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 gul-labs/craftsman-marketplace --skill craft-auditgit clone --depth 1 https://github.com/gul-labs/craftsman-marketplaceWrote 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/gul-labs/craftsman-marketplace/craft-audit)<a href="https://agentmods.dev/skills/gul-labs/craftsman-marketplace/craft-audit"><img src="https://agentmods.dev/badge/skills/gul-labs/craftsman-marketplace/craft-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/gul-labs/craftsman-marketplace/craft-audit"><img src="https://agentmods.dev/badge/skills/gul-labs/craftsman-marketplace/craft-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 | $0.00197 | $0.04874 |
| Opus 5 | $0.00098 | $0.02437 |
| Sonnet 5 | $0.00039 | $0.00975 |
| Haiku 4.5 | $0.00020 | $0.00487 |
Grade A, and why
craft-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 5d 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 — 268 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Craftsman Audit — the production-readiness orchestrator
This is the conductor, not another peer domain. The ten craft-* skills each own one surface
(ux, frontend, backend, db, security, infra, observability, testing, lint, ai). This skill stands above them: it looks
at the whole project, decides which of those surfaces apply, plans an audit for each, routes the
actual findings to the domain skills, and keeps a durable record of what's been audited and what's
left — so a large assessment can run across multiple sessions without losing the thread.
It does not duplicate domain knowledge. To judge the auth layer it loads craft-security; the
design system, craft-ux; static quality gates, craft-lint; LLM integrations, craft-ai. The
orchestrator owns discovery, applicability, planning, prioritization, and tracking — the domain
skills own the findings. Keeping that boundary is what stops the two from drifting out of sync. Once
findings are tracked, the companion action skill craft-fix works through the climb sequence — this
skill audits and tracks, it does not itself change code.
Who this is for (read this first — it sets the register)
The primary user is the builder of a cool-but-fragile MVP: someone who used Claude, Lovable, Replit, or v0 to ship something that looks impressive and works in the demo, but is nowhere near production-grade — no real error/empty/loading states, no auth worth the name, no observability, AI "slop" patterns, data that'll corrupt under concurrency, infra that falls over at the first spike. The secondary user is more advanced but still can't reliably hit enterprise-grade.
That persona changes how you communicate, and it is not optional polish — it's the job. It is why the first three "Standing principles" below are non-negotiable rather than style advice:
- Plain language because the reference docs are written for you, the agent, while the findings are written for someone who won't recognize "CLS regression" or "IDOR" — lead with "anyone can open another customer's invoice by changing the number in the URL," then name it.
- Ruthless prioritization because handing this user 200 findings makes them freeze. Your value is making the climb ordered and unscary, not dumping the whole mountain.
- Meeting the project where it is because a "rewrite to my favorites" audit is worthless to someone whose stack already works.
What ships with it
11 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.
- references/claim-verification.md 20 KB
- references/delegation.md 3.3 KB
- references/discovery.md 22 KB
- references/prioritization.md 14 KB
- references/quality.md 5.3 KB
- references/recommended-stack.md 6.5 KB
- references/rerun.md 24 KB
- references/synthesis.md 4.8 KB
- references/workspace.md 44 KB
- scripts/validate-findings.mjs 20 KB runs code
- scripts/validate-synthesis.mjs 3.8 KB runs code
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.
- 5d ago Changed · +1 lines 6c408030d2a7
- 12d ago First seen · 267 lines · 197 tokens per session scan A b09dd469c4e9
craft-audit is a skill published in the GitHub repository gul-labs/craftsman-marketplace (1 stars, last pushed today), licensed MIT. It adds 197 tokens to every session and 4,874 once invoked, about $0.0010 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.
Other skills, from other repositories
plumb-line-audit
Use when auditing a diff or repository against the plumb-line principles — finds laundered uncertainty, boundary leaks, hardcoded priors, overstated maturity, outputs lacking recorded lineage, and baseline drift with no explanation. Read-only: it reports, never auto-fixes.
explain-back
Use before trusting, merging, or building on top of code you (or an agent) just wrote or are about to change. The agent explains the code back in plain language — what it does, why it exists, what breaks if it's wrong — and refuses to proceed until the mental model is confirmed. Use when a diff looks fine but nobody…
prove-every-number
Use whenever code contains a numeric constant, threshold, default, rate, capacity, tolerance, or coefficient — especially one the agent just introduced. Enforces the rule: every number is either derived (from real data or first principles, traceably) or cited (to a spec, datasheet, standard, or documented decision) …
boyscout
Use when touching an existing file to make a change, so you leave it slightly cleaner than you found it without derailing into a giant refactor. Identifies small, safe, in-scope improvements adjacent to the change you're already making — a better name, a deleted dead line, an extracted helper, a clarified condition …
why-comments
Use when a file is littered with comments that narrate what the code already says (// increment the counter), when load-bearing code has no explanation of why it exists, or when reviewing AI-generated code (agents pad output with narration and never record the why). Deletes comments that restate the code, keeps and…
everywhere-else
Use immediately after fixing a bug or improving a pattern in one place — before reporting done. Asks the question agents never ask themselves: 'did you do that anywhere else?' Enumerates the full population of sibling sites (other templates, scenarios, endpoints, components, fixtures, configs that share the same…