lfe-inspector

lfe-inspector is a command for Claude Code from StChiotis/Library-First-Engineering. It costs 35 tokens per session (186 once invoked), scanned A, a copy of lfe-improve-architecture, MIT.

An inspection workflow for LFE-compliant projects that checks an implementation against domain facts, validation baselines, or reported regressions. The supplied description does not detail its individual checks.

In plain words
What is it for?
Verifying implementations and debugging regressions within projects that follow the LFE process.
Why use it?
It provides a defined place to investigate whether code is correct, meets agreed validation standards, or has introduced a bug.

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-inspector
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-inspector

README.md
[![agentmods](https://agentmods.dev/badge/commands/stchiotis/library-first-engineering/lfe-inspector.svg)](https://agentmods.dev/commands/stchiotis/library-first-engineering/lfe-inspector)
Your own site
<a href="https://agentmods.dev/commands/stchiotis/library-first-engineering/lfe-inspector"><img src="https://agentmods.dev/badge/commands/stchiotis/library-first-engineering/lfe-inspector.svg" alt="Measured on agentmods" height="20"></a>
Per session 35 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 186 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 86% 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 $0.00035 $0.00186
Opus 5 $0.00017 $0.00093
Sonnet 5 $0.00007 $0.00037
Haiku 4.5 $0.00003 $0.00019

Measured 4d ago against content hash 8e41e95ab196, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

lfe-inspector 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.

Origin

This is a copy

86% identical to lfe-improve-architecture — 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-inspector.md · 9 lines

What it actually says

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

Read .agents/skills/lfe-inspector/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. 4d ago First seen · 9 lines · 35 tokens per session scan A 8e41e95ab196

Subscribe to this mod's changes

lfe-inspector is a command published in the GitHub repository StChiotis/Library-First-Engineering (43 stars, last pushed 1mo ago), licensed MIT. It adds 35 tokens to every session and 186 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 86% identical to lfe-improve-architecture, differing in 8 lines, and is treated as a copy.