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 ThibautBaissac/rails_ai_agents --skill mutation-testinggit clone --depth 1 https://github.com/ThibautBaissac/rails_ai_agentsWrote 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/thibautbaissac/rails_ai_agents/mutation-testing)<a href="https://agentmods.dev/skills/thibautbaissac/rails_ai_agents/mutation-testing"><img src="https://agentmods.dev/badge/skills/thibautbaissac/rails_ai_agents/mutation-testing.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
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 →
- medium Excessive Agency · line 10 Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
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 | $0.00075 | $0.01678 |
| Opus 5 | $0.00037 | $0.00839 |
| Sonnet 5 | $0.00015 | $0.00336 |
| Haiku 4.5 | $0.00007 | $0.00168 |
Grade A, and why
mutation-testing 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 8d 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 — 231 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mutation Testing with Mutant
When to Activate
- The user asks to run mutation testing.
- The user has alive mutations to fix.
- The user asks to verify mutation coverage on a subject.
When Not to Use
- The task does not involve mutation testing.
Inputs
- Alive mutation output to act on (paste the
evil:block). - Optional: subject expression to scope the run.
Outputs (Fixed Order)
- Mutation results (alive count, coverage percentage).
- Clear action for each alive mutation: add test or simplify code.
Reading Mutation Output
An alive mutation looks like:
evil:YourClass#method:YourClass#method:lib/your_class.rb:42:abc12
@@ -1,3 +1,3 @@
def method
- @value >= threshold
+ @value > threshold
end
evilmeans no test killed this mutation.- The diff shows original (
-) and mutated (+) code.
Reporting Format (BLUF)
Lead with the verdict — bottom line up front:
If unkillable:
Unkillable. Both forms are equivalent because [reason]. Add to ignore list.
If killable:
Killable.
Option A — add test:
(test diff)Option B — simplify code:
(source diff)
Always present both options so the user can choose. Include evidence: if you cannot think of a test that would kill the mutation, say so — that is valuable signal toward unkillable.
Usage
1. Run Mutant
bundle exec mutant run --fail-fast
When the subject is known, scope the run to avoid testing unrelated subjects:
bundle exec mutant run --fail-fast 'Entities::CreateService#call'
If the command succeeds, coverage is 100% — done.
If it fails, find the evil: line in the output — it has the subject
name, file path, and line number. The diff block immediately after shows
the original and mutated code.
2. Investigate
Read the source file and existing spec file for the subject. Ask: "Is the mutated code acceptable for all valid inputs?"
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.
- 8d ago First seen · 231 lines · 75 tokens per session scan A 9f1f143cd93a
mutation-testing is a skill published in the GitHub repository ThibautBaissac/rails_ai_agents (659 stars, last pushed 3mo ago), licensed MIT. It adds 75 tokens to every session and 1,678 once invoked, about $0.0004 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
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.