Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/lorsabyan/okf-skillnpx agentmods add skills/lorsabyan/okf-skill/okfWrote 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/lorsabyan/okf-skill/okf)<a href="https://agentmods.dev/skills/lorsabyan/okf-skill/okf"><img src="https://agentmods.dev/badge/skills/lorsabyan/okf-skill/okf.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 5.1 | $0.00163 | $0.04247 |
| Opus 5 | $0.00081 | $0.02124 |
| Sonnet 5 | $0.00033 | $0.00849 |
| Haiku 4.5 | $0.00016 | $0.00425 |
Grade A, and why
okf 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.
How it starts
The opening of the file, as written. The whole thing — 360 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Open Knowledge Format (OKF)
OKF v0.2 is a vendor-neutral format for representing knowledge — the metadata,
context, and curated insight around data and systems — as plain markdown files
with YAML frontmatter, organized in a directory tree called a bundle.
No SDK, no registry, no required tooling: if you can read a file you can
consume OKF, and if you can git clone you can ship it.
The full specification is in references/SPEC.md. Read it when you need exact rules (reserved filenames, conformance, attested-computation contracts, versioning). This file covers the 90% you need for day-to-day work.
This skill targets v0.2. v0.1 bundles are still valid input — see Reading v0.1 bundles at the end.
Core model
- Bundle — a directory tree of
.mdfiles. The unit of distribution. - Concept — one markdown file describing one unit of knowledge (a table,
a metric, an API, a playbook, an idea). Its concept ID is the file path
without
.md(e.g.tables/users.md→tables/users). - Reserved filenames —
index.md(directory listing) andlog.md(change history) are never concept docs. - Links — standard markdown links between concepts express relationships; the surrounding prose conveys the relationship's meaning. Broken links are legal (they mark not-yet-written knowledge).
Concept document format
Every concept file = YAML frontmatter + markdown body:
---
type: BigQuery Table # REQUIRED — the only required field
title: Customer Orders # recommended: display name
description: One row per completed customer order. # recommended: one line
resource: https://console.cloud.google.com/bigquery?p=acme&d=sales&t=orders
tags: [sales, orders]
generated: { by: reference_agent/gemini-2.5-pro, at: 2026-07-13T00:00:00Z }
verified: { by: human:ahormati, at: 2026-07-14T09:00:00Z }
status: stable # draft | stable | deprecated
stale_after: 2026-12-31T00:00:00Z # absolute instant; stale when now >= this
sources:
- id: bq-schema
resource: https://console.cloud.google.com/bigquery?p=acme&d=sales&t=orders
title: BigQuery table schema
author: team:data-platform
last_modified: 2026-07-01T00:00:00Z
# any extra producer-defined keys are allowed
---
One row per completed customer order across web, mobile, and marketplace
channels. The grain is the order, not the line item — per-line detail lives in
[order_lines](order_lines.md). Covers 2019-01-01 onward.[^bq-schema]
# Schema
| Column | Type | Description |
|---------------|--------|-------------------------------------------------|
| `order_id` | STRING | Unique order identifier. |
| `customer_id` | STRING | FK to [customers](customers.md). |
# Common query patterns
```sql
SELECT COUNT(*) FROM `acme.sales.orders`;
```
[^bq-schema]: BigQuery table schema
What ships with it
3 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.
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.
- 8d ago First seen · 360 lines · 163 tokens per session scan A e0394020f83b
okf is a skill published in the GitHub repository lorsabyan/okf-skill (5 stars, last pushed 15d ago), licensed Apache-2.0. It adds 163 tokens to every session and 4,247 once invoked, about $0.0008 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
backfill
Reconstruct an OKF bundle by event-sourcing a repository's history (git log and Claude session transcripts). Use when creating an .okf/ bundle for an existing repository that predates this skill, or when resuming an interrupted backfill session. Triggers on: "reconstruct the OKF bundle", "backfill the knowledge…
okf
Author, maintain, and consume Open Knowledge Format (OKF) knowledge bundles — portable markdown + YAML frontmatter that both humans and agents read. Use when capturing project knowledge (services, APIs, schemas, metrics, runbooks, decisions) into an OKF bundle, when updating one after code or docs change, or when a…
validate
Check that an Open Knowledge Format (OKF) bundle is conformant with the v0.2 spec (§11). Use when asked to validate, lint, or check an OKF bundle, or before committing changes to one. Runs a deterministic Python checker — not an eyeball pass. Also migrates a v0.1 bundle to v0.2 in place with --migrate.
visualize
Render an Open Knowledge Format (OKF) bundle as a single self-contained, interactive HTML graph (viz.html) — concepts as nodes coloured by type and sized by body length, markdown links and bundle-internal sources as edges, a wiki-style detail panel with rendered markdown, v0.2 trust/lifecycle/provenance metadata, and…
okf-pro
Operating rules for the .okf/ knowledge bundle — filing new concepts, the board, the journal, the daily snapshot, closing work, source attribution, and the generated/verified attestation policy. Use before reading from or writing anything into .okf/.
okf
Be the expert on Open Knowledge Format (OKF) — portable project knowledge as a directory of markdown files with YAML frontmatter that humans and agents read from one source. Use when capturing knowledge into a bundle (a service, schema, metric, decision, runbook: "document this in OKF", "capture this as a concept")…