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 skills add mindroom-ai/mindroom --skill open-knowledge-formatgit clone --depth 1 https://github.com/mindroom-ai/mindroomWrote 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/mindroom-ai/mindroom/open-knowledge-format)<a href="https://agentmods.dev/skills/mindroom-ai/mindroom/open-knowledge-format"><img src="https://agentmods.dev/badge/skills/mindroom-ai/mindroom/open-knowledge-format/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/mindroom-ai/mindroom/open-knowledge-format"><img src="https://agentmods.dev/badge/skills/mindroom-ai/mindroom/open-knowledge-format.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 | $0.00040 | $0.01037 |
| Opus 5.5 | $0.00016 | $0.00415 |
| Sonnet 5.5 | $0.00008 | $0.00207 |
| Haiku 4.5 | $0.00004 | $0.00104 |
Grade A, and why
open-knowledge-format 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 10d 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Open Knowledge Format (OKF)
An OKF v0.2 bundle is a folder of markdown concept files.
Each concept starts with YAML frontmatter, and type is its only required field.
index.md files list a folder's concepts and log.md records changes; neither is a concept.
Links that start with / resolve from the bundle root, such as /playbooks/deploy.md; other links resolve from the file that contains them.
Reading
- Start at the bundle root
index.mdand follow indexes and links to the concepts you need. - Tell the user what the frontmatter says about each concept you rely on:
| Field | Meaning |
|---|---|
status: deprecated |
No longer current; find its replacement. |
status: draft |
Not reviewed; may be incomplete. |
stale_after before now |
Stale; ask a person to re-confirm. |
no verified |
Unverified. |
verified only by non-human: actors |
Machine-confirmed; not human-reviewed. |
verified by a human: actor |
Human-reviewed; name who and when. |
generated.at after the newest verified time |
Changed since it was last verified. |
- Cite concept paths in your answer.
- For
type: Attested Computation, use its# Computationblock, or the file itscomputationkey names, exactly as written, and supply only values for its declaredparameters.
Writing
New concepts get this frontmatter shape; when you edit a concept, keep all its existing keys and values and change only what the edit requires:
---
type: Playbook # required; keep the existing type when editing
title: "Payments: rotate the signing key"
description: "One sentence, reused in index.md."
tags: [payments, security]
generated: { by: "@analyst:example.org/gpt-6-luna", at: 2026-10-03T18:30:00-07:00 }
status: stable # stable, draft, or deprecated; no other values
sources:
- id: ops-412
resource: OPS-412 # required in every source: URL, bundle path, ticket, or "chat with @alice:example.org"
title: "Ticket OPS-412: key rotation"
author: human:@alice:example.org
---
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.
- 10d ago First seen · 66 lines · 40 tokens per session scan A a02a513feec9
open-knowledge-format is a skill published in the GitHub repository mindroom-ai/mindroom (335 stars, last pushed today), licensed Apache-2.0. It adds 40 tokens to every session and 1,037 once invoked, about $0.0002 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 2026-10-06.
Other skills, from other repositories
csv-tools
Parse and analyze CSV data.
xlsx-workbooks
XLSX workbook work. Load for XLSX, Excel workbook, or spreadsheet deliverable.
pdf-documents
Create a PDF deliverable or split, merge, and rotate pages. Not for reading; read returns PDF text with page markers.
word-documents
Create or edit a DOCX deliverable. Not for reading; read returns DOC and DOCX text.
ocr
A decision guide for choosing between OCR, which reads text from an image, and visual description, which explains what a scene or object shows. It also covers cases where both kinds of understanding are needed.
legal-document-comparison
Compare versions or related legal documents and agreements. Load after document-review. Do not use for one-document review, broad diligence, or a matter chronology.