agentmods.dev

angry-architect

angry-architect is a command for Claude Code from Custos/angry-ralph. It costs 25 tokens per session (543 once invoked), scanned A, original, MIT.

A command that breaks a specification into smaller parts and writes an implementation plan for the first stages of the angry-ralph workflow.

In plain words
What is it for?
Use it with a specification file to decompose the work and create a plan, optionally skipping clarification questions.
Why use it?
It helps turn a large or unclear request into an organized plan before code changes begin. It can also save progress so completed planning work is not repeated.

Command for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable.

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

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

not rated 5 6mo ago A scan 25 tokens original MIT
View the source file Custos/angry-ralph
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.

agentmods
npx agentmods add commands/custos/angry-ralph/angry-architect
Clone the repo
git clone --depth 1 https://github.com/Custos/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-architect

README.md
[![agentmods](https://agentmods.dev/badge/commands/custos/angry-ralph/angry-architect.svg)](https://agentmods.dev/commands/custos/angry-ralph/angry-architect)
Your own site
<a href="https://agentmods.dev/commands/custos/angry-ralph/angry-architect"><img src="https://agentmods.dev/badge/commands/custos/angry-ralph/angry-architect.svg" alt="Measured on agentmods" height="20"></a>
Per session 25 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 543 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00025 $0.00543
Opus 5 $0.00013 $0.00271
Sonnet 5 $0.00005 $0.00109
Haiku 4.5 $0.00003 $0.00054

Measured 5d ago against content hash 4f026a7a1890, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

angry-architect 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 5d 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-architect.md · 65 lines

What it actually says

/angry-architect Command

Run Phases 1-2 only: Decompose the spec and write the implementation plan.

1. Argument Parsing

  • @file.md (required) -- Input specification file.
  • --auto (optional) -- Skip clarifying questions.

If no @file.md is provided:

Usage: /angry-architect @spec.md [--auto]

Validate spec file exists. Resolve absolute path.

2. Environment Validation

bash ${CLAUDE_PLUGIN_ROOT}/scripts/checks/validate-env.sh

Halt on failure. Confirm git repo.

3. Resume Detection

Check .ralph-state/phases/architect.done:

  • If exists → "Phases 1-2 already complete. Plan at .planning/angry-ralph-plan.md." Stop.
  • If .ralph-state/pipeline.json exists with current_phase beyond plan → offer resume.

4. Setup

Run these Bash commands exactly as written. Do NOT create pipeline.json or directories manually — the script handles paths, gitignore, and JSON structure:

bash ${CLAUDE_PLUGIN_ROOT}/scripts/lib/pipeline.sh create . "<SPEC_FILE>" "<MODE>" "<MAX_REVIEW>" "<MAX_SECTION_REVIEW>" "<MAX_TDD>" "<REVIEW_TIER>" "<AVAILABLE_REVIEWERS>"

mkdir -p .planning/reviews .planning/sections

Set <MODE> to auto if --auto passed, otherwise interactive. The script creates .ralph-state/pipeline.json — never create this file directly.

5. Execute Phases 1-2

Follow the angry-ralph skill's Phase 1 (DECOMPOSE) and Phase 2 (PLAN) instructions.

When Phase 2 is complete:

bash ${CLAUDE_PLUGIN_ROOT}/scripts/lib/pipeline.sh write_done . architect
bash ${CLAUDE_PLUGIN_ROOT}/scripts/lib/pipeline.sh write . current_phase review
bash ${CLAUDE_PLUGIN_ROOT}/scripts/lib/pipeline.sh append . completed_phases decompose
bash ${CLAUDE_PLUGIN_ROOT}/scripts/lib/pipeline.sh append . completed_phases plan

Report: "Phases 1-2 complete. Run /angry-review plan to review, or /angry-execute to proceed."

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. 5d ago First seen · 65 lines · 25 tokens per session scan A 4f026a7a1890

Subscribe to this mod's changes

angry-architect is a command published in the GitHub repository Custos/angry-ralph (5 stars, last pushed 6mo ago), licensed MIT. It adds 25 tokens to every session and 543 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.

Planning
Related

Other commands, from other repositories

checklist

Generate a custom checklist for the current feature based on user requirements.

github/spec-kit · 13 tokens

clarify

Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.

github/spec-kit · 27 tokens

specify

Create or update the feature specification from a natural language feature description.

github/spec-kit · 13 tokens

converge

Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.

github/spec-kit · 35 tokens

implement

Execute the implementation plan by processing and executing all tasks defined in tasks.md.

github/spec-kit · 14 tokens

analyze

Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.

github/spec-kit · 26 tokens