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 agentmods add skills/sancovp/dinf/using-dinfnpx skills add sancovp/dinf --skill using-dinfgit clone --depth 1 https://github.com/sancovp/dinfWrote 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/sancovp/dinf/using-dinf)<a href="https://agentmods.dev/skills/sancovp/dinf/using-dinf"><img src="https://agentmods.dev/badge/skills/sancovp/dinf/using-dinf.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00118 | $0.01464 |
| Opus 5 | $0.00059 | $0.00732 |
| Sonnet 5 | $0.00024 | $0.00293 |
| Haiku 4.5 | $0.00012 | $0.00146 |
Grade A, and why
using-dinf 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 5d 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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
using-dinf
⊥ (the simplest instance — start here): a joke. The setup lays out parts; the punchline adds nothing new — it only re-shows what the setup already contained, and the whole thing lands at once. That click is the target experience of every structure below. If you have ever gotten a joke, you already run this natively.
The basis (five marks)
⟨ a ; b ; c | Ω ⟩
- Working terms
a ; b ; c— the k parts that DO things. Each one nameable. - The bar
|— the jurisdiction line. Left of it: action. Right of it: never action. - The closure
Ω— the +1. Three laws identify it anywhere:- Stative — a state or a delta, never a step.
- Zero-delta — introduces nothing the working terms didn't contain; it may only recombine and re-show them. (A punchline with new information is setup.)
- Self-referential — the structure applied to itself.
- Nesting — any working term expands into its own full structure. Depth is free.
- Succession — a closure retypes as the next structure's opening,
Ω₁ ↦ ⊥₂.
The construction (three operators, and how to run them)
-
FACTOR — find Ω by the three laws; what remains is k. If a system resists factoring, it is either a segment (its opening lives one level up) or genuinely incomplete — and you now know exactly what it is missing.
dinf factor "the hero's journey" -
ADJOIN — two frames fighting is a missing Ω one level up. Do not adjudicate: pair them and close the pair,
⟨ A ; B | Ω′ ⟩. Both views survive.dinf adjoin "move fast" "don't break things" -
CHRISTEN — the moment you feel "these are all the same", name the invariant and write it down. Unnamed convergences evaporate; named ones become vocabulary. The
kb/directory in the AIOS is that vocabulary, and it only grows.
The gate (why this is not just a way of talking)
A chain is the notation in executable form: [Focus] ⇒ [Focus] ⇒ |Converge|.
Bare labels in the brackets, exactly one closing convergence.
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.
- 5d ago First seen · 112 lines · 118 tokens per session scan A ebe1edeb5597
using-dinf is a skill published in the GitHub repository sancovp/dinf (1 stars, last pushed 28d ago), licensed MIT. It adds 118 tokens to every session and 1,464 once invoked, about $0.0006 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 2026-08-31.
Other skills, from other repositories
playwright
Use when the task requires capturing or automating a real browser from the terminal.
eli5
Explain concepts in very simple terms suitable for a five-year-old.
transformer-attention
Use when reasoning about Transformer self-attention, multi-head attention, positional encoding, masked decoder attention, or why attention replaced recurrence/convolutions in sequence models; not for generic NLP or unrelated attention topics.
extract-wisdom
Extract wisdom, insights, and actionable takeaways from YouTube videos, blog posts, articles, or text files. Use when asked to extract wisdom or key insights from a given content source.
ml-llm-wiki
Use when answering questions from this machine-learning knowledge base. Triggers: questions about transformers, attention cost and efficiency, and long-context scaling; 'what do we know about attention', 'check the ML wiki'. Read-only querying of compiled knowledge; to add, update, supersede, lint, audit, or critique…
ai-engineering-curriculum
Use when structured AI engineering curriculum — 382 skills + 99 prompts across 20 phases covering ML, deep learning, LLMs, agents, and production systems. Use when learning AI, building AI skills,.