lfe-mutation-verify

lfe-mutation-verify is a command for Claude Code from StChiotis/Library-First-Engineering. It costs 66 tokens per session (223 once invoked), scanned A, a copy of lfe-boot, MIT.

A testing review that imagines small code changes, called mutations, and checks whether the existing tests would detect them. It does this through reasoning and does not require running the test suite.

In plain words
What is it for?
Checking test strength for critical or safety-sensitive modules as part of the LFE inspector workflow.
Why use it?
It shows whether tests would catch important mistakes, even when mutation-testing software or a test runner is unavailable.

Command for Claude Code

Install

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.

agentmods
npx agentmods add commands/stchiotis/library-first-engineering/lfe-mutation-verify
Clone the repo
git clone --depth 1 https://github.com/StChiotis/Library-First-Engineering

Made for: Claude Code.

Wrote 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.

agentmods badge for lfe-mutation-verify

README.md
[![agentmods](https://agentmods.dev/badge/commands/stchiotis/library-first-engineering/lfe-mutation-verify.svg)](https://agentmods.dev/commands/stchiotis/library-first-engineering/lfe-mutation-verify)
Your own site
<a href="https://agentmods.dev/commands/stchiotis/library-first-engineering/lfe-mutation-verify"><img src="https://agentmods.dev/badge/commands/stchiotis/library-first-engineering/lfe-mutation-verify.svg" alt="Measured on agentmods" height="20"></a>
Per session 66 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 223 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 84% copy Near-identical to another mod in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00066 $0.00223
Opus 5 $0.00033 $0.00112
Sonnet 5 $0.00013 $0.00045
Haiku 4.5 $0.00007 $0.00022

Measured 3d ago against content hash 17f1619aacfd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 3d 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.

Origin

This is a copy

84% identical to lfe-boot — 8 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.claude/commands/lfe-mutation-verify.md · 9 lines

What it actually says

Generated pointer — not the protocol. This command exists so /lfe-mutation-verify dispatches natively in Claude Code. The canonical skill lives at .agents/skills/lfe-mutation-verify/SKILL.md (LFE-SOURCE).

Read .agents/skills/lfe-mutation-verify/SKILL.md now and execute its protocol exactly as written — including its position-in-pipeline preconditions and its coordination-file contract. Honor the Skill Invocation Authority rules (LLM_AGENT_GUIDE §8.8): if this skill is agent-dispatched only and was typed out of sequence, refuse and route through the assembly line. Any change to skill behavior belongs in the canonical file, never in this pointer.

Changes

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.

  1. 3d ago First seen · 9 lines · 66 tokens per session scan A 17f1619aacfd

Subscribe to this mod's changes

lfe-mutation-verify is a command 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 223 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 84% identical to lfe-boot, differing in 8 lines, and is treated as a copy.