Paperthin is a collection of low-level design patterns that coding agents can apply as repeatable checks and actions during software work. It is for people using agents such as Claude Code, Codex, Cursor, or other supported tools, and its catalogue entries package the patterns as skills, an instruction, and a plugin.
Borrowing it
Nothing to install: this file belongs to LilMGenius/paperthin. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/LilMGenius/paperthin/main/AGENTS.mdgit 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/instructions/lilmgenius/paperthin/agents-md)<a href="https://agentmods.dev/instructions/lilmgenius/paperthin/agents-md"><img src="https://agentmods.dev/badge/instructions/lilmgenius/paperthin/agents-md/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/instructions/lilmgenius/paperthin/agents-md"><img src="https://agentmods.dev/badge/instructions/lilmgenius/paperthin/agents-md.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 | $0.03405 | $0.03405 |
| Opus 5.5 | $0.01362 | $0.01362 |
| Sonnet 5.5 | $0.00681 | $0.00681 |
| Haiku 4.5 | $0.00341 | $0.00341 |
Grade A, and why
paperthin AGENTS.md 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 17d 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
94% identical to paperthin CLAUDE.md — 118 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.
How it starts
The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Paperthin
Paperthin is an agent-agnostic suite of plain-Markdown skills that keep an artifact clean and true — hygiene reflexes an agent reaches for on its own. This is the guide for authoring them — and itself a skill artifact, so re0 it when it drifts. Every skill named below is defined in the shipped catalog, the README.
Philosophy
- Trust the artifact, not the author. A skill exists to make work read true to someone who wasn't there — clear (does it read?) and correct (is what it claims real?). The maker's in-session mind is the worst judge of either, so a skill either re-derives the work from what's true now or imports outside eyes to test it.
- Generic examples, not instances. In any durable doc — this guide, a
SKILL.md, a release note — an example stays generic ((#123, @handle),land/pr-<n>); a real PR number, handle, SHA, or range ages into residue a later reader misreads for current fact. - Single source of truth, and self-contained skills. One fact lives in one place; everything else references it by name. But a skill ships and runs installed alone (
npx skills addcan pull one without its siblings or this guide), so it states the runtime rules it needs inline rather than pointing at AGENTS.md or another skill. The two live at different layers: SSOT keeps a fact from drifting; self-containment lets a skill travel. The one-home rule bends in exactly two places: cross-skill naming, for declared pairs and orchestrators (see Conventions); and the skill roster, which — with no build step to generate it — is hand-written onto several surfaces that can't reference each other (re0-upgrade's catalog,scripts/catalog.cjs, plugin.json, the READMEs). CI guards those copies in sync —validate-skills.shandcheck-catalog-sync.cjs— rather than one home feeding them; never dedupe them. - Restraint. Change only what genuinely improves — a pass that finds nothing to improve changes nothing. The enemy is slop (noise, duplication, padding), not addition.
- Recursive. Every skill is general enough to use while building the skills, so we maintain the skills with the skills, and each pass is audited and refined by the tools it ships. Treat that loop as the point.
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.
- 17d ago Changed · +51 tokens per session 903ea9dbcd44
- 1mo ago First seen · 118 lines · 3,354 tokens per session scan A fc197759be6a
paperthin AGENTS.md is an instructions file published in the GitHub repository LilMGenius/paperthin (1,154 stars, last pushed yesterday), licensed MIT. It adds 3,405 tokens to every session, about $0.0136 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 94% identical to paperthin CLAUDE.md, differing in 118 lines, and is treated as a copy.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).