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 Claritune/mutantx --skill mx-testgit clone --depth 1 https://github.com/Claritune/mutantxWrote 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/claritune/mutantx/mx-test)<a href="https://agentmods.dev/skills/claritune/mutantx/mx-test"><img src="https://agentmods.dev/badge/skills/claritune/mutantx/mx-test/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/claritune/mutantx/mx-test"><img src="https://agentmods.dev/badge/skills/claritune/mutantx/mx-test.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 | $0.00026 | $0.00520 |
| Opus 5.5 | $0.00010 | $0.00208 |
| Sonnet 5.5 | $0.00005 | $0.00104 |
| Haiku 4.5 | $0.00003 | $0.00052 |
Grade A, and why
mx-test 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 1mo 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.
What it actually says
MutantX — Phase 3: Mutant Testing
This phase is handled by the deterministic Python script mx-test.py. It applies each mutant patch, runs the test suite, records results, and reverts — all without consuming AI tokens.
How to Run
Locate mx-test.py from the MutantX installation. It is in the scripts/ directory alongside the skills:
python3 ~/.claude/scripts/mx-test.py
Or if MutantX is installed at a known path:
python3 /path/to/mutantx/src/scripts/mx-test.py
Options
| Flag | Description |
|---|---|
--mutants-dir PATH |
Path to the .mutants/ directory (default: .mutants) |
--timeout N |
Test command timeout in seconds (default: 120) |
--skip-baseline |
Skip the baseline test run |
--no-clean-check |
Skip the clean working tree check |
What the Script Does
-
Pre-flight checks:
- Verifies the working tree is clean (no uncommitted changes)
- Runs baseline tests to confirm they pass on unmodified code
-
For each pending mutant:
- Applies the patch:
git apply .mutants/patches/NNN.patch - Runs the test command with a timeout
- Records the result: killed, survived, timeout, or skipped
- Reverts the patch:
git apply -R .mutants/patches/NNN.patch - Saves progress to
manifest.jsonafter each mutant
- Applies the patch:
-
Supports resuming — only tests mutants with
status: "pending"
When Invoked as a Skill
If the user runs /mx-test, execute the script using the Bash tool:
python3 <path-to-mx-test.py> --mutants-dir .mutants
Find mx-test.py by checking these locations in order:
./src/scripts/mx-test.py(if inside the MutantX repo)~/.claude/scripts/mx-test.py(global install)
Display the script output to the user as it runs.
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.
- 1mo ago First seen · 63 lines · 26 tokens per session scan A 510331649f7e
mx-test is a skill published in the GitHub repository Claritune/mutantx (2 stars, last pushed 2mo ago), licensed MIT. It adds 26 tokens to every session and 520 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
test-driven-development
TDD: enforce RED-GREEN-REFACTOR, tests before code.
starfleetctl-dev
Developing and deploying the starfleetctl source itself — claim protocol, make, bootstrap, daemon restarts in the right order, end-to-end verification. Load before editing anything in a starfleetctl source checkout, before running starfleet-bootstrap, or when a web/plugin change 'is done' but the fleet does not see it.
engineering-workflow
A Chinese-language workflow for reliable software development. It describes exploring the problem, making a plan, using TDD (test-driven development, where tests are written before the code), debugging methodically, reviewing code, and verifying the result.
writing-tests
Kiro Crew repo only: how to write a backend pytest test with NO side effects that does not flake. Use when adding, editing, reviewing or debugging a test there: which conftest applies, what leaks (temp dirs, data home, /.kiro, cron, threads), the seven flake classes, cross-platform traps.
pod-e2e
ONLY for developing Kiro Crew itself -- if the project you are working on is anything else, ignore this skill: it drives Kiro Crew's own pod tooling, which does not exist in another repository. Boots a Kiro Crew feature worktree's full stack as an ISOLATED throwaway pod and proves it boots, authenticates and renders…
dashboard-template
Kiro Crew repo only: load this when a task will author or change a dashboard page. A page never ships alone: the same PR carries its TypedDict contract, its provider, and a parity test that the two agree. Scaffold all four from one field list; read numbers from an existing fold, never type them.