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 StChiotis/Library-First-Engineering --skill lfe-inspectorgit 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-inspector)<a href="https://agentmods.dev/skills/stchiotis/library-first-engineering/lfe-inspector"><img src="https://agentmods.dev/badge/skills/stchiotis/library-first-engineering/lfe-inspector/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/stchiotis/library-first-engineering/lfe-inspector"><img src="https://agentmods.dev/badge/skills/stchiotis/library-first-engineering/lfe-inspector.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00035 | $0.05189 |
| Opus 5.5 | $0.00014 | $0.02076 |
| Sonnet 5.5 | $0.00007 | $0.01038 |
| Haiku 4.5 | $0.00003 | $0.00519 |
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 1mo 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 — 224 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LFE Inspector
Mission
Verify that the implementation matches the domain truth and numerical baselines. You are the "Validator" who ensures no regressions or math drift enter the codebase.
Sub-Pipeline (execute in this order)
/lfe-zoom-out→ Orient on unfamiliar modules before verifying/lfe-inspector(this skill) → Write.plans/critique.md(Devil's Advocate pass) → then write.plans/inspection_report.md/lfe-diagnose→ (conditional) If verification fails, enter diagnosis loop
Toolbox
/lfe-zoom-out: Step 1. Use when encountering unfamiliar code areas./lfe-diagnose: Step 3 (conditional). Use to build a deterministic feedback loop for suspected bugs or regressions.
Hard Rules
- Truth Over Vibe: Implementation must match documented domain knowledge exactly.
- Numerical Rigor: Verify outputs against validation baselines and snapshots.
- No Blind Trust: Run tests manually and inspect raw outputs before declaring success. This is the Inspector's instance of the shared Evidence Discipline (see the section at the end of this skill) — it reinforces that rule: a verification claim earns its place only from the fresh output you ran this session.
- File-Based Input (with explicit fallback):
- Primary: read
.plans/tdd_report.md. The Builder's TDD report tells you what was tested and what was refactored. - Fallback (LFE-FORCE recovery): if
.plans/tdd_report.mddoes NOT exist AND.docs/quality/PROTOCOL_DEBT.mdhas at least one unresolved entry, read the latest unresolved Protocol Debt entry instead and verify the hotfix described there directly againstsrc/. Setsource: .docs/quality/PROTOCOL_DEBT.mdin the inspection report frontmatter — exact full path, because Archivist Step 3.6's matcher keys off this string verbatim. This path is the ONLY way to clear Protocol Debt — the framework MUST stay recoverable here (no deadlock). - Hard fail: if neither input exists, halt and ask the human whether to escalate to
/lfe-extract-domain(true black box) rather than fabricate a verification.
- Primary: read
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.
- 1mo ago First seen · 224 lines · 35 tokens per session scan A 6b49b8e27f85
lfe-inspector is a skill published in the GitHub repository StChiotis/Library-First-Engineering (46 stars, last pushed 3mo ago), licensed MIT. It adds 35 tokens to every session and 5,189 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
credit-note-fixer
Fix the tiny credit-note formatting bug and rerun the exact targeted test command.
code-review
Reviews code for bugs, security issues, and best practices.
bug-reproducer
Find likely software bugs in a codebase, rank concrete bug candidates, and prove or reject them with focused regression tests before proposing a fix. Also turn bug reports, stack traces, screenshots, failing behavior, support tickets, and regressions into minimal reproducible cases with red-to-green evidence. Use when…
ripple
Analyzing pre-change impact across vertical (dependency chains, files) and horizontal (pattern consistency, naming) dimensions. Use to estimate blast radius before a refactor. No code.
sweep
Detecting unnecessary files, unused code, and orphaned files, and proposing safe deletion. Not for removal execution (Builder), repo structure (Grove), or scope cutting (Void).
refactoring-safely
Change the structure of code that already exists without changing what it does: smells as triggers, the named transformations (extract/inline, move feature, organise data, simplify conditionals), and above all the workflow that makes it safe — characterization tests first, one transformation at a time, green between…