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.
/plugin marketplace add LilMGenius/paperthinnpx agentmods add plugins/lilmgenius/paperthin/paperthingit clone --depth 1 https://github.com/LilMGenius/paperthinGrade A, and why
paperthin 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 yesterday.
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.
What it actually says
{
"name": "paperthin",
"description": "Low-level agentic design patterns. Turning old engineering wisdom into reflexes your agent reaches for on its own—on any agent.",
"skills": [
"./skills/depth/re0",
"./skills/depth/readchk",
"./skills/depth/aim",
"./skills/depth/modelchk",
"./skills/depth/hate",
"./skills/depth/macrothink",
"./skills/depth/feynman",
"./skills/depth/autobahn",
"./skills/depth/reorder",
"./skills/depth/detool",
"./skills/depth/dedash",
"./skills/depth/debloat",
"./skills/depth/shower",
"./skills/depth/factchk",
"./skills/depth/mandela",
"./skills/depth/sip",
"./skills/depth/re0-git",
"./skills/depth/re0-release",
"./skills/depth/re0-merge",
"./skills/breadth/ssotize",
"./skills/breadth/re0-upgrade",
"./skills/coil/re0-plan",
"./skills/coil/re0-loop",
"./skills/coil/re0-memo",
"./skills/coil/re0-work",
"./skills/coil/catchup",
"./skills/coil/nba",
"./skills/mesh/prism"
]
}
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.
- yesterday First seen · 35 lines scan A 7ac2df50d744
paperthin is a plugin published in the GitHub repository LilMGenius/paperthin (914 stars, last pushed 13d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 plugins, from other repositories
rune
67-skill mesh for Claude Code with runtime auto-discipline — native hooks (preflight/sentinel/completion-gate/quarantine) auto-fire at lifecycle boundaries. 248 mesh connections + 46 signals, adaptive routing, mesh analytics, MCP quarantine guidance, and project memory.
jaiskills
Orchestration (insistir, constatar, remoto), prompting (metaprompt), knowledge compounding, file-based TODOs, and OpenAI tooling (askcodex, image-to-frontend) as one Claude Code plugin.
clean-code-skills
Plugin marketplace listing 1 plugin: clean-code-skills.
clean-code-skills
Language-agnostic clean-code skill for AI agents: naming, focused functions, file and code placement, single responsibility, boundaries, error handling, tests, concurrency, security, agent failure modes, and surgical or whole-project refactoring.
mojiemoji-github
GitHub Markdown 向け mojiemoji 画像スタンプを埋め込むスキル + サブエージェント + 6 必須パラメータゲートフック.
missing-codex-manifest
Anti fixture: declares claude+codex agent-targets but ships no .codex-plugin manifest, to trip S6.