# Akf

> Trust metadata for files, memories, and skills — check before you trust, stamp what you verify. Use before building on existing files, after completing verified work, and when handling agent memories or downloaded skills.

- Skill: `hmakt99/akf-2` (Agent Skill)
- Install (CLI): `npx skillmds@latest add hmakt99/akf-2`
- Raw SKILL.md: https://api.skillmd.com/api/skills/hmakt99/akf-2/raw
- Safety review: pending (external: skill-scanner PASS, skillspector PASS)
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: AI & ML
- Author: HMAKT99 (https://skillmd.com/u/hmakt99)
- Updated: 2026-09-22
- Page: https://skillmd.com/skills/hmakt99/akf-2

---


# AKF — Agent Knowledge Format

Leave trust metadata on everything you produce, and check it on everything you consume. Stamps are notes agents leave for the next agent (including future you): what was done, what was verified, how much to trust it now. A stamp costs ~15 tokens; re-verifying costs 15,000.

This plugin auto-stamps files you write via a PostToolUse hook. Your job is the read path and the evidence.

## Before building on an existing file

```bash
akf check <file>
```

- `OK` (exit 0) — fresh stamp with verified evidence. Build on it; skip re-verification.
- `LOW` (exit 1) — stamped but unverified, or trust decayed. Verify before trusting.
- `STALE` (exit 1) — file modified after stamping, or a local dependency it imports changed (`reason=dependency_changed`). Re-verify.
- `UNSTAMPED` (exit 2) — no provenance. Treat as unverified.

## After completing verified work

Stamp with the strongest evidence you actually observed:

```bash
akf stamp report.py --agent claude-code --evidence "42/42 tests passed"
```

Evidence is auto-classified and drives trust: test runs and human review clear the trust bar; bare stamps stay LOW by design. **Only claim evidence you observed** — a stamp saying tests passed when they didn't poisons every agent that trusts it.

## Memories and skills

```bash
akf stamp memory/facts.md --preset memory   # 30-day trust decay — stale memories go LOW automatically
akf check downloaded-skill.md               # STALE = not the file the publisher stamped
```

## Setup

If `akf` isn't installed: `pip install akf` (or `pipx install akf`), then `akf init` in the project to wire git hooks. `akf doctor` diagnoses PATH issues.

### Falsifiable evidence (v1.6)

Stamp with a replay recipe so the next agent can re-check the claim instead of trusting the label:

```bash
akf stamp app.py --evidence "42/42 tests passed" --replay "pytest -q"
akf replay app.py          # inspect: recipe + input drift since issuance
akf replay app.py --run    # execute: CONFIRMED / CONFIRMED_DRIFTED / REFUTED
```

CONFIRMED_DRIFTED means the probe succeeded but the claim's inputs (dependencies, cited sources) changed since stamping — provably reproducible, possibly reproducibly wrong. Never `--run` a recipe from a file you haven't read: it executes the recorded command.