A command that runs the complete MAID workflow, from defining a goal to validating the finished code. MAID is a method that uses a written plan, behavior-focused tests, and implementation checks.

Breaking work into a manifest, designing tests, implementing the change, and running validation until the tests pass.

It organizes the planning and testing work so implementation starts with a clear scope and tests that initially fail.

How mamertofabian/maid-runner-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to mamertofabian/maid-runner-mcp. 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/mamertofabian/maid-runner-mcp/main/.claude/commands/maid-run.md

Clone the repo

git clone --depth 1 https://github.com/mamertofabian/maid-runner-mcp

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/commands/mamertofabian/maid-runner-mcp/maid-run/github.svg)](https://agentmods.dev/commands/mamertofabian/maid-runner-mcp/maid-run)

Your own site

<a href="https://agentmods.dev/commands/mamertofabian/maid-runner-mcp/maid-run"><img src="https://agentmods.dev/badge/commands/mamertofabian/maid-runner-mcp/maid-run/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/commands/mamertofabian/maid-runner-mcp/maid-run"><img src="https://agentmods.dev/badge/commands/mamertofabian/maid-runner-mcp/maid-run.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 10 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 527 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	$0.00010	$0.00527
Opus 5	$0.00005	$0.00264
Sonnet 5	$0.00002	$0.00105
Haiku 4.5	$0.00001	$0.00053

Measured 10d ago against content hash ac1fe46afe2b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

maid-run 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/commands/maid-run.md · 65 lines

How it starts

The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Execute full MAID workflow for: $ARGUMENTS

This command orchestrates the complete MAID methodology from goal to validated, passing implementation.

Workflow Phases

Phase 1: Goal & Manifest Creation

Use the maid-manifest-architect subagent to:

Analyze the goal and identify affected files
Find next task number: ls manifests/task-*.manifest.json | tail -1
Create manifest: manifests/task-XXX-description.manifest.json
Validate structure: maid validate manifests/task-XXX.manifest.json --use-manifest-chain

Phase 2: Test Design

Use the maid-test-designer subagent to:

Read manifest expectedArtifacts
Create behavioral tests: tests/test_task_XXX_*.py
Tests must USE artifacts AND ASSERT on behavior
Validate behavioral: maid validate manifests/task-XXX.manifest.json --validation-mode behavioral --use-manifest-chain
Verify Red phase: pytest tests/test_task_XXX_*.py -v (tests should FAIL)

Phase 3: Implementation

Use the maid-developer subagent to:

Confirm Red phase (tests fail)
Implement code to make tests pass
Run tests until Green: pytest tests/test_task_XXX_*.py -v
Validate implementation: maid validate manifests/task-XXX.manifest.json --use-manifest-chain

Phase 3.5: Refactoring (if needed)

Use the maid-refactorer subagent to:

Improve code quality while tests pass
Run tests after each change
Keep public API unchanged

Phase 4: Final Integration

Run complete validation to ensure no regressions:

maid validate    # Validate ALL manifests
maid test        # Run ALL validation commands
make lint        # Check code style
make type-check  # Check type hints
make test        # Run full test suite

Success Criteria

All behavioral tests pass
Implementation validation passes
No regressions in existing tests (maid test passes)
Code quality checks pass

Error Recovery

If validation fails at any phase, use the maid-fixer subagent to:

Identify the specific error
Fix one issue at a time
Re-validate after each fix

Read the full file on GitHub · 65 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 · 65 lines · 10 tokens per session scan A ac1fe46afe2b

Subscribe to this mod's changes

maid-run is a command published in the GitHub repository mamertofabian/maid-runner-mcp (0 stars, last pushed 5mo ago), licensed MIT. It adds 10 tokens to every session and 527 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 Testing

prototype

You are building a proof-of-concept for the current Grainulator sprint. Read CLAUDE.md for sprint context and claims.json for existing research claims.

grainulation/grainulator · 0 tokens

verify

Run repository verification using the verification-loop skill.

cloudnative-co/claude-code-starter-kit · 9 tokens

qa-changes

This skill should be used when the user asks to "QA a pull request", "test PR changes", "verify a PR works", "functionally test changes", or when an automated workflow triggers QA validation of code changes. Provides a structured methodology for setting up the environment, exercising changed behavior, and reporting…

OpenHands/extensions · 63 tokens

maid-runner-mcp: Command for Claude Code