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 mattwynne/yaks --skill triaging-mutantsgit clone --depth 1 https://github.com/mattwynne/yaksWrote 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/mattwynne/yaks/triaging-mutants)<a href="https://agentmods.dev/skills/mattwynne/yaks/triaging-mutants"><img src="https://agentmods.dev/badge/skills/mattwynne/yaks/triaging-mutants/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/mattwynne/yaks/triaging-mutants"><img src="https://agentmods.dev/badge/skills/mattwynne/yaks/triaging-mutants.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Rogue Agent · line 289 Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
- high Rogue Agent · line 289 Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
- medium Excessive Agency · line 328 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00034 | $0.02895 |
| Opus 5 | $0.00017 | $0.01448 |
| Sonnet 5 | $0.00007 | $0.00579 |
| Haiku 4.5 | $0.00003 | $0.00290 |
Grade A, and why
triaging-mutants 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.
How it starts
The opening of the file, as written. The whole thing — 331 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Triaging Mutants
Overview
A survived mutant is a question, not just a gap in test
coverage. When cargo mutants reports a miss, the obvious
response is to write a test that kills it. But that's often the
shallow fix. The deeper question is: why did this mutation
produce code that still works?
Three possibilities:
- Missing test — the behaviour is real and untested. Write a test.
- Design weakness — the code tolerates the mutation because the design is too permissive, has redundant paths, or uses a representation that doesn't constrain values tightly enough. Improve the design so the mutation becomes impossible or obviously wrong.
- Equivalent mutant — the mutation produces logically identical behaviour. No action needed; mark it accepted.
Option 2 is the most valuable and most commonly overlooked. Changing the modelling often obviates entire classes of mutants — making the code both more correct and simpler to test.
When to Use
- After a mutation test run produces missed mutants
- When working on a "fix missed mutants" sub-yak
- When reviewing mutation results before deciding what to do
- Periodically, to reassess previously-accepted mutants
Don't use when:
- No mutation results exist yet (run
dev mutatefirst) - The mutant is in generated or trivial code (skip it)
Pacing
Don't ask which mutant to triage next — just pick one and go. After presenting a verdict and acting on it, immediately move to the next untriaged mutant. Keep momentum. The user will interrupt if they want to change direction.
Prefer domain-layer mutants over adapter-layer, and single-mutant files over multi-mutant files (quick wins build momentum).
Inputs
The skill expects one of:
- A specific mutant yak (e.g.
yx show "adapters-event_store-mod mutants") - A file path with mutants from
mutants.out/missed.txt - The full
mutants.out/missed.txtfor a triage session
Phase 1: Gather Context
For each mutant (or group of mutants in the same file):
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 · 331 lines · 34 tokens per session scan A da458ac9dbba
triaging-mutants is a skill published in the GitHub repository mattwynne/yaks (58 stars, last pushed 28d ago), licensed MIT. It adds 34 tokens to every session and 2,895 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 2026-08-30.
Other skills, from other repositories
coding
Use when five specialized coding agents (linter, perf, refactor, security, test) that enforce quality gates across the development lifecycle. From lint enforcement through performance profiling, refactoring, security auditing, and test coverage. Use when working with coding agents.
test-agent
Use when writing comprehensive test suites covering happy paths, error paths, edge cases, and integration points.
test-driven-development
Use when implementing any feature or bugfix, before writing implementation code.
tdd
Test-driven development with red-green-refactor loop. Use when user wants to build features or fix bugs using TDD, mentions "red-green-refactor", wants integration tests, or asks for test-first development.
chaos-fault-injection
Deliberately inject faults — dropped connections, corrupted writes, latency, malformed responses, resource exhaustion — and assert the system's expected recovery (escalation, hardstop, rollback).
metamorphic-testing
Test systems with no reliable oracle using metamorphic relations — equivalence-preserving input transforms whose outputs must agree, with concrete relations for LLM/NLP stability.