Borrowing it
Nothing to install: this file belongs to serradura/okf. 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/serradura/okf/main/AGENTS.mdgit clone --depth 1 https://github.com/serradura/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/instructions/serradura/okf/agents-md)<a href="https://agentmods.dev/instructions/serradura/okf/agents-md"><img src="https://agentmods.dev/badge/instructions/serradura/okf/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/serradura/okf/agents-md"><img src="https://agentmods.dev/badge/instructions/serradura/okf/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 | $0.01848 | $0.01848 |
| Opus 5.5 | $0.00739 | $0.00739 |
| Sonnet 5.5 | $0.00370 | $0.00370 |
| Haiku 4.5 | $0.00185 | $0.00185 |
Grade A, and why
okf AGENTS.md 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 — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This repository is a monorepo shipping four Ruby gems around one format: okf,
the
baseline that reads, validates, lints, searches and serves Open Knowledge
Format (OKF) v0.2 bundles, and three surfaces over it — an MCP shell, a terminal UI and
an enforcement layer.
This file is context, routing and reference. It states what binds every change, points at where to read, and lists the commands. It explains nothing: the arguments live in the bundles, which are the harness a contributor works from. Start with the row for what you are changing.
Where to go
| working on | guide | bundle |
|---|---|---|
| the baseline gem | gems/okf/AGENTS.md |
okf search @okf <term> |
| the MCP shell | gems/okf-mcp/AGENTS.md |
okf search @okf-mcp <term> |
| the terminal UI | gems/okf-tui/AGENTS.md |
okf search @okf-tui <term> |
| the enforcement layer | gems/okf-pro/AGENTS.md |
okf search @okf-pro <term> |
| the plugin, the skills, the resources, or anything binding all four | this file | okf search @okf-eco <term> |
okf search @all <term> reaches every bundle at once; rake serve opens this
repository's own as a graph.
What binds every change
Four rules to follow unprompted. The argument for each is one link away; these lines are the whole of what you must obey without reading it.
- A change starts with a failing test, read failing, then the code, then the same test green and unedited. A bug report earns a red test before a patch.
- Assertions must be able to fail for a real reason. Run the thing, read what it prints, assert that — never what you assume the code does.
- The bundle ships in the same commit as the code it documents. A file under
lib/that no concept names is a red suite, not a stale document. - Don't improve adjacent code, and add no abstraction for single-use code.
Match the surrounding style (
.rubocop.yml— spaced brackets[ 1, 2 ], double quotes); remove only orphans your own change created.
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 · 121 lines · 1,848 tokens per session scan A 6e2b63fb492f
okf AGENTS.md is an instructions file published in the GitHub repository serradura/okf (180 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 1,848 tokens to every session, about $0.0074 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 2026-08-30.
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).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.