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 agentmods add skills/claritune/mutantx/mutatenpx skills add Claritune/mutantx --skill mutategit clone --depth 1 https://github.com/Claritune/mutantxWhat 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 | $0.00032 | $0.01101 |
| Opus 5 | $0.00016 | $0.00550 |
| Sonnet 5 | $0.00006 | $0.00220 |
| Haiku 4.5 | $0.00003 | $0.00110 |
Grade A, and why
mutate 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 3d 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 — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MutantX — AI-Powered Mutation Testing
You are a mutation testing engine. Your job is to evaluate the quality of a project's test suite by injecting realistic bugs (mutants) into source code and checking whether the tests catch them.
Key principle: You are NOT an AST-based tool applying blind syntactic transformations. You understand the code semantically. Generate mutations that represent realistic bugs a developer might actually introduce — off-by-one errors, wrong operator choices, forgotten edge cases, swapped arguments, missing null checks. Avoid trivial or equivalent mutations.
Execute all four phases in sequence. Do not stop between phases unless an error requires user intervention.
Phase 1: Project Detection
Follow the instructions in /mx-detect.
If arguments files or test-cmd are provided, pass them through. Otherwise, auto-detect the project configuration.
Write the detection results to .mutants/detect.json and display them to the user.
Phase 2: Mutant Generation
Follow the instructions in /mx-generate.
Pass count and regen arguments through if provided.
Use per-file caching: only regenerate mutants for files whose content hash has changed since the last run. Report cache status to the user.
Generate up to count (default 5) mutants per source file as unified diff patches in .mutants/patches/. Write metadata to .mutants/manifest.json.
Phase 2.5: Validation (Deterministic + Optional AI)
The test script automatically validates mutants before testing, but if it reports needs-review mutants (source file changed, patch still applies), handle them:
- Run
mx-validate.py(already done automatically by mx-test.py) — classifies mutants as valid, stale, or needs-review. - If needs-review mutants exist, follow the instructions in
/mx-validateto review them. This is the only step that uses AI tokens in the validation flow. - Alternative: run
mx-validate.py --promoteto trust the patches and skip AI review.
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.
- 3d ago First seen · 120 lines · 32 tokens per session scan A e684e8a7a4fe
mutate is a skill published in the GitHub repository Claritune/mutantx (2 stars, last pushed 1mo ago), licensed MIT. It adds 32 tokens to every session and 1,101 once invoked, about $0.0002 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.
Other skills, from other repositories
commit
Atomic git commit with conventional message. Use when the user says "commit", "save my changes", "commit this", or wants to create a git commit. Stages specific files, writes a conventional commit message with body explaining non-obvious decisions. Never uses git add -A.
systematic-debugging
4-phase root cause debugging: understand bugs before fixing.
python-run
Run and debug Python scripts in the project. Use when the user says "run python", "execute this script", "debug this py file", or wants to run/modify a .py file. Handles dependency checks, linting, execution, and error analysis.
github-code-review
Review PRs: diffs, inline comments via gh or REST.
plan
Plan mode: write markdown plan, no execution.
simplify-code
Sequential 3-lens cleanup of recent code changes.