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/stchiotis/library-first-engineering/lfe-mutation-verifynpx skills add StChiotis/Library-First-Engineering --skill lfe-mutation-verifygit clone --depth 1 https://github.com/StChiotis/Library-First-EngineeringWrote 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/stchiotis/library-first-engineering/lfe-mutation-verify)<a href="https://agentmods.dev/skills/stchiotis/library-first-engineering/lfe-mutation-verify"><img src="https://agentmods.dev/badge/skills/stchiotis/library-first-engineering/lfe-mutation-verify.svg" alt="Measured on agentmods" 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 | $0.00066 | $0.01212 |
| Opus 5 | $0.00033 | $0.00606 |
| Sonnet 5 | $0.00013 | $0.00242 |
| Haiku 4.5 | $0.00007 | $0.00121 |
Grade A, and why
lfe-mutation-verify 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LFE Mutation Verify — Prompt-Based Test Quality Reasoning
Position in Pipeline
- Phase: 3 (Inspector sub-skill)
- Persona: Inspector (read-only; no src/ writes)
- Trigger: Invoked by
/lfe-inspectorSub-Skill Dispatch whenlfe-mutation-verify: truein.docs/quality/inspector-config.md - Output:
.plans/checks/mutation_findings.md— aggregated by Inspector intocritique.md
Mission
Reason about test quality by asking: "If we made this change to the production code, would the existing tests catch it?" This is the logical equivalent of a mutation testing tool, done entirely through LLM reasoning over the diff. It surfaces tests that pass for the wrong reason (coincidental correctness) and logic paths that have no discriminating test.
This skill is expensive in reasoning tokens. Enable selectively — critical business logic, security-sensitive paths, and mission-critical calculations.
Hard Rules
- Dispatch Context Required (refuse direct invocation): This skill is dispatched by
/lfe-inspectorStep 6 — it is not a Brain-typeable skill (perLLM_AGENT_GUIDE.md§8.8 Skill Invocation Authority). If invoked without.plans/builder_done.mdAND.plans/tdd_report.mdfor the current slice, halt immediately and reply: "/lfe-mutation-verifyis an Inspector sub-skill dispatched by/lfe-inspector. It cannot be run standalone. Run/lfe-inspector— the dispatcher will invoke this sub-skill if it is enabled in.docs/quality/inspector-config.md(or via an## Inspector Overridessection inactive_plan.md)." Direct invocation produces orphaned findings files and breaks the Inspector's aggregation logic. - Prompt-Only: No test runner, no mutation framework, no code execution.
- Diff-Scoped: Reason only over implementation + test files in
builder_done.md. - Candidate Mutations: For each production function changed, propose 3–5 plausible mutations; reason whether any test would catch them.
- Severity: Escaped (no test catches the mutation) / Covered (mutation is caught by ≥1 test) / Partial (mutation is caught only by an integration test, not a unit test).
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 First seen · 101 lines · 66 tokens per session scan A e00144b637c7
lfe-mutation-verify is a skill published in the GitHub repository StChiotis/Library-First-Engineering (43 stars, last pushed 1mo ago), licensed MIT. It adds 66 tokens to every session and 1,212 once invoked, about $0.0003 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
playwright
Use when the task requires capturing or automating a real browser from the terminal.
implementation-final-review
Perform the repository's risk-tiered independent final review before implementation completion. Use only when explicitly invoked or when repository instructions require it after behavior-impacting implementation work; audit the complete task diff, supported contracts, lifecycle and security boundaries, complexity, and…
redteam-plugin-development
Standards for creating redteam plugins and graders. Use when creating new plugins, writing graders, or modifying attack templates.
promptfoo-evals
Write, refine, run, and QA promptfoo evaluation suites: promptfooconfig.yaml, prompts, providers, vars, tests, assertions, model-graded rubrics, transforms, datasets, exports, and CI gates. Use for non-redteam eval coverage, regression tests, or new eval matrices. Do not use for adversarial redteam plugin or strategy…
promptfoo-provider-setup
Configure promptfoo providers or redteam targets for hosted models, live HTTP APIs, Python/JavaScript local scripts, agent SDKs, or multi-input systems. Use when connecting promptfoo to the system under test, mapping vars, auth env vars, request bodies, response transforms, or static-code-derived provider wrappers. Do…
code-change-verification
Run the mandatory verification stack when changes affect runtime code, tests, or build/test behavior in the OpenAI Agents Python repository.