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/rhtevan/agentfsnpx agentmods add skills/rhtevan/agentfs/okf-bundle-setupWrote 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/rhtevan/agentfs/okf-bundle-setup)<a href="https://agentmods.dev/skills/rhtevan/agentfs/okf-bundle-setup"><img src="https://agentmods.dev/badge/skills/rhtevan/agentfs/okf-bundle-setup/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/rhtevan/agentfs/okf-bundle-setup"><img src="https://agentmods.dev/badge/skills/rhtevan/agentfs/okf-bundle-setup.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00019 | $0.05155 |
| Opus 5.5 | $0.00008 | $0.02062 |
| Sonnet 5.5 | $0.00004 | $0.01031 |
| Haiku 4.5 | $0.00002 | $0.00515 |
Grade A, and why
okf-bundle-setup 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.
How it starts
The opening of the file, as written. The whole thing — 509 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OKF Bundle Setup
Scope guard: This skill is not available in LITE scope projects. LITE scope does not support skills or knowledge bundles. If the target project's AGENTS.md contains
agentfs-scope: lite, refuse with a clear message.
Create, organize, or update a directory as an Open Knowledge Format (OKF) v0.1 knowledge bundle.
For the full OKF specification, see references/okf-spec-summary.md.
Prerequisites
- bash available (for scaffolding / scanning scripts)
- Write access to the target directory
Inputs
The skill accepts an optional bundle path argument:
| Input | Example | Behaviour |
|---|---|---|
| (none) | "set up an okf bundle" |
Use ~/.agents/knowledge/ as the bundle root |
| Explicit path | "create an okf bundle at docs/data-catalog" |
Use the given path as the bundle root |
Procedure
Execute these phases in order. Each phase references a helper script or gives inline agent instructions.
Naming Convention — lowercase kebab-case
All bundle and sub-bundle directory names MUST follow
lowercase kebab-case (this-style):
- Only lowercase letters (
a-z), digits (0-9), and hyphens (-) - No underscores, spaces, uppercase, or special characters
- Maximum 25 characters
- Must not start or end with a hyphen
Examples:
- ✅
rca-labeled-dataset,sales-data,ml-training-configs - ❌
rca_labeled_dataset(underscores),RCA-Data(uppercase),my data(spaces)
When the input directory name violates this convention, the agent
must rename it to conform (e.g., rca_labeled_dataset →
rca-labeled-dataset). The normalization rule is:
lowercase → replace _ and spaces with - → strip non-alphanumeric
except - → collapse consecutive hyphens → trim leading/trailing
hyphens → truncate to 25 chars.
Reserved directory names (assets, scripts, etc.) are exempt from
the length limit but must still be lowercase kebab-case (they already
are by definition).
What ships with it
5 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.
- 1mo ago First seen · 509 lines · 19 tokens per session scan A 5e3f2d18d273
okf-bundle-setup is a skill published in the GitHub repository rhtevan/agentfs (2 stars, last pushed yesterday), licensed Apache-2.0. It adds 19 tokens to every session and 5,155 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
apify-youtube-transcript-scraper
Get YouTube captions, timestamped quotations, SRT/VTT and translated transcripts for videos, channels and playlists through the harshmaur/youtube-transcript-scraper Apify Actor.
legal-hold
Issue, refresh, release, or report on legal holds — drafts the hold notice as .docx, updates legalhold fields in log.yaml, and calendars the next refresh. Use when the user says "issue a hold", "refresh hold", "release hold", or asks for a portfolio-wide hold status report.
baoyu-youtube-transcript
A tool for downloading the written captions, subtitles, chapter information, speaker labels, and cover image from a YouTube video using its URL or ID.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.