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 utk2103/Prompt-Studio --skill lean-auditgit clone --depth 1 https://github.com/utk2103/Prompt-StudioWrote 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/utk2103/prompt-studio/lean-audit)<a href="https://agentmods.dev/skills/utk2103/prompt-studio/lean-audit"><img src="https://agentmods.dev/badge/skills/utk2103/prompt-studio/lean-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/utk2103/prompt-studio/lean-audit"><img src="https://agentmods.dev/badge/skills/utk2103/prompt-studio/lean-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 | $0.00098 | $0.00400 |
| Opus 5.5 | $0.00039 | $0.00160 |
| Sonnet 5.5 | $0.00020 | $0.00080 |
| Haiku 4.5 | $0.00010 | $0.00040 |
Grade A, and why
lean-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.
This is a copy
86% identical to ponytail-audit — 15 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
lean-review, repo-wide. Scan the whole tree instead of a diff. Rank findings biggest cut first.
Tags
Same as lean-review:
delete:dead code, unused flexibility, speculative feature. Replacement: nothing.stdlib:hand-rolled thing the standard library ships. Name the function.native:dependency or code doing what the platform already does. Name the feature.yagni:abstraction with one implementation, config nobody sets, layer with one caller.shrink:same logic, fewer lines. Show the shorter form.
Hunt
Deps the stdlib or platform already ships, single-implementation interfaces, factories with one product, wrappers that only delegate, files exporting one thing, dead flags and config, hand-rolled stdlib.
Output
One line per finding, ranked: <tag> <what to cut>. <replacement>. [path].
End with net: -<N> lines, -<M> deps possible. Nothing to cut: Lean already. Ship.
Boundaries
Scope: over-engineering and complexity only. Correctness bugs, security holes, and performance are explicitly out of scope. Route them to a normal review pass. Lists findings, applies nothing. One-shot. "stop lean-audit" or "normal mode" to revert.
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 · 43 lines · 98 tokens per session scan A 43958e7525b9
lean-audit is a skill published in the GitHub repository utk2103/Prompt-Studio (9 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 98 tokens to every session and 400 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 86% identical to ponytail-audit, differing in 15 lines, and is treated as a copy.
Other skills, from other repositories
code-review
Reviews code for bugs, security issues, and best practices.
verify-absence-claims
Use when you're about to act on a "there is no X / none exists / not found / nothing handles this" claim — especially one from a delegated subagent, research handoff, or a teammate's summary. Positive file:line claims are citable and checkable; absence claims are only as good as the search pattern that produced them.…
distill-the-scar
Use when you just hit a real failure worth keeping — a bug, a wrong fix, a wasted hour — and want to turn it into a reusable skill instead of a private lesson. Turns one concrete failure into a Whetstone-shaped SKILL.md: extract the transferable invariant, write it so an agent can apply it without the original…
manufacture-review-independence
Use when reviewing your own work, or when the author-equals-reviewer guard is deliberately overridden — real independence is gone, so manufacture it: parallel independently-scoped sub-reviews plus an adversarial re-read of source for every high-severity claim, and treat cross-reviewer disagreement as a pointer to the…
diff-each-side-against-merge-base
Use when resolving a merge or rebase conflict, or reviewing a merge commit — conflict markers show where git gave up, not the full semantic delta, and 3-way auto-merge silently drops fields outside the markers. Compare ours/theirs/base by symbol and field inventory before trusting the result. Triggers on "merge…
findings-list-is-not-a-todo-list
Use when re-engaged to "act on" or "fix the rest of" a review, audit, or recommendation list — the list is not a to-do list. Re-read each item's own disposition first and bucket them; some are explicitly marked no-fix, some need a human decision, some are scale-gated. Triggers on "fix the findings", "address the…