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/hamakyo/okf-skills/agents-mdgit clone --depth 1 https://github.com/hamakyo/okf-skillsWrote 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/hamakyo/okf-skills/agents-md)<a href="https://agentmods.dev/instructions/hamakyo/okf-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/hamakyo/okf-skills/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 | $0.00470 | $0.00470 |
| Opus 5 | $0.00235 | $0.00235 |
| Sonnet 5 | $0.00094 | $0.00094 |
| Haiku 4.5 | $0.00047 | $0.00047 |
Grade A, and why
okf-skills 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 5d 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 — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codex Instructions
This repository is a public template collection for Codex and Claude Code users who want reusable Skills and OKF project knowledge.
Before You Work
- Read README.md first.
- Read the relevant document under docs/ for the requested task.
- If the task uses a Skill, read the matching
skills/*/SKILL.mdbefore making changes. - If the task touches OKF, read okf/index.md and okf/log.md before editing.
Skill Rules
- Keep reusable workflow instructions in
skills/*/SKILL.md. - Keep project facts, architecture, domain concepts, data contracts, and playbooks in
okf/. - When changing a Skill, update related docs and examples if the usage or behavior changes.
- Use the Skill frontmatter description to make trigger conditions explicit.
OKF Rules
- Treat OKF as project knowledge, not as a task checklist.
- Treat
okf/index.mdas the router and load only relevant concepts for the task. - Read
okf/log.mdwhen history is relevant or before editing OKF, not for every task. - Reserved files are
index.mdandlog.md. - Non-reserved OKF Markdown concept files must include YAML frontmatter with a non-empty
type. - Follow OKF v0.2 metadata semantics and the repository's software-project profile.
- When changing OKF structure, confirm that
okf/index.mdandokf/log.mdstill describe the bundle accurately.
Editing Rules
- Preserve the existing structure unless a small, clear improvement is needed.
- Prefer small, reviewable diffs.
- Use relative Markdown links inside this repository.
- Do not add secrets, API keys, tokens, private URLs, or personal data.
- Do not mix Codex-only guidance into
CLAUDE.mdunless it also applies to Claude Code. - Do not mix Claude Code-only guidance into
AGENTS.mdunless it also applies to Codex.
Final Response
In the final response, include:
- What changed.
- Which files were added or updated.
- What validation was run.
- Any remaining release or human-review tasks.
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.
- 5d ago First seen · 46 lines · 470 tokens per session scan A cb5d8e23fb4c
okf-skills AGENTS.md is an instructions file published in the GitHub repository hamakyo/okf-skills (2 stars, last pushed 15d ago), licensed MIT. It adds 470 tokens to every session, about $0.0024 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
core copilot-instructions.md
Copilot instructions for asdecided/core: These decisions are already accepted. Do not re-open or contradict them; ask the AsDecided MCP tools (getartifact, searchartifacts) for the full text before proposing a change that touches one.
docs AGENTS.md
AGENTS.md instructions for argos-ci/docs, covering agents.md, always use the documentation skills and keep the table of contents in sync.
AmbyKit CLAUDE.md
Claude Code instructions for ambystechcom/AmbyKit, covering claude code — notes for the ambykit repo and claude-specific.
living-manual CLAUDE.md
Instructions for dougstanford/living-manual, covering living-manual, start of every session, how work lands — non-negotiable, user's manual (living-manual) and releasing.
lumen AGENTS.md
AGENTS.md instructions for ory/lumen, covering agents.md, repository expectations and commands.
sourcebook CLAUDE.md
Instructions for BackendGameSetMatch/sourcebook, covering ai documentation, when to consult docs, how to access, keep docs alive and hard rules from conventions.