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 agentmods add skills/lilmgenius/paperthin/sipnpx skills add LilMGenius/paperthin --skill sipgit clone --depth 1 https://github.com/LilMGenius/paperthinWrote 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/lilmgenius/paperthin/sip)<a href="https://agentmods.dev/skills/lilmgenius/paperthin/sip"><img src="https://agentmods.dev/badge/skills/lilmgenius/paperthin/sip.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 | $0.00055 | $0.00702 |
| Opus 5 | $0.00028 | $0.00351 |
| Sonnet 5 | $0.00011 | $0.00140 |
| Haiku 4.5 | $0.00006 | $0.00070 |
Grade A, and why
sip 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 4d 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 — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Taste your own cooking: the moment you finish making something, check it with the very skills this repo ships before you serve it.
Goal
A reminder buried in docs ("remember to verify") won't reliably fire in a fresh session. sip makes the recursive self-improvement loop a triggered habit: right after any create or change, run our own skills on the result — the clean checks and the true ones — so quality doesn't ride on the author's biased in-session judgment.
Workflow
- Spot the trigger: you just created or changed an artifact or skill and are about to call it done, commit, or hand it off.
- Cold-read it — run
showeron the artifact (fresh-eyes comprehension / handoff check). - Verify it's true — if the artifact asserts a reality-grounded claim, run
factchk; if it defines an eval, metric, or experiment, runmandela. Skip when it has neither. - Check consistency — run
ssotizein audit mode across the repo for anything the change duplicated or contradicted; execute its consolidation plan only after approval. - Detool portability claims — run
detoolonly when the artifact claims portability, tool-neutrality, stack-agnostic durability, or cross-agent reuse. Skip when it is provenance, operational notes, a tool-targeted runbook, or does not claim portability. - Tidy —
re0the changed docs so the result reads as a clean v0, not a patch over a draft. - Apply the findings here, then serve it.
Rules
- Trigger on your OWN output, right after making it — that's when bias is highest and a check is cheapest.
- Use the skills; don't re-implement them —
showerfor clarity,factchk/mandelafor truth,ssotizefor SSOT,detoolfor portability claims,re0for cleanup.siporchestrates and routes findings back to the author session to fix; the skills do the work. - Skip what plainly doesn't apply, or any check whose skill isn't installed — run only what's present.
factchk/mandelafire only when there is a claim or an eval;detoolfires only when the artifact claims portability, tool-neutrality, stack-agnostic durability, or cross-agent reuse; a one-line prose tweak may need only a consistency check. Say what you skipped and why. - Stop at the artifact —
sipnever touches git or makes commits. - Chain only model-invoked skills; a user-invoked skill (marked
disable-model-invocation) is a human's to fire deliberately, sosipmust not call one.
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.
- 4d ago First seen · 37 lines · 55 tokens per session scan A e92f71a75197
sip is a skill published in the GitHub repository LilMGenius/paperthin (1,054 stars, last pushed 16d ago), licensed MIT. It adds 55 tokens to every session and 702 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 2026-08-30.
Other skills, from other repositories
mm-init-project
Инициализирует или обновляет проект для mm-системы — создаёт passport.md в корне, копию в Obsidian, dashboard.md, handoff.md (скелет), project-instructions.md для claude.ai. Use when user says "оформи проект", "сделай паспорт", "init project", "/mm-init", "/mm-init-project", "обнови паспорт", "регистрирую проект".…
mm-setup
Онбординг/персонализация mm-системы под конкретного пользователя — спрашивает имя, чем занимается, стек, язык, путь к Obsidian vault, и записывает это в личный gitignored-оверлей config/mm-config.local.json + генерирует персональную копию claude.ai-скилла mm-web-bridge. Use when user says "/mm setup", "/mm onboard"…
mm-update
Самообновление mm-системы из удалённого репозитория. mm раздаётся через git clone + register-skills (не npm), поэтому update = git pull свежего mm из origin/main + повторный register-skills + notice о перезапуске Claude Code. Use when user says "обнови mm", "обнови систему", "/mm update", "update mm", "подтяни свежий…
mm
Диспетчер mm-системы — короткая команда вместо длинных. /mm без аргументов = список всех команд. /mm new = init project, /mm save = save session, /mm next = handoff, /mm prompt = bridge, /mm rules = instructions, /mm check = doctor. Use when user types "/mm" anything OR says "что есть в mm", "какие mm команды"…
content-editor
Writes and edits the portfolio's pages. Reads a brief, follows the style guide, and emits the HTML into public/.
notion-publish
Mirrors the portfolio's pages into Notion after publishing, creating one Notion page per site page via the Notion MCP. Use it from /publish, or when the user asks to sync the site to Notion.