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/hmakt99/akf/agents-mdgit clone --depth 1 https://github.com/HMAKT99/AKFWrote 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/hmakt99/akf/agents-md)<a href="https://agentmods.dev/instructions/hmakt99/akf/agents-md"><img src="https://agentmods.dev/badge/instructions/hmakt99/akf/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 | $0.00335 | $0.00335 |
| Opus 5 | $0.00168 | $0.00168 |
| Sonnet 5 | $0.00067 | $0.00067 |
| Haiku 4.5 | $0.00034 | $0.00034 |
Grade A, and why
AKF 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 4d 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.
This is a copy
100% identical to AKF copilot-instructions.md — 4 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
AKF — Agent Knowledge Format
AKF is the trust metadata standard for AI-generated content. When you create or modify files, stamp them with trust metadata so every output carries provenance.
Rules
After creating or modifying files
akf stamp <file> --agent codex --evidence "<evidence>"
Evidence examples: "tests pass", "docs reviewed", "refactored from existing code", "generated from spec"
After completing a task with commits
akf stamp <file> --agent codex --evidence "<summary of evidence>"
When working with existing AKF-stamped files
akf read <file> # Check existing trust metadata before modifying
akf inspect <file> # See detailed trust scores
Classification
- Use
--label confidentialfor files in*/finance/*,*/secret/*,*/internal/* - Use
--label publicfor README, docs, examples - Default is
internal
Key Commands
akf stamp <file>— Add trust metadata to any fileakf read <file>— Read trust metadata from any fileakf inspect <file>— Pretty-print trust scoresakf embed <file>— Embed metadata into DOCX/PDF/imagesakf scan <dir>— Security scan a directoryakf audit <file>— Compliance audit (EU AI Act, SOX, NIST)akf trust <file>— Compute effective trust scores
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.
- 4d ago First seen · 37 lines · 335 tokens per session scan A 12bda9054b65
AKF AGENTS.md is an instructions file published in the GitHub repository HMAKT99/AKF (15 stars, last pushed 1mo ago), licensed MIT. It adds 335 tokens to every session, about $0.0017 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to AKF copilot-instructions.md, differing in 4 lines, and is treated as a copy.
Other instructions, from other repositories
EverOS CLAUDE.md
Claude Code instructions for EverMind-AI/EverOS, covering everos — md-first memory extraction framework, quick commands, architecture, engineering practices and branch strategy.
honcho CLAUDE.md
Claude Code instructions for plastic-labs/honcho, covering claude.md, honcho overview, what is honcho?, core concepts and peer paradigm.
pi-extensions CLAUDE.md
Claude Code instructions for MattDevy/pi-extensions, covering claude.md, commands, architecture, data flow and key modules.
basic-memory CLAUDE.md
Claude Code instructions for basicmachines-co/basic-memory, a project described as: AI conversations that actually remember. Never re-explain your project to your AI again. Join our Discord: https://discord.gg/tyvKNccgqN.
Kompl 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.
brainlayer AGENTS.md
Instructions for EtanHey/brainlayer, covering brainlayer — a letter from etan, brainlayer agent notes (operational), review guidelines, key paths and database.