What is angry-execute?

A command that runs the later stages of the angry-ralph workflow: splitting a plan into sections, implementing them with TDD, and performing a final review. TDD means writing tests before the code they check.

Use it after the planning and review stages to split the plan, execute each section with tests, and run the final review.

It organizes implementation into smaller sections and keeps track of completed work. It can also rebuild a selected section and checks that earlier planning stages are finished.

angry-execute — Command by Custos

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-execute

Clone the repo

git clone --depth 1 https://github.com/Custos/angry-ralph

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

Per session 29 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 807 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.

Model	Per session	Once invoked
Fable 5	$0.00029	$0.00807
Opus 5	$0.00015	$0.00404
Sonnet 5	$0.00006	$0.00161
Haiku 4.5	$0.00003	$0.00081

Measured 2d ago against content hash 354fb7ef7a62, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

angry-execute 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 2d 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-execute.md · 106 lines

How it starts

The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/angry-execute Command

Run Phases 4-6: Split the plan into sections, execute each via TDD Ralph Loop, and run final review.

1. Argument Parsing

--auto (optional) -- Skip confirmation prompts.
--rebuild <section> (optional) -- Delete a section's done marker and re-run it.

If --rebuild is passed:

bash ${CLAUDE_PLUGIN_ROOT}/scripts/lib/pipeline.sh remove_done . "<section>"
bash ${CLAUDE_PLUGIN_ROOT}/scripts/lib/pipeline.sh remove_from_list . "completed_sections" "<section>"

Both the .done marker file and the completed_sections array entry are removed, so the section will be re-executed.

2. Prerequisites

Verify .ralph-state/pipeline.json exists:

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

If empty → error: "No pipeline state found. Run /angry-architect or /angry-ralph first."

Verify Phases 1-2 complete:

bash ${CLAUDE_PLUGIN_ROOT}/scripts/lib/pipeline.sh check_done . architect

If exit non-zero → error: "Phases 1-2 not complete. Run /angry-architect @spec.md first."

3. Phase 4: SPLIT

Check if Phase 3 was run:

bash ${CLAUDE_PLUGIN_ROOT}/scripts/lib/pipeline.sh check_done . review

If not done, ask user: "Phase 3 (review) was not run. Proceed without review, or run /angry-review plan first?"

Follow the angry-ralph skill's Phase 4 (SPLIT) instructions.

4. Phase 5: EXECUTE (Ralph Loop + TDD)

For each section in .planning/sections/index.md:

Read completed sections:

bash ${CLAUDE_PLUGIN_ROOT}/scripts/lib/pipeline.sh read . completed_sections

Skip sections already in completed_sections. For incomplete sections, execute via TDD Ralph Loop per the skill instructions. Run mechanical gates before section review:

bash ${CLAUDE_PLUGIN_ROOT}/scripts/lib/mechanical-gates.sh run_all "<test_runner>" "<section_spec>" "."

On section completion, append to completed_sections:

bash ${CLAUDE_PLUGIN_ROOT}/scripts/lib/pipeline.sh append . completed_sections "<section-name>"

Read the full file on GitHub · 106 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.

2d ago First seen · 106 lines · 29 tokens per session scan A 354fb7ef7a62

Subscribe to this mod's changes

angry-execute is a command published in the GitHub repository Custos/angry-ralph (5 stars, last pushed 6mo ago), licensed MIT. It adds 29 tokens to every session and 807 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 TDD Testing

angry-execute

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

/angry-execute Command

1. Argument Parsing

2. Prerequisites

3. Phase 4: SPLIT

4. Phase 5: EXECUTE (Ralph Loop + TDD)

What this file has done since we first saw it

Other commands, from other repositories

tdd-requirements

go-test

pm-auto-design2dev

task-verify

execute-plan

tdd