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 ssotizegit 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/ssotize)<a href="https://agentmods.dev/skills/lilmgenius/paperthin/ssotize"><img src="https://agentmods.dev/badge/skills/lilmgenius/paperthin/ssotize/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/ssotize"><img src="https://agentmods.dev/badge/skills/lilmgenius/paperthin/ssotize.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 | $0.00078 | $0.01120 |
| Opus 5.5 | $0.00031 | $0.00448 |
| Sonnet 5.5 | $0.00016 | $0.00224 |
| Haiku 4.5 | $0.00008 | $0.00112 |
Grade A, and why
ssotize 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:
- ssotize — 100% identical
How it starts
The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Find where one truth lives, get approval for the consolidation plan, then collapse it into one canonical home.
Goal
Enforce Single Source of Truth (SSOT): one fact = one home, and every other place that needs it references that home instead of copying it. References don't drift; copies do. This mutates artifacts, so it is deliberate and loss-averse.
ssotize starts as a read-only audit. It names the truth in scope, finds every copy, chooses the canonical home, and reports the exact consolidation plan. Only after the user approves that plan does it mutate artifacts.
Use this to establish or repair SSOT — messy, legacy, or freshly-scaffolded states. Once SSOT holds, don't overuse it: consolidation is a one-time repair, not ongoing upkeep. When a read-only checker and a mutating follow-up have become one inseparable workflow, fold the checker into the consolidator and keep the approval gate; splitting the reflex only makes the safer first half easier to skip.
Workflow
- Name the truth in scope — the specific fact, value, spec, decision, status, or definition being tracked, not the whole document.
- Audit read-only first: enumerate every occurrence across the given artifacts and platforms.
- Re-enumerate by a second method — a different search term, synonym, or tool — and confirm it surfaces no occurrence the first pass missed.
- Classify each occurrence: exact copy, paraphrase, partial, stale, or contradictory.
- Pick the canonical home — the most authoritative and most-maintained location, closest to where the fact actually changes. Never promote a weak copy just because it is convenient; extract a new canonical home if none exists.
- Decide the action per non-canonical occurrence: dedupe (redundant copy), reference (docs should link to canonical, code should import/source/include it, config should use a shared read), or reconcile (it disagrees and needs a human call).
- Report the audit before editing: a table of occurrences (location · kind · action), the proposed canonical home with a one-line justification, unique details that must be folded into it, contradictions that need a decision, and the exact mutation plan.
- Ask for explicit approval to execute the mutation plan. If approval is not given, stop after the read-only report.
- Make or extract the canonical home complete and current — fold in any unique detail that lived only in a copy. Never lose information to consolidation.
- Reconcile contradictions in the canonical home first; when the correct value is ambiguous, confirm it before replacing anything.
- Replace each duplicate with a live reference to the canonical home — for docs, use a link, a "see ", a quote-with-link, or a transclude where the platform supports it; for code, use an import/source/include of the shared home; for config, use a shared read from the one maintained file.
- Remove the now-redundant copies. Where removal would orphan a reader, leave a one-line pointer instead of deleting outright.
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 · 53 lines · 78 tokens per session scan A 65a5097919bf
ssotize is a skill published in the GitHub repository LilMGenius/paperthin (1,329 stars, last pushed yesterday), licensed MIT. It adds 78 tokens to every session and 1,120 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
hackmd
Create and edit HackMD documents and Book mode navigation with Markdown, diagrams (Mermaid, Graphviz, PlantUML), and embeds (YouTube, Gist, PDF, Figma). Use for collaborative documentation and organizing linked notes into books.
hackwiki
Use the Hackwiki CLI to inspect, search, and maintain a HackMD-backed wiki when the user asks to work with Hackwiki notes.
wiki-ingest-pdf
Use when adding one or more PDF files as sources in a llm-wiki knowledge base. Covers source folder creation, PDF extraction, structured analysis, index update, and wiki ingest. Triggers on: "add this PDF to the wiki", "ingest this paper", "create a source for this file", "add as source in my wiki".
pdf-parse
Extract text and structure from PDF files into Markdown or plain text. Selects the right tool automatically: xberg for machine-readable PDFs (fast, Rust core, no ML overhead), marker-pdf for scanned or image-heavy PDFs (OCR + layout detection). Includes tool installation, update, and cleanup. Use before any task that…
research-paper
Process an academic paper (PDF or URL) into the agent-knowledge repository. Extracts text, produces a confidence-annotated structured analysis, and integrates findings into the appropriate topic. Use when asked to read, analyse, or integrate a research paper into the knowledge base. Do NOT use for general web pages or…
summarize
Summarize URLs, local files (PDFs, documents, audio), and YouTube links. Composable pipeline using llm + markitdown + Jina Reader. Supports local models via Ollama. Use when you need a quick one-shot summary without ingesting into the knowledge base.