Borrowing it
Nothing to install: this file belongs to saschb2b/okf-studio. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/saschb2b/okf-studio/main/AGENTS.mdgit clone --depth 1 https://github.com/saschb2b/okf-studioWrote 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/instructions/saschb2b/okf-studio/agents-md)<a href="https://agentmods.dev/instructions/saschb2b/okf-studio/agents-md"><img src="https://agentmods.dev/badge/instructions/saschb2b/okf-studio/agents-md/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/instructions/saschb2b/okf-studio/agents-md"><img src="https://agentmods.dev/badge/instructions/saschb2b/okf-studio/agents-md.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 | $0.05820 | $0.05820 |
| Opus 5.5 | $0.02328 | $0.02328 |
| Sonnet 5.5 | $0.01164 | $0.01164 |
| Haiku 4.5 | $0.00582 | $0.00582 |
Grade D, and why
okf-studio AGENTS.md scanned grade D with 2 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 3d 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.
Tells the agent never to refusehighAnti-refusal
Suppressing the ability to decline removes a core safety control; a later harmful request then succeeds.
- **Tolerant consumer:** never refuse a bundle for soft issues (missing fields, unknown `type`, broken links, missing `index.md`); surface them via [Validation](docs/features/validation.md) instead. Enumerates other installed skillsmediumAgent snooping
Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.
- **Gate it separately:** `pnpm --dir site build` (it deploys via the [Pages workflow](.github/workflows/pages.yml), not the app CI). The bundle's own conformance check, `node .claude/skills/odsf/odsf-validate.mjs design How it starts
The opening of the file, as written. The whole thing — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OKF Studio
A cross-platform desktop workspace (Windows + Ubuntu, macOS for free) that autodetects OKF bundles, renders their connected concepts as a graph and reader, and lets the user connect an external ACP agent or Studio Agent to create, curate, and query knowledge through explicit context and reviewed writes. Built with Tauri 2.0 — a Rust core plus the system webview.
How it's put together
The Rust core (crates/okf-core + src-tauri/) owns filesystem, process, and network mediation: it scans a folder for bundles, parses concepts/links/backlinks, validates, watches for changes, and hosts explicit agent connections. Its typed command/event surface hands the React 19 + TypeScript frontend (src/, Vite, React Compiler enabled — no manual memoization) ready-to-render state. The frontend combines the graph, concept reader, search, navigation, and Agent Panel. Folder opening remains read-only; agent processes and network actions start only after explicit user actions.
okf-studio/
src/ # web frontend (React 19 + TS, Vite) — domain-first: features/ + shared/
src-tauri/ # Tauri shell: tauri.conf.json, capabilities/, commands
crates/okf-core/ # Rust parsing/validation core (unit-tested against docs/)
docs/ # the OKF product spec bundle — source of truth AND built-in sample
design-system/ # ODSF bundle: the marketing site's visual language
site/ # marketing/landing page (Astro) — see site/README.md
scripts/ # okf-validate.mjs (vendored conformance checker), gen-icon.mjs
The spec in docs/ is the source of truth. Read it before changing behavior, and keep it in sync when you do. Start at docs/index.md:
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.
- 3d ago First seen · 182 lines · 5,820 tokens per session scan D a24273fe5237
okf-studio AGENTS.md is an instructions file published in the GitHub repository saschb2b/okf-studio (47 stars, last pushed yesterday), licensed MIT. It adds 5,820 tokens to every session, about $0.0233 per session on Opus 5.5. A static security scan graded it D with 2 findings (tells the agent never to refuse, enumerates other installed skills). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-23.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.