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/pumblus/okf-harness/agents-mdgit clone --depth 1 https://github.com/pumblus/okf-harnessWrote 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/pumblus/okf-harness/agents-md)<a href="https://agentmods.dev/instructions/pumblus/okf-harness/agents-md"><img src="https://agentmods.dev/badge/instructions/pumblus/okf-harness/agents-md.svg" alt="Measured on agentmods" 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 | $0.00377 | $0.00377 |
| Opus 5 | $0.00188 | $0.00188 |
| Sonnet 5 | $0.00075 | $0.00075 |
| Haiku 4.5 | $0.00038 | $0.00038 |
Grade A, and why
okf-harness 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 6d 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.
What it actually says
OKF Harness
An agent-first, local-first, terminal-native harness for maintaining OKF-compatible LLM Wikis through coding agents. The unified agent entrypoint is okf-harness; the CLI alias is okfh.
Toolchain
- pnpm 11 (not npm), Node >= 22. Scripts:
pnpm -w run test,pnpm -w run typecheck,pnpm -w run lint,pnpm -w run build(-wtargets the workspace root from any directory). Lint is Biome plus the llms docs freshness check. - Layering rule:
packages/coreimports nothing from other packages;packages/cliis the bridge between core and agent-pack.
Repo layout
packages/core— harness logic;packages/cli—okfhcommand surface,--jsoneverywhere;packages/agent-pack— agent guidance renderers and skill templates;packages/setup— universal setup;packages/native-integration— host installers.skills/okf-harness— the unified host entrypoint skill.examples/— dogfood workspaces whoseraw/sources/are immutable fixtures.docs/,site/,CONTEXT.md— product docs, website sources, glossary.
Read before you act
- Before finishing a change: run the verify loop.
- Before writing user-facing text, running or documenting
okfhcommands, or changing cross-package behavior: read read-before-write. - Before opening a PR: read CONTRIBUTING.md and follow the guardrails.
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.
- 6d ago First seen · 22 lines · 377 tokens per session scan A 3104a8f8cf81
okf-harness AGENTS.md is an instructions file published in the GitHub repository pumblus/okf-harness (34 stars, last pushed 22d ago), licensed Apache-2.0. It adds 377 tokens to every session, about $0.0019 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 2026-08-30.
Other instructions, from other repositories
obsidian-llm-wiki AGENTS.md
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.
Kompl AGENTS.md
AGENTS.md instructions for tuirk/Kompl, covering agents.md — kompl operator guide, what is kompl?, agent rules — wiki safety (read before any docker command), never without explicit user confirmation and if a destructive action is going to happen anyway.
wenlan AGENTS.md
AGENTS.md instructions for 7xuanlu/wenlan, covering agents.md, start here, build and verification, repository invariants and git and release.
wenlan CLAUDE.md
Claude Code instructions for 7xuanlu/wenlan, a project described as: Wenlan is a knowledge base for the AI-native age. Your AI agents capture what they learn, Wenlan keeps it current and distills it into source-cited wiki pages you can trust.
Khaos-Brain AGENTS.md
Instructions for liuyingxuvka/Khaos-Brain, covering repository expectations, bootstrap, start here, purpose and github publish default.
llm-brain CLAUDE.md
Instructions for kimsanguine/llm-brain, covering llm-brain — claude code 운영 지침, 가드레일 (절대 위반 금지), 프라이버시 경계 (agent memory os), 명령어 and ingest.