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.
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 LilMGenius/paperthin --skill re0-memogit 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/re0-memo)<a href="https://agentmods.dev/skills/lilmgenius/paperthin/re0-memo"><img src="https://agentmods.dev/badge/skills/lilmgenius/paperthin/re0-memo/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/lilmgenius/paperthin/re0-memo"><img src="https://agentmods.dev/badge/skills/lilmgenius/paperthin/re0-memo.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk warn
- NVIDIA SkillSpector pass
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 | $0.00064 | $0.00685 |
| Opus 5 | $0.00032 | $0.00342 |
| Sonnet 5 | $0.00013 | $0.00137 |
| Haiku 4.5 | $0.00006 | $0.00068 |
Grade A, and why
re0-memo 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 9d 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 — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Turn a completed cycle into lessons the next cycle can actually use.
Goal
re0-memo extracts durable learning from a work cycle without defending the artifact that produced it. A cycle can run, pass tests, and still be the wrong thing. The output is not a changelog or therapy note: it is a local, evidence-backed record of what worked, what misled the build, and what gate the next pass must clear.
Use re0-memo when the artifact is done, failed, disappointing, or ambiguous enough that the next agent needs the cycle's lessons more than its momentum.
Workflow
- Read the original objective, final artifact, QA evidence, user complaints, and any local planning notes.
- Separate working assets from misleading progress: contracts, schemas, tests, services, vocabulary, and examples that earned reuse vs. UI, panels, scaffolds, or abstractions that only looked productive.
- Generalize before recording: when feedback arrives as many specific complaints, cluster them upward into the shared pattern before writing anything down — many specifics against many items usually share one root gap. Record the root and its pattern family as the lesson; keep the specifics under it as evidence, not as lessons themselves.
- Name each failure as an anti-pattern, not a mood.
- Convert repeated or high-impact failures into quality gates for the next pass.
- Convert vague user direction into architecture vocabulary a fresh agent can use.
- Write or refresh local docs for the cycle: a re0-memo for lessons and a plan for next-cycle contracts, gates, and vocabulary.
- Verify that a from-scratch agent could avoid the same failure from those docs alone.
Rules
- Do not defend the artifact. If it missed the product, say what missed.
- Do not write a changelog. File lists and effort summaries are not lessons.
- Do not transcribe a specific complaint as a lesson. A lesson that only fixes the reported case keeps the system human-in-the-loop: the same class of failure returns anywhere a person didn't point. Escalate every specific to the pattern that catches its whole class — the reporter's exact words are evidence, not the gate.
- Preserve negative corpus. Failed paths are training data.
- Prefer hard gates over advice.
- Cite evidence from the cycle: objective, file facts, QA output, screenshots, transcripts, diffs, or user feedback.
- If the next agent cannot act on it, it is not a lesson yet.
- Keep provenance local; shipped artifacts should not narrate their scars.
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.
- 9d ago First seen · 44 lines · 64 tokens per session scan A 10d2a533ad92
re0-memo is a skill published in the GitHub repository LilMGenius/paperthin (1,086 stars, last pushed 2d ago), licensed MIT. It adds 64 tokens to every session and 685 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-handoff
A skill that creates a compact handoff.md summary for starting a new Claude chat when the current chat is full. The file records recent work, current status, open questions, and selected project context.
mm-save-session
An end-of-session recorder for Claude Code that saves the conversation summary and project state in Obsidian notes. Obsidian is a note-taking app that stores information as files.
mm-clear-gate
A read-only checkpoint that uses a script to check whether project notes, handoff files, repository changes, and session records have been saved before clearing context.
mm-setup
A setup guide that personalizes a shared mm system for one user. It asks for details such as your name, work area, tools, language, and Obsidian vault location, then saves them in private configuration files.
mm-vault
A setup tool that creates a private GitHub repository for an Obsidian project memory folder and connects it to Claude.ai project knowledge. Obsidian is a note-taking app that stores information as files.
mm-doctor
A diagnostic workflow for checking the health of the mm system, including its configuration, project links, note vault, passports, session archive, and planning consistency.