lfe-dep-audit

lfe-dep-audit is a skill for Claude Code, Codex from StChiotis/Library-First-Engineering. It costs 81 tokens per session (1,334 once invoked), scanned A, original, MIT.

A read-only review step for dependency manifest files such as package.json, requirements.txt, or go.mod.

In plain words
What is it for?
Use it when dependency files changed in a code review and you need a written findings file for the larger inspection process.
Why use it?
It flags risky version patterns, large major-version changes, and potentially outdated packages, while leaving the actual audit command for a human to run.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

Good fit Use it when dependency files changed in a code review and you…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/stchiotis/library-first-engineering/lfe-dep-audit
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.

Any agent
npx skills add StChiotis/Library-First-Engineering --skill lfe-dep-audit
Clone the repo
git clone --depth 1 https://github.com/StChiotis/Library-First-Engineering

Made for: Claude Code, Codex.

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-dep-audit

README.md
[![agentmods](https://agentmods.dev/badge/skills/stchiotis/library-first-engineering/lfe-dep-audit.svg)](https://agentmods.dev/skills/stchiotis/library-first-engineering/lfe-dep-audit)
Your own site
<a href="https://agentmods.dev/skills/stchiotis/library-first-engineering/lfe-dep-audit"><img src="https://agentmods.dev/badge/skills/stchiotis/library-first-engineering/lfe-dep-audit.svg" alt="Measured on agentmods" height="20"></a>
Per session 81 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,334 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found 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 5.1 $0.00081 $0.01334
Opus 5 $0.00041 $0.00667
Sonnet 5 $0.00016 $0.00267
Haiku 4.5 $0.00008 $0.00133

Measured 7d ago against content hash cfa62ee0ca00, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

lfe-dep-audit 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 7d 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.

.agents/skills/lfe-dep-audit/SKILL.md · 119 lines

How it starts

The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.

LFE Dependency Audit — Manifest Review + Human-Run Instruction

Position in Pipeline

  • Phase: 3 (Inspector sub-skill)
  • Persona: Inspector (read-only; no src/ writes)
  • Trigger: Invoked by /lfe-inspector Sub-Skill Dispatch when lfe-dep-audit: true in .docs/quality/inspector-config.md
  • Output: .plans/checks/dep_findings.md — aggregated by Inspector into critique.md

Mission

Review any dependency manifest files touched by the current diff for known-risky version patterns, major version jumps, and unmaintained packages. Since actual vulnerability databases require tool execution, this skill emits a structured instruction block asking the Brain to run the appropriate audit command and paste the output — keeping the skill fully tool-agnostic.

Hard Rules

  1. Dispatch Context Required (refuse direct invocation): This skill is dispatched by /lfe-inspector Step 6 — it is not a Brain-typeable skill (per LLM_AGENT_GUIDE.md §8.8 Skill Invocation Authority). If invoked without .plans/builder_done.md for the current slice, halt immediately and reply: "/lfe-dep-audit is 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 Overrides section in active_plan.md)." Direct invocation produces orphaned findings files and breaks the Inspector's aggregation logic.
  2. No Tool Execution: Reason over manifest contents only; emit the audit command for the Brain to run rather than running npm audit/pip audit/cargo audit here.
  3. Manifest-Scoped: Audit only the dependency files that appear in builder_done.md; skip unchanged manifests.
  4. Emit Instruction Block: Always emit a "Brain Action Required" block for each detected manifest type — even if no static concerns are found — because dynamic vulnerability data requires runtime tools.
  5. Severity: High (version pinned to * or latest; known-risky major) / Medium (very old major; no upper bound) / Low (minor version drift).

Read the full file on GitHub · 119 lines

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. 7d ago First seen · 119 lines · 81 tokens per session scan A cfa62ee0ca00

Subscribe to this mod's changes

lfe-dep-audit is a skill published in the GitHub repository StChiotis/Library-First-Engineering (43 stars, last pushed 1mo ago), licensed MIT. It adds 81 tokens to every session and 1,334 once invoked, about $0.0004 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.