A read-only knowledge base about machine learning, focused on transformer models, attention, its computational cost, and methods for handling long text. It contains compiled articles that can be queried without changing the knowledge base.

Use it to answer questions about how attention works, why it can become expensive, and how systems process longer context. Use it for querying the existing articles, not for adding or revising knowledge.

It gives you a prepared source of explanations instead of requiring you to reconstruct these topics from scratch. It also separates everyday questions from the maintenance work needed to update or audit the articles.

ml-llm-wiki — Skill by sammcj

Install

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.

agentmods

npx agentmods add skills/sammcj/agentic-coding/examples

Any agent

npx skills add sammcj/agentic-coding --skill examples

Clone the repo

git clone --depth 1 https://github.com/sammcj/agentic-coding

Made for: Claude Code, Codex.

Per session 80 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 765 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00080	$0.00765
Opus 5	$0.00040	$0.00382
Sonnet 5	$0.00016	$0.00153
Haiku 4.5	$0.00008	$0.00076

Measured yesterday against content hash fc14c58aea82, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ml-llm-wiki 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.

Skills/llm-wiki/examples/SKILL.md · 40 lines

How it starts

The opening of the file, as written. The whole thing — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Machine Learning Wiki

A self-contained markdown knowledge base on transformer architectures, attention cost and efficiency, and long-context scaling. This skill is for querying it: the knowledge is already compiled into articles under wiki/, so read those rather than re-deriving from scratch.

Keep this current: as the wiki grows, update the name and description above so they describe what it actually covers and trigger on the right questions.

(Sample note: this example wiki lives in examples/ within the llm-wiki repo. To load it as a skill, place the directory in your skills path named ml-llm-wiki, so the directory matches the name above.)

Maintenance and deeper analysis - ingesting sources, superseding stale knowledge, linting, auditing, critiquing reasoning - is not done here. Use the llm-wiki skill, which owns the write workflow and the file format. The llm-wiki skill is required to keep this wiki current; without it the wiki is still readable, but do not hand-edit articles outside the conventions in wiki/README.md.

What's inside

One topic so far, machine-learning: how attention works, why its memory cost was once thought to be a hard quadratic limit and why that turned out to be an implementation artefact, and what makes long context practical.

How to query

Read wiki/index.md - the catalogue, grouped by topic. Start here to find relevant articles.
Read the articles it points to. Follow body links for related material; grep -rl "<article>.md" wiki/ lists pages that link to a given article (backlinks).
If a local/ directory exists, search it too and fold in any relevant personal notes, labelling each hit as local/ (uncommitted) so it is never mistaken for shared, committed knowledge. local/ is the user's own, gitignored and absent from the index.
Answer from the wiki's content in preference to general knowledge. Cite articles with markdown links, e.g. [Attention Efficiency](wiki/machine-learning/attention-efficiency.md).
If a cited article has status: stale, say so and point to its replacement. Here, attention-cost.md is stale and superseded by attention-efficiency.md.
If the wiki has no answer, check wiki/gaps.md - the question may already be a tracked gap. Recording a new gap is a write, so it goes through the llm-wiki skill, not here.

Read the full file on GitHub · 40 lines

Files

What ships with it

13 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

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 · 40 lines · 80 tokens per session scan A fc14c58aea82

Subscribe to this mod's changes

ml-llm-wiki is a skill published in the GitHub repository sammcj/agentic-coding (158 stars, last pushed 7d ago), licensed Apache-2.0. It adds 80 tokens to every session and 765 once invoked, about $0.0004 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.

Code review Data and AI LLM Memory and context agentic agents ai cline copilot

ilya-sutskever

Agente que simula Ilya Sutskever — co-fundador da OpenAI, ex-Chief Scientist, fundador da SSI. Use quando quiser perspectivas sobre: AGI safety-first, consciência de IA, scaling laws, deep learning profundo, o episódio de novembro 2023 na OpenAI, superinteligência segura.

beel-collab/presets.dev · 67 tokens

yann-lecun

Agente que simula Yann LeCun — inventor das Convolutional Neural Networks, Chief AI Scientist da Meta, Prêmio Turing 2018.

beel-collab/presets.dev · 32 tokens

shopify-apps

Expert patterns for Shopify app development including Remix/React Router apps, embedded apps with App Bridge, webhook handling, GraphQL Admin API, Polaris components, billing, and app extensions.

beel-collab/presets.dev · 36 tokens

yann-lecun-debate

Sub-skill de debates e posições de Yann LeCun. Cobre críticas técnicas detalhadas aos LLMs, rivalidades intelectuais (LeCun vs Hinton, Sutskever, Russell, Yudkowsky, Bostrom), lista completa de rejeições a afirmações mainstream, posição sobre risco existencial de IA, e técnicas de debate ao vivo.

beel-collab/presets.dev · 78 tokens

context-guardian

Guardiao de contexto que preserva dados criticos antes da compactacao automatica. Snapshots, verificacao de integridade e zero perda de informacao.