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 debloatgit 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/debloat)<a href="https://agentmods.dev/skills/lilmgenius/paperthin/debloat"><img src="https://agentmods.dev/badge/skills/lilmgenius/paperthin/debloat/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/debloat"><img src="https://agentmods.dev/badge/skills/lilmgenius/paperthin/debloat.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
- 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 | $0.00066 | $0.00751 |
| Opus 5.5 | $0.00026 | $0.00300 |
| Sonnet 5.5 | $0.00013 | $0.00150 |
| Haiku 4.5 | $0.00007 | $0.00075 |
Grade A, and why
debloat 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 1mo 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- debloat — 100% identical
How it starts
The opening of the file, as written. The whole thing — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cut a bloated artifact to its load-bearing minimum: same meaning, fewer words.
Goal
An artifact that is correct and current can still rot a second way: it accretes. Each edit bolts a qualifier onto the nearest sentence, a rule gets restated wherever it might apply, an enumeration grows into a wall — until a reader must study what they should skim. debloat compresses that bloat to its load-bearing density: every claim that carries weight survives, every word that does not is cut. It is not a rewrite (re0), a dedup (ssotize), or a tell-remover (dedash, detool) — it is a density pass on prose that is otherwise fine.
Workflow
- Pin the artifact and read it end to end; note in one line what each section must convey — the load-bearing content that has to survive.
- Find the bloat, not the content: padding that adds length but not meaning; a qualifier or parenthetical the sentence holds without; a fused sentence carrying three ideas; a wall of enumeration where a rule plus a short list would do; a point restated within reach of itself; litigation-history (why-we-decided-it) where the rule alone suffices.
- Compress in place: cut the padding, split the fused sentence or drop its dead clause, collapse the wall, keep a repeated point once. Move nothing to another artifact and re-derive nothing.
- Preserve every load-bearing claim — a rule, fact, constraint, or example that carries weight. If cutting a word would lose one, keep the word.
- When the bloat is really duplication across artifacts, or the content has drifted stale, stop and name it: hand duplication to
ssotizeand drift tore0.debloatonly tightens. - Re-read cold and cut again — the first pass always leaves some.
Rules
- Cut words, never load-bearing claims. Every rule, fact, and constraint that was there is still there; only the density changed.
- Preserve the artifact's voice and structure; compress within it, do not re-style it.
- Not a rewrite, a dedup, or a tell-remover: re-derive nothing (
re0), move nothing to another home (ssotize), and leave em-dashes and stack nouns todedash/detool. - Respect intended richness: human-facing prose meant to teach or orient (a quickstart, a worked example) earns its length — compress the bloat, not the accessibility.
- A pass that finds nothing genuinely bloated changes nothing.
- Mutate with edit-safety: assert each target exists (report a MISS, never a silent no-op), edit unicode-safe (
PYTHONUTF8=1), replace per occurrence, and script a large structural move.
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.
- 1mo ago First seen · 38 lines · 66 tokens per session scan A dfc15de621d0
debloat is a skill published in the GitHub repository LilMGenius/paperthin (1,334 stars, last pushed today), licensed MIT. It adds 66 tokens to every session and 751 once invoked, about $0.0003 per session on Opus 5.5. 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-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-update
A guided updater for the mm system, which is installed by copying a Git repository rather than through a package manager. It downloads the latest version, registers its skills again, and tells you to restart Claude Code.
mm
A dispatcher that provides short /mm commands for project setup, session recovery, project overviews, and workflow checks. It maps these aliases to longer system commands.
mm-instructions
A generator for ready-to-paste instructions for a Claude.ai project. It reads project details and fills a template with the project's name, technology, planning information, and current work context.
mm-projects
A read-only overview of all registered projects stored in Obsidian notes. It shows each project's status, type, current GSD phase, recent activity, and number of open questions.
goal-loop
Drive a verifiable goal to done with factory-built agents, visible and held-out evidence, and a cross-provider judge.