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.
npx skills add wdm0006/mutmut-mcp --skill local-devgit clone --depth 1 https://github.com/wdm0006/mutmut-mcpWrote 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/skills/wdm0006/mutmut-mcp/local-dev)<a href="https://agentmods.dev/skills/wdm0006/mutmut-mcp/local-dev"><img src="https://agentmods.dev/badge/skills/wdm0006/mutmut-mcp/local-dev/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/skills/wdm0006/mutmut-mcp/local-dev"><img src="https://agentmods.dev/badge/skills/wdm0006/mutmut-mcp/local-dev.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 | $0.00030 | $0.01013 |
| Opus 5 | $0.00015 | $0.00507 |
| Sonnet 5 | $0.00006 | $0.00203 |
| Haiku 4.5 | $0.00003 | $0.00101 |
Grade C, and why
local-dev scanned grade C with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
- uv 0.12.10 at `~/.local/bin/uv` (bootstrap: `curl -LsSf https://astral.sh/uv/install.sh | sh`). Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- uv 0.12.10 at `~/.local/bin/uv` (bootstrap: `curl -LsSf https://astral.sh/uv/install.sh | sh`). How it starts
The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Local dev — mutmut-mcp
Durable record of the onboarding run (2026-09-06). Everything below was executed and verified in the sandbox; re-run it the same way.
Environment
- Python >= 3.10 required; the sandbox venv uses 3.13.14 and deps + all tests pass on it.
- uv 0.12.10 at
~/.local/bin/uv(bootstrap:curl -LsSf https://astral.sh/uv/install.sh | sh). - No external services, no env vars, no ports — stdio MCP server.
Bring-up
export PATH="$HOME/.local/bin:$PATH"
make install # uv venv .venv --seed && uv pip install -e ".[dev]" — ONCE
Quirk: every make target depends on install, and uv venv errors when .venv
already exists. After the first install, run the tools directly:
uv run ruff check .
uv run ruff format --check .
uv run pytest tests/ -v
or UV_VENV_CLEAR=1 make test to rebuild the venv every time.
Start the server
uv run mutmut_mcp.py # stdio JSON-RPC; equivalent: .venv/bin/mutmut-mcp
No HTTP port — clients speak MCP over stdin/stdout. Smithery and the Dockerfile use
python mutmut_mcp.py the same way.
Primary-flow verification (MCP session)
Fixture pattern (mirrors tests/test_integration.py): foo.py with 3 functions,
test_foo.py testing two of them, setup.cfg containing [mutmut] +
source_paths=foo.py. Then drive the spawned server with fastmcp's client:
import os
from fastmcp import Client
from fastmcp.client.transports import StdioTransport
transport = StdioTransport(command=".venv/bin/python", args=["mutmut_mcp.py"], cwd=".")
async with Client(transport) as client:
tools = await client.list_tools() # expect the 7 tools
await client.call_tool(
"run_mutmut",
{
"options": "--max-children 1", # no target = full run
"project_path": "<fixture dir>",
"venv_path": ".venv", # repo venv holds mutmut + pytest
},
)
print(await client.call_tool("show_results", {"project_path": "<fixture dir>", "venv_path": ".venv"}))
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 · 94 lines · 30 tokens per session scan C 2be3ddddab5f
local-dev is a skill published in the GitHub repository wdm0006/mutmut-mcp (0 stars, last pushed 2d ago), licensed MIT. It adds 30 tokens to every session and 1,013 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-08.
Other skills, from other repositories
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
neuron-evaluation-engineer
Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.