custos/angry-ralph
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add Custos/angry-ralph
Claude Code
/plugin install angry-ralph

Made for: Claude Code.

Or install angry-ralph, the plugin that ships this one along with the rest of its 1 skill, 8 commands, 1 agent, 2 hooks.

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 angry-review

README.md
[![agentmods](https://agentmods.dev/badge/commands/custos/angry-ralph/angry-review.svg)](https://agentmods.dev/commands/custos/angry-ralph/angry-review)
Your own site
<a href="https://agentmods.dev/commands/custos/angry-ralph/angry-review"><img src="https://agentmods.dev/badge/commands/custos/angry-ralph/angry-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 545 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 $0.00017 $0.00545
Opus 5 $0.00009 $0.00272
Sonnet 5 $0.00003 $0.00109
Haiku 4.5 $0.00002 $0.00055

Measured 8d ago against content hash de8f2cc621fa, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

angry-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 8d 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.

commands/angry-review.md · 58 lines

How it starts

The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/angry-review Command

Unified review command. Pipeline Phase 3 when run in context, or on-demand anytime.

1. Argument Parsing

Parse the first argument as the review target:

  • plan (default) -- Review the implementation plan.
  • code -- Review the codebase against the plan.
  • section <name> -- Review a specific section against its spec.

If no target, default to plan.

2. Detect Context: Pipeline vs On-Demand

Pipeline (Phase 3): .ralph-state/pipeline.json exists AND current_phase is "review" AND target is plan.

Read pipeline state:

bash ${CLAUDE_PLUGIN_ROOT}/scripts/lib/pipeline.sh read . current_phase
bash ${CLAUDE_PLUGIN_ROOT}/scripts/lib/pipeline.sh read . review_tier
bash ${CLAUDE_PLUGIN_ROOT}/scripts/lib/pipeline.sh read . available_reviewers
bash ${CLAUDE_PLUGIN_ROOT}/scripts/lib/pipeline.sh read . max_review_iterations

On-demand: Everything else.

Pipeline Mode (Phase 3)

  1. Follow the angry-ralph skill's Phase 3 (ADVERSARIAL REVIEW) procedure.
  2. On completion:
bash ${CLAUDE_PLUGIN_ROOT}/scripts/lib/pipeline.sh write_done . review
bash ${CLAUDE_PLUGIN_ROOT}/scripts/lib/pipeline.sh write . current_phase split
bash ${CLAUDE_PLUGIN_ROOT}/scripts/lib/pipeline.sh append . completed_phases review

On-Demand Mode

  1. If .ralph-state/pipeline.json exists, read review_tier and available_reviewers. Otherwise run validate-env.sh.
  2. Create output directory: .planning/reviews/on-demand/<target>-<timestamp>/

For plan: Validate .planning/angry-ralph-plan.md exists. Spawn external-reviewer subagent with the plan file.

For code: Validate .planning/angry-ralph-plan.md exists. Spawn external-reviewer subagent for code review against plan.

For section <name>: Resolve .planning/sections/section-<name>.md. Spawn external-reviewer subagent with section spec and changed files.

In all on-demand cases: run triage (CRITICAL/WARNING/INFO), present findings. Do NOT write .done markers.

Read the full file on GitHub · 58 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. 8d ago First seen · 58 lines · 17 tokens per session scan A de8f2cc621fa

Subscribe to this mod's changes

angry-review is a command published in the GitHub repository Custos/angry-ralph (5 stars, last pushed 6mo ago), licensed MIT. It adds 17 tokens to every session and 545 once invoked, about $0.0001 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.

Code review
Related

Other commands, from other repositories

sdd-init

Initialize SDD context — detects project stack and bootstraps persistence backend.

Gentleman-Programming/gentle-ai · 14 tokens

review-branch

Review the current branch's diff against base by dispatching atomic-reviewer. No orchestration loop, no spec required — pre-flight before /commit pr or /commit merge.

damusix/atomic-claude · 35 tokens

init

Install the formatters this repository needs, with every command visible before it runs.

azrtydxb/procoder · 16 tokens

merge-conflict-analysis

You are analyzing merge conflicts for PR #${{ pr-number }}.

rjmurillo/ai-agents · 0 tokens

repo-audit

Audit a codebase (local or remote GitHub/GitLab) against architecture principles and requirements, surfacing drift, risk, and missing decisions.

tractorjuice/arc-kit · 29 tokens

argos

A command for checking whether an implementation matches its design deliverables. Its Korean description compares the work to the design as part of a completion inspection.

Dannykkh/skill-olympus · 21 tokens