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-gaingit 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-gain)<a href="https://agentmods.dev/skills/utk2103/prompt-studio/lean-gain"><img src="https://agentmods.dev/badge/skills/utk2103/prompt-studio/lean-gain.svg" alt="Measured on agentmods" 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 | $0.00069 | $0.00591 |
| Opus 5 | $0.00034 | $0.00296 |
| Sonnet 5 | $0.00014 | $0.00118 |
| Haiku 4.5 | $0.00007 | $0.00059 |
Grade A, and why
lean-gain 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.
What it actually says
Lean Gain
Display this scoreboard when invoked. One-shot: do NOT change mode, write flag files, or persist anything.
The figures are Prompt-Studio's own benchmark medians, measured — not computed
from the current repo. Source: benchmarks/results/latest.json and
benchmarks/results/2026-08-12-lean-vs-ponytail.md.
Scoreboard
Render plain ASCII bars. The bar length shows the measured range; the label carries the exact figure:
lean gain measured · gpt-4o-mini · n=3 · 7 tasks
Lines of code baseline ████████████████████ 100%
lean ██████·············· 25–35% ▼ 65–75%
Speed lean ▸ ~4× faster (3.5–4.3×, full = 4.25×)
Cost not shown by design — see Honesty boundary.
This repo: /prompt-studio:lean-stats (real tokens, this session)
/prompt-studio:lean-debt (counted shortcut ledger)
/prompt-studio:lean-audit (what's still cuttable)
Honesty boundary
These are benchmark medians, not this repo. NEVER print a per-repo savings number ("you saved X lines/tokens here"): the unbuilt version was never written, so there is no real baseline to subtract from in a live repo.
No cost bar is shown by design, not omission: on single-shot tasks Lean's
cost is roughly flat (~100–108% of baseline in latest.json) because the Lean
system-prompt input tokens offset the output-token savings. Claiming a cost win
would contradict the measured data. For real per-session cost use
/prompt-studio:lean-stats (actual token counts) and /prompt-studio:lean-debt
(counted ledger); for what's still cuttable, /prompt-studio:lean-audit.
Basis is a single model (gpt-4o-mini, n=3) — the footer says so. Do not present it as multi-model.
Boundaries
One-shot display. Edits nothing, changes no mode. "stop lean" or "normal mode": 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.
- 7d ago First seen · 59 lines · 69 tokens per session scan A 4fe1720df09d
lean-gain is a skill published in the GitHub repository utk2103/Prompt-Studio (7 stars, last pushed 7d ago), licensed Apache-2.0. It adds 69 tokens to every session and 591 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.
Other skills, from other repositories
avoid-ai-writing
Audit and rewrite content to remove AI writing patterns ("AI-isms"). Use this skill when asked to "remove AI-isms," "clean up AI writing," "edit writing for AI patterns," "audit writing for AI tells," or "make this sound less like AI." Supports a detect-only mode, an edit-in-place mode for files, an optional voice…
ai-writing-detector
Use when the user asks to detect, scan, audit, score, or flag AI-writing patterns without rewriting the text, including requests for a deterministic local detector result when the host can execute Node.
preservation-verifier
Use when the user provides an original and rewritten version, asks whether a rewrite preserved protected content, or wants a deterministic check for code, frontmatter, quotes, tables, links, paths, numbers, headings, and residual AI-pattern regressions.
avoid-ai-writing-router
Use when a request combines AI-writing audit, rewrite, file editing, voice preservation, false-positive interpretation, verification, or when the user invokes Avoid AI Writing without naming a mode.
false-positive-reviewer
Use when a user asks what AI-writing flags mean, whether detector output proves AI authorship, or wants a careful interpretation of possible false positives, especially for academic, hiring, publication, disciplinary, or other consequential decisions.
file-edit-in-place
Use when the user names a local file and explicitly asks to clean, rewrite, humanize, or remove AI-writing patterns in that file itself, with minimal targeted edits and post-edit verification.