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.
git clone --depth 1 https://github.com/multiplex-ai/muggle-ai-teamsWrote 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.
[](https://agentmods.dev/commands/multiplex-ai/muggle-ai-teams/muggle-do)<a href="https://agentmods.dev/commands/multiplex-ai/muggle-ai-teams/muggle-do"><img src="https://agentmods.dev/badge/commands/multiplex-ai/muggle-ai-teams/muggle-do/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.
<a href="https://agentmods.dev/commands/multiplex-ai/muggle-ai-teams/muggle-do"><img src="https://agentmods.dev/badge/commands/multiplex-ai/muggle-ai-teams/muggle-do.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00050 | $0.04981 |
| Opus 5.5 | $0.00020 | $0.01992 |
| Sonnet 5.5 | $0.00010 | $0.00996 |
| Haiku 4.5 | $0.00005 | $0.00498 |
Grade A, and why
muggle-do 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.
How it starts
The opening of the file, as written. The whole thing — 590 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Muggle Do — Autonomous Development Pipeline
Muggle Do is a session-based, iterative development pipeline. Given a task description, it autonomously:
- Extracts requirements and acceptance criteria
- Analyzes impact across configured repositories
- Validates git state (branches, commits, working tree)
- Writes or fixes implementation code
- Runs unit tests
- Runs QA test cases via Muggle AI infrastructure
- Triages failures and loops back to fix them
- Opens pull requests when done
Each run is a session with full state persistence in markdown files. Sessions survive crashes, support resume, and provide a complete audit trail.
Input
The user's task description is: $ARGUMENTS
This is a natural-language description of what to build, fix, or change. If $ARGUMENTS is empty, ask the user to describe the task before proceeding.
Repo Configuration
Repos are configured in muggle-repos.json in the working directory:
[
{ "name": "frontend", "path": "/absolute/path/to/frontend", "testCommand": "pnpm test" },
{ "name": "backend", "path": "/absolute/path/to/backend", "testCommand": "pnpm test" }
]
Read this file at startup. If it does not exist, ask the user to provide repo details and create it before proceeding.
Session Management
On invocation, check .muggle-do/sessions/ for existing sessions.
If sessions exist
Read each session's state.md to determine its status. Present the user with options:
Existing sessions:
[1] add-login-page — CODING (iteration 2) ← in progress
[2] fix-payment-timeout — DONE (2 iterations) ← completed
[3] Start new session
Which session? _
- Resume active session — continue from the current stage recorded in
state.md - Review completed session — read and display
result.md - Start new session — proceed with
$ARGUMENTSas the task description
If no sessions exist
Skip the prompt entirely. Go straight to creating a new session with $ARGUMENTS.
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.
- 5d ago First seen · 590 lines · 50 tokens per session scan A eec533dd62ac
muggle-do is a command published in the GitHub repository multiplex-ai/muggle-ai-teams (2 stars, last pushed yesterday), licensed MIT. It adds 50 tokens to every session and 4,981 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-22.
Other commands, from other repositories
verify
Grade work that already exists and decide whether it can merge. Runs the project's current unit, integration, and E2E suites plus security scanning and type checking, scores every dimension 0-10, and returns a merge verdict with a VERIFIED-vs-CLAIMED evidence manifest. Writes no test files and edits no source. Use…
kill-mutants
Analyze surviving mutants from a mutation testing run and write targeted unit tests to kill them. Re-runs mutations to confirm kills.
uw-cmd-test
Write comprehensive tests for a feature and verify they all pass.
generate-tests
Comprehensive test suite generation with unit, integration, and end-to-end tests. Analyzes existing code patterns and generates thorough test coverage following testing best practices and project conventions.
checklist
Generate a custom checklist for the current feature based on user requirements.
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.