shipkit-codebase-audit

A codebase audit that looks for dead code, unused dependencies, unreachable files, broken imports, and disconnected modules.

In plain words
What is it for?
Use it to inspect an application codebase at different levels of depth and receive findings without automatically deleting code.
Why use it?
It reveals stale or unwired parts of an application that ordinary linters may miss.

Skill for Claude CodeCodex

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 skills/stefan-stepzero/shipkit/shipkit-codebase-audit
Any agent
npx skills add stefan-stepzero/shipkit --skill shipkit-codebase-audit
Clone the repo
git clone --depth 1 https://github.com/stefan-stepzero/shipkit

Made for: Claude Code, Codex.

Per session 65 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,791 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00065 $0.03791
Opus 5 $0.00032 $0.01895
Sonnet 5 $0.00013 $0.00758
Haiku 4.5 $0.00006 $0.00379

Measured yesterday against content hash f26cae70dcdd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

shipkit-codebase-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 yesterday.

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.

install/skills/shipkit-codebase-audit/SKILL.md · 267 lines

How it starts

The opening of the file, as written. The whole thing — 267 lines — stays where its author put it; the contents beside it link to each section on GitHub.

shipkit-codebase-audit - Dead Code & Wiring Audit

Purpose: Deliver one outcome — this codebase has nothing stale, orphaned, or unwired. Find unused exports, unreachable files, unused dependencies, broken imports, and the contract drift that linters can't see.

What this is: A standing operating procedure. Its value is remembering that dead-code and wiring checks must happen, running them the same way in any repo (even repos with no tooling installed), and reasoning past what the tooling is blind to. Running a linter is a natural capability — this skill is the discipline around it, not the linter itself.

What this is NOT:

  • Not an auto-fixer — it reports, it does not delete code (deletion is a deliberate call you make).
  • Not a code-quality reviewer — that's /shipkit-review-shipping (12 dimensions on recent changes).
  • Not a production-readiness gate — that's /shipkit-preflight.
  • Not the framework-internal wiring validator — /shipkit-validate-wiring and /shipkit-wiring-graph validate Shipkit's OWN component graph; this audits your application code.

When to Invoke

Invocation Tier What runs
/shipkit-codebase-audit quick (default) Mode A only — ephemeral knip-class run + report. Cheap, CI-suitable.
/shipkit-codebase-audit deep standard Mode A, then a handful of parallel dimension agents reason about blind spots.
/shipkit-codebase-audit exhaustive exhaustive Mode A, then one agent per file (or slice) + contract-ledger reconcile-join. Full coverage. Expensive — opt-in.
/shipkit-codebase-audit src/ quick on a scope Limit the audit to a directory.

Also triggers on: "audit my codebase", "find dead code", "what's unused here", "check for orphaned modules", "is anything unwired", "deep/exhaustive codebase audit".

Workflow position: any time for quick (it's a hygiene sweep); deep/exhaustive before a milestone, a refactor, or a release.

Read the full file on GitHub · 267 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. yesterday First seen · 267 lines · 65 tokens per session scan A f26cae70dcdd

Subscribe to this mod's changes

shipkit-codebase-audit is a skill published in the GitHub repository stefan-stepzero/shipkit (1 stars, last pushed 1mo ago), licensed MIT. It adds 65 tokens to every session and 3,791 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 2026-08-31.