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 agentmods add instructions/roncodes88/okf-agents/agents-mdgit clone --depth 1 https://github.com/RonCodes88/okf-agentsWhat 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 | $0.01350 | $0.01350 |
| Opus 5 | $0.00675 | $0.00675 |
| Sonnet 5 | $0.00270 | $0.00270 |
| Haiku 4.5 | $0.00135 | $0.00135 |
Grade A, and why
okf-agents 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 2d 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 — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — okf-agents
This file is for AI coding agents (Cursor, Claude Code, Codex, Copilot,
etc.) that are writing code using the okf-agents library. Follow these
instructions exactly.
What this library does
okf-agents connects OKF (Open Knowledge Format) Markdown bundles to
LangGraph/LangChain. An OKF bundle is a directory of .md files with
YAML frontmatter. This library parses them, builds a link graph, and
exposes typed LangChain tools, retrievers, a router, and a navigator
subgraph.
Install
pip install okf-agents
Public exports
Everything is importable from the top-level package:
from okf_agents import (
OKFBundle,
Concept, ConceptFrontmatter, LinkEdge, BundleIndex, SyncResult,
create_okf_tools,
OKFRetriever, OKFGraphRetriever,
create_okf_router,
create_okf_navigator,
sync_bundle_to_vector_store,
OKFError, BundleNotFoundError, BundleValidationError,
ConceptNotFoundError, LinkResolutionError, # LinkResolutionError is deprecated, never raised
)
Do NOT import from submodules like okf_agents.bundle or
okf_agents.models. Always import from okf_agents.
create_okf_tools, create_okf_router, create_okf_navigator,
OKFRetriever, and OKFGraphRetriever all validate their bundle
argument eagerly and raise immediately (TypeError, or
pydantic.ValidationError for the two retrievers) if it is not an
OKFBundle — they never wait until first use to fail.
Patterns
Pattern 1: Load a bundle
from okf_agents import OKFBundle
bundle = OKFBundle.load("path/to/bundle")
concept = bundle.get("concepts/orders")
results = bundle.search("customer", top_k=5)
OKFBundle.load() takes a str | Path. It eagerly parses all .md
files on init. The bundle is immutable after loading.
Pattern 2: Create agent tools
from okf_agents import OKFBundle, create_okf_tools
bundle = OKFBundle.load("path/to/bundle")
tools = create_okf_tools(bundle)
# Returns 4 tools: read_concept, search_concepts, list_links, read_index
# Pass `tools` to any LangChain/LangGraph tool-calling agent.
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.
- 2d ago First seen · 167 lines · 1,350 tokens per session scan A a0d885ff9d47
okf-agents AGENTS.md is an instructions file published in the GitHub repository RonCodes88/okf-agents (5 stars, last pushed 1mo ago), licensed MIT. It adds 1,350 tokens to every session, about $0.0068 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 instructions, from other repositories
haive CLAUDE.md
Instructions for pr1m8/haive, covering claude.md - haive agent framework, project context, guides & documentation, agent design (new — 2026-04-06) and architecture.
deepagents AGENTS.md
AGENTS.md instructions for langchain-ai/deepagents, covering global development guidelines for the deep agents monorepo, corridor security analysis, development workflow, suppressing ruff rules and pr conventions.
obsidian-llm-wiki AGENTS.md
Instructions for green-dalii/obsidian-llm-wiki, covering llm wiki plugin project development standards, 🛡️ six-gate quality closure, gate 1: five-gate automated, gate 2: no side effects and gate 3: no breaking changes.
dawnai AGENTS.md
Instructions for cacheplane/dawnai, covering agents.md, what this is (and isn't), workspace map, definition of done and conventions.
raytsystem-public-os AGENTS.md
Instructions for romarayt/raytsystem-public-os, covering raytsystem — agent routing, invariants, commands, skill routing and documentation.
TradingAgents-Telegram CLAUDE.md
Instructions for IvanWng97/TradingAgents-Telegram, covering tradingagents-telegram — architecture reference, layout, architecture (for code reviewers), request lifecycle (manual /watch tap) and state ownership.