okf-create-bundle

okf-create-bundle is a skill for Claude Code from saulmcphd/okf-skills. It costs 174 tokens per session (3,144 once invoked), scanned A, original, MIT.

Um criador de pastas com arquivos Markdown — textos simples e fáceis de ler — ligados por links. O formato OKF cria uma base de conhecimento portátil, como um segundo cérebro, sem banco de dados ou serviço proprietário.

In plain words
What is it for?
Serve para iniciar bases de conhecimento sobre qualquer assunto, definindo a estrutura de pastas, o índice e os arquivos interligados.
Why use it?
Ajuda a organizar conhecimento de modo que pessoas e agentes de IA encontrem os conceitos relacionados sem precisar carregar todos os arquivos de uma vez.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions CLAUDE.md.

Part of the okf-skills plugin — 8 skills shipped together

Good fit Serve para iniciar bases de conhecimento sobre qualquer assunto, definindo a estrutura de pastas, o índice e os arquivos interligados.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/saulmcphd/okf-skills/okf-create-bundle
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.

Any agent
npx skills add saulmcphd/okf-skills --skill okf-create-bundle
Clone the repo
git clone --depth 1 https://github.com/saulmcphd/okf-skills

Made for: Claude Code.

Or install okf-skills, the plugin that ships this one along with the rest of its 8 skills.

Wrote 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.

agentmods badge for okf-create-bundle

README.md
[![agentmods](https://agentmods.dev/badge/skills/saulmcphd/okf-skills/okf-create-bundle.svg)](https://agentmods.dev/skills/saulmcphd/okf-skills/okf-create-bundle)
Your own site
<a href="https://agentmods.dev/skills/saulmcphd/okf-skills/okf-create-bundle"><img src="https://agentmods.dev/badge/skills/saulmcphd/okf-skills/okf-create-bundle.svg" alt="Measured on agentmods" height="20"></a>
Per session 174 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,144 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00174 $0.03144
Opus 5 $0.00087 $0.01572
Sonnet 5 $0.00035 $0.00629
Haiku 4.5 $0.00017 $0.00314

Measured 8d ago against content hash dd8f3f13d3a3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

okf-create-bundle 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 8d 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.

plugins/okf-skills/skills/okf-create-bundle/SKILL.md · 215 lines

How it starts

The opening of the file, as written. The whole thing — 215 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Create an OKF bundle

Scaffold a new Open Knowledge Format (OKF) bundle: a directory of interlinked markdown files that form a portable, vendor-neutral "brain." This skill covers the folder layout, the build process, and the definition of done. It is domain-agnostic — the same structure serves a gardening brain, an academic brain, or a company wiki.

If the repo already contains an okf-gold-standard.md, treat it as the fuller source of truth and follow any project-specific extensions it records. This skill is the self-contained version.

What an OKF bundle is (the mental model)

  • Just files, just markdown, just YAML frontmatter. No database, no runtime, no proprietary SDK.
  • Each file is one concept / unit of knowledge. The file path is the identity of that node.
  • Nodes interlink with ordinary markdown links, forming a knowledge graph an agent can traverse.
  • Read index.md first. An agent opens the index (progressive disclosure), finds the few files relevant to its task, and opens only those — it never loads the whole bundle. This is why nodes can and should carry MAXIMUM detail: findability is the index's job, not the reader's.
  • The index replaces RAG / embeddings as the retrieval layer. Retrieval is by curated navigation, not vector search — transparent, deterministic, auditable, and needs no embedding store. Index-first navigation works well up to roughly a few hundred nodes; beyond that, keep the index but add an on-device search pass (BM25 + optional local vectors, with LLM re-ranking) — still local, still no cloud embedding infrastructure.
  • A brain is a compounding artifact, not a one-shot export. The tedious part of a knowledge base is the bookkeeping — updating cross-references, spotting contradictions, keeping the index current — which is exactly what an agent does tirelessly. Humans curate sources and direct the work; the agent maintains the graph. Value accrues every time a source is ingested or a good answer is filed back.

Read the full file on GitHub · 215 lines

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.

  1. 8d ago First seen · 215 lines · 174 tokens per session scan A dd8f3f13d3a3

Subscribe to this mod's changes

okf-create-bundle is a skill published in the GitHub repository saulmcphd/okf-skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 174 tokens to every session and 3,144 once invoked, about $0.0009 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.

Related

Other skills, from other repositories

media-ingest

Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.

garrytan/gbrain · 52 tokens

mem0-oss-to-platform

Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…

mem0ai/mem0 · 273 tokens

Cortex

Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…

danielmiessler/LifeOS · 196 tokens

memory

Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.

opensquilla/opensquilla · 44 tokens

ha-data-stores

Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…

shiwenwen/hope-agent · 115 tokens

establishing-project-context

Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.

GanyuanRan/Aegis · 45 tokens