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 ALTEN-group/coding-pal --skill mutation-bargit clone --depth 1 https://github.com/ALTEN-group/coding-palWrote 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/alten-group/coding-pal/mutation-bar)<a href="https://agentmods.dev/skills/alten-group/coding-pal/mutation-bar"><img src="https://agentmods.dev/badge/skills/alten-group/coding-pal/mutation-bar/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/alten-group/coding-pal/mutation-bar"><img src="https://agentmods.dev/badge/skills/alten-group/coding-pal/mutation-bar.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 | $0.00087 | $0.00680 |
| Opus 5.5 | $0.00035 | $0.00272 |
| Sonnet 5.5 | $0.00017 | $0.00136 |
| Haiku 4.5 | $0.00009 | $0.00068 |
Grade A, and why
mutation-bar 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 4d 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 — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mutation Bar
Deterministic Mutation Testing Bar gate. It proves the tests themselves: mutants injected into the code must be caught by the test suite. It reads a mutation report and never runs a mutation tool.
When to Use This Skill
- The agent has written or changed tests and must know whether they actually catch defects.
- CI (Prove) must block a pull request whose mutation score is below the bar, and hand the survivors to auto-remediation.
- A reviewer wants the surviving mutants listed as
file:line mutator.
Path resolution
Resolve references/ and scripts/ relative to this skill's install directory (the folder that contains this SKILL.md), not the consumer repository root or the current shell cwd. If the skill was installed under .agents/skills/mutation-bar/ or .claude/skills/mutation-bar/, use that base path. Run the script from the repository root, where mutation-bar.json lives, and write <skill-dir> as that install path.
Workflow
- Read
references/mutation-bar-contract.mdnow. It is the authoritative source for statuses, the score formula, thresholds, and exit codes. - Run the project's mutation tool so that it writes a Stryker JSON report (for example
reports/mutation/mutation.json). A generic summary{ "killed", "survived", "timeout", "noCoverage" }is accepted for tools such as Mutmut. - Run the gate from the repository root:
# Whole report, using mutation-bar.json when present
node <skill-dir>/scripts/mutation-bar.mjs --report reports/mutation/mutation.json
# Only the files this change touched, with a per-file floor
git diff --name-only origin/main... > changed.txt
node <skill-dir>/scripts/mutation-bar.mjs --report reports/mutation/mutation.json --changed changed.txt --per-file-min 60
- Treat a nonzero exit as a failed gate. Add or strengthen tests to kill each listed survivor. Never lower the bar, exclude mutants, or shrink the mutated scope. The command line can only raise the minimum above
mutation-bar.json(default 80). - Read the
Ignored: N mutantsline and anyWarning: no mutants for <file>: not provenline. A growing ignored count means a survivor may be hidden by aStryker disablecomment; a warned file is not proven by this gate. Neither changes the exit code.
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 4d ago First seen · 44 lines · 87 tokens per session scan A 5e80510c433e
mutation-bar is a skill published in the GitHub repository ALTEN-group/coding-pal (5 stars, last pushed 5d ago), licensed MIT. It adds 87 tokens to every session and 680 once invoked, about $0.0003 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 2026-10-14.
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.
eval-dataset-design
A guide to creating reliable test sets for AI agents. Each evaluation task includes the request, the simulated user's behaviour, a reset starting state, and a success check that can be independently verified.
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".
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
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.