Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/greglas75/zuvonpx agentmods add skills/greglas75/zuvo/mutation-testWrote 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/greglas75/zuvo/mutation-test)<a href="https://agentmods.dev/skills/greglas75/zuvo/mutation-test"><img src="https://agentmods.dev/badge/skills/greglas75/zuvo/mutation-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/greglas75/zuvo/mutation-test"><img src="https://agentmods.dev/badge/skills/greglas75/zuvo/mutation-test.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 13 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 Tool Misuse · line 252 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- medium MCP Rug Pull · line 162 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 360 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 675 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 163 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 361 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 398 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 399 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 676 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 184 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 730 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 1267 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium Agent Snooping · line 224 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00210 | $0.26286 |
| Opus 5.5 | $0.00084 | $0.10514 |
| Sonnet 5.5 | $0.00042 | $0.05257 |
| Haiku 4.5 | $0.00021 | $0.02629 |
Grade A, and why
mutation-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 5d 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 — 1,704 lines — stays where its author put it; the contents beside it link to each section on GitHub.
zuvo:mutation-test -- LLM-Guided Mutation Testing
Intelligent mutation testing that targets meaningful behavioral gaps rather than random code changes. For each production file, the LLM generates mutations in 7 categories (boundary, logic, null, error, state, async, security), runs only the tests that cover that file, and closes the gaps it finds: every survivor is triaged as a real gap or an equivalent mutant, and each real gap gets the missing assertion added and re-probed in the same run.
Scope: Production files that have associated test files. Measures how well existing tests detect real behavioral changes.
When to use: After writing tests, before releases, when mutation score is unknown, when test suite feels shallow despite high line coverage.
Out of scope: Writing a test suite from scratch (use zuvo:write-tests), fixing systematic test
anti-patterns across many files (use zuvo:fix-tests), auditing test quality without execution (use
zuvo:test-audit), code quality review (use zuvo:review). Adding the single missing assertion that
a surviving mutant exposes is IN scope — that is the point of finding it.
Argument Parsing
Parse $ARGUMENTS as: [path | full | continue] [--whole-files] [--max N] [--category CATEGORY] [--runner MODE] [--break N] [--no-install] [--dry-run] [--quick] [--report-only]
| Flag | Env equivalent | Effect |
|---|---|---|
[path] |
— | Scope to a specific directory or file — still narrowed to its CHANGED lines |
--whole-files |
— | Mutate the scoped files whole, changed lines or not. Only on the user's explicit request — never set by the agent or by a calling skill to "add context" or "include dependencies" |
continue |
— | Resume an interrupted run from its checkpoint (Phase 3.0). Re-runs nothing already resolved. |
full |
— | All production files that have test coverage |
--max N |
— | Max total LLM mutations to execute (default: 50). Does not bound the native runner, which mutates exhaustively by design. |
--category CATEGORY |
— | Only generate LLM mutations of this category: BOUNDARY, LOGIC, NULL, ERROR, STATE, ASYNC, SECURITY |
--runner MODE |
ZUVO_MUTATION_RUNNER |
auto (default) / native / llm / hybrid — see 0.1d |
--break N |
ZUVO_MUTATION_BREAK |
Fail the run when the final score_triaged is below N% (4.2c — evaluated after the 4.2b fix loop, not at 4.1). The flag overrides the env value; both are recorded with their source. |
--no-install |
ZUVO_MUTATION_NO_INSTALL=1 or ZUVO_NO_INSTALL=1 |
Never offer to install a mutation runner (disables the 0.1c consent gate). Detection still runs. |
--dry-run |
— | Generate mutations and show the plan, but do not execute any. Also suppresses 0.1c entirely. |
--quick |
— | Max 3 LLM mutations per file, max 20 total |
--report-only |
— | Report the score; do NOT fix surviving gaps (skips 4.2b). The only way to skip the fix loop. |
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.
- 5d ago Changed · +16 lines de8676b53574
- 6d ago Changed · +68 lines d104b761afef
- 7d ago Changed · +50 lines f94d27eda2b2
- 14d ago Changed · +49 lines · +20 tokens per session 1424ca825c4a
- 23d ago Changed · +25 lines 3603e529e09c
- 25d ago Changed · +3 lines ff6adf1cf00d
- 1mo ago Changed · +52 lines 78215ff50578
- 1mo ago Changed a85214f986b8
- 1mo ago Changed · +71 lines 82ba5d7b5d86
- 1mo ago First seen · 1,370 lines · 190 tokens per session scan A 27b47cdc8577
mutation-test is a skill published in the GitHub repository greglas75/zuvo (8 stars, last pushed today), licensed MIT. It adds 210 tokens to every session and 26,286 once invoked, about $0.0008 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
ai-agent-bench
Compare Claude Code and Codex on the same code task, with isolated worktrees, common checks, time, and cost.
create-test
Define or implement regression proof: test strategy, black-box or integration tests, KPIs, thresholds, audits, or missing tests.
wrap-up-branch
Finish a feature branch: add missing tests, review and fix the code, align docs, then merge only after explicit confirmation.
eval-regression
Check skill routing or behavior, investigate a regression, or compare plugin changes with a base commit.
brooks-sweep
Full-sweep mode: runs a unified analysis across all quality dimensions — code decay, architecture, tech debt, and test quality — then applies fixes directly to the codebase. Safe changes are auto-applied; risky changes are confirmed before execution. Drawing on twelve classic engineering books. Triggers when: user…
brooks-test
Test quality review drawing on twelve classic engineering books — with primary focus on xUnit Test Patterns, The Art of Unit Testing, How Google Tests Software, and Working Effectively with Legacy Code — that diagnoses structural problems in an existing test suite: brittleness, mock abuse, coverage illusions, slow…