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 stefan-stepzero/shipkit --skill shipkit-codebase-auditgit clone --depth 1 https://github.com/stefan-stepzero/shipkitWrote 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/stefan-stepzero/shipkit/shipkit-codebase-audit)<a href="https://agentmods.dev/skills/stefan-stepzero/shipkit/shipkit-codebase-audit"><img src="https://agentmods.dev/badge/skills/stefan-stepzero/shipkit/shipkit-codebase-audit/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/stefan-stepzero/shipkit/shipkit-codebase-audit"><img src="https://agentmods.dev/badge/skills/stefan-stepzero/shipkit/shipkit-codebase-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00065 | $0.03791 |
| Opus 5.5 | $0.00026 | $0.01516 |
| Sonnet 5.5 | $0.00013 | $0.00758 |
| Haiku 4.5 | $0.00006 | $0.00379 |
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 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 — 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-wiringand/shipkit-wiring-graphvalidate 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.
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.
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 · 267 lines · 65 tokens per session scan A f26cae70dcdd
shipkit-codebase-audit is a skill published in the GitHub repository stefan-stepzero/shipkit (1 stars, last pushed 3mo ago), licensed MIT. It adds 65 tokens to every session and 3,791 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
pero-ponte-sueter
Use when writing code that touches input, I/O, network, parsing, persistence, concurrency, or lifecycle boundaries, to handle the null, empty, malformed, timed-out, partial, and failed paths before the happy path is called finished. NOT for hostile input, injection, or secrets; use ya-te-lavaste-las-manos.
recoge-tu-tiradero
Use after debugging or experimentation, before final evidence or handoff, to remove residue you created that the solution does not need — trace logs, scratch files, .only, temporary flags, abandoned deps. NOT for the handoff gate itself; use vienen-las-visitas. NOT for unreproducible state; use por-si-se-ocupa.
el-vaporub
Use at the very start of a failure investigation, before forming any theory, to rule out your own stale state — unsaved file, unrestarted process, stale cache, wrong branch or worktree, wrong file, outdated build output. Run the ladder once. NOT for an unavailable or misconfigured environment; use ya-comiste.
pero-no-haces-caso
Use after a bug, failure, regression, or rework, to check whether you yourself flagged this exact problem earlier in this session and it was not acted on. Quote your earlier words verbatim or say nothing at all. NOT for late-arriving new scope; use no-se-te-olvide-que.
ya-comiste
Use when a failure may come from an unavailable or misconfigured environment — service down, dependency or version missing, unset or expired credential, exhausted port, disk, or memory, unreachable host — before you debug application code. NOT for stale state you created this session; use el-vaporub.
y-si-lo-encuentro-que
Use before reporting that a repository file, path, symbol, function, route, config key, or dependency is absent or cannot be found. NOT for unverified claims about an external library, API, or platform; use cadena-de-whatsapp.