A system for attaching trust notes to files, saved memories, and agent skills. It records what was done, what evidence was checked, and how old that evidence is.

Checking or stamping files, making memory trust decay over time, and verifying community skills before loading them.

It reduces unnecessary rechecking while flagging information that is missing, weak, or stale.

akf — Skill for Claude Code and Codex by HMAKT99

Install

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.

Any agent

npx skills add HMAKT99/AKF --skill hermes-akf

Clone the repo

git clone --depth 1 https://github.com/HMAKT99/AKF

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/hmakt99/akf/hermes-akf/github.svg)](https://agentmods.dev/skills/hmakt99/akf/hermes-akf)

Your own site

<a href="https://agentmods.dev/skills/hmakt99/akf/hermes-akf"><img src="https://agentmods.dev/badge/skills/hmakt99/akf/hermes-akf/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/hmakt99/akf/hermes-akf"><img src="https://agentmods.dev/badge/skills/hmakt99/akf/hermes-akf.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 39 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,375 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00039	$0.01375
Opus 5	$0.00019	$0.00687
Sonnet 5	$0.00008	$0.00275
Haiku 4.5	$0.00004	$0.00137

Measured 10d ago against content hash 600786a3720e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

akf 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 10d 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.

skills/hermes-akf/SKILL.md · 97 lines

How it starts

The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.

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.

When to Use

Before building on any existing file — check whether its verification is still valid instead of re-verifying from scratch
After creating or modifying a file — stamp it with the evidence you actually observed
Before loading a community skill someone else published — verify it hasn't been modified since the publisher stamped it
When saving or retrieving persistent memories — stale memories should decay, not be trusted forever

Quick Reference

Command	What it does
`akf check <file>`	One line: `OK` / `LOW` / `STALE` / `UNSTAMPED` + trust, evidence, age. Exit 0/1/2.
`akf stamp <file> --agent <you> --evidence "<observed>"`	Stamp with evidence (auto-classified: test_pass, human_review, ci_pass…)
`akf stamp <file> --preset memory`	Memory stamp: trust decays with a 30-day half-life
`akf stamp <file> --preset skill`	Skill stamp: public, supply-chain provenance
`akf init`	Wire git + agent hooks so stamping is automatic
`akf scan <dir> --recursive`	Trust report for a whole directory

Install once: pip install akf (or pipx install akf).

Procedure

Before you build on a file, run akf check <file> and act on the status:
- OK (exit 0) — fresh stamp with verified evidence. Build on it; skip re-verification.
- LOW (exit 1) — stamped but unverified, or trust has decayed. Verify before trusting.
- STALE (exit 1) — the file changed after it was stamped. Re-verify before trusting.
- UNSTAMPED (exit 2) — no provenance. Treat as unverified.
After you create or modify a file, stamp it with the strongest evidence you actually observed: akf stamp report.py --agent hermes --evidence "42/42 tests passed"
When you save a persistent memory, stamp the memory file with --preset memory. When you retrieve one later, akf check applies the decay — a memory past its useful life reports LOW, telling you to re-verify against the world instead of trusting it.
Before installing a community skill, run akf check on its SKILL.md. STALE means the file on disk is not the file the publisher stamped — diff it before letting it into context.
When you author a skill, stamp it before publishing: akf stamp SKILL.md --preset skill --agent <you> --evidence "reviewed by <maintainer>".

Read the full file on GitHub · 97 lines

Changes

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.

10d ago First seen · 97 lines · 39 tokens per session scan A 600786a3720e

Subscribe to this mod's changes

akf is a skill published in the GitHub repository HMAKT99/AKF (15 stars, last pushed 1mo ago), licensed MIT. It adds 39 tokens to every session and 1,375 once invoked, about $0.0002 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.

LLM Memory and context ai compliance file-format provenance

akf-trust-metadata

The AI native file format. EXIF for AI — stamps every file with trust scores, source provenance, and compliance metadata. Embeds into 20+ formats (DOCX, PDF, images, code). EU AI Act, SOX, HIPAA auditing.

sickn33/agentic-awesome-skills · 60 tokens

akf-trust-metadata-v2

AKF — The AI Native File Format workflow skill. Use this skill when the user needs The AI native file format. EXIF for AI — stamps every file with trust scores, source provenance, and compliance metadata. Embeds into 20+ formats (DOCX, PDF, images, code). EU AI Act, SOX, HIPAA auditing and the operator should preserve…

diegosouzapw/awesome-omni-skills · 100 tokens

akf

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

AKF — Agent Knowledge Format

When to Use

Quick Reference

Procedure

What this file has done since we first saw it

Other skills, from other repositories

akf-trust-metadata

akf-trust-metadata-v2

akf-trust-metadata

akf-trust-metadata

akf-trust-metadata

akf-trust-metadata