paperthin CLAUDE.md

paperthin CLAUDE.md is an instructions file for coding agents from LilMGenius/paperthin. It costs 3,343 tokens per session, scanned A, original, MIT.

A contributor guide for Paperthin, a collection of plain-Markdown instructions for coding agents. It explains how to write skills that keep documents clear, accurate, and usable on their own.

In plain words
What is it for?
Use it when creating or maintaining Paperthin skills, including their Markdown format, layout, philosophy, and invocation settings.
Why use it?
It helps authors avoid stale examples, unsupported claims, and skills that only work when other files are present.

Instructions file

Install

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.

agentmods
npx agentmods add instructions/lilmgenius/paperthin/claude-md
Clone the repo
git clone --depth 1 https://github.com/LilMGenius/paperthin

Wrote 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.

agentmods badge for paperthin CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/lilmgenius/paperthin/claude-md.svg)](https://agentmods.dev/instructions/lilmgenius/paperthin/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/lilmgenius/paperthin/claude-md"><img src="https://agentmods.dev/badge/instructions/lilmgenius/paperthin/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 3,343 This file is loaded in full into every session.
When invoked 3,343 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.03343 $0.03343
Opus 5 $0.01672 $0.01672
Sonnet 5 $0.00669 $0.00669
Haiku 4.5 $0.00334 $0.00334

Measured 4d ago against content hash 295f51549fb8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

paperthin CLAUDE.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 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.

CLAUDE.md · 118 lines

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 add can pull one without its siblings or this guide), so it states the runtime rules it needs inline rather than pointing at CLAUDE.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.sh and check-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.

Read the full file on GitHub · 118 lines

Changes

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.

  1. 4d ago First seen · 118 lines · 3,343 tokens per session scan A 295f51549fb8

Subscribe to this mod's changes

paperthin CLAUDE.md is an instructions file published in the GitHub repository LilMGenius/paperthin (1,054 stars, last pushed 16d ago), licensed MIT. It adds 3,343 tokens to every session, about $0.0167 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.