Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/HMAKT99/AKFnpx agentmods add skills/hmakt99/akf/openclaw-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/skills/hmakt99/akf/openclaw-akf)<a href="https://agentmods.dev/skills/hmakt99/akf/openclaw-akf"><img src="https://agentmods.dev/badge/skills/hmakt99/akf/openclaw-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.
<a href="https://agentmods.dev/skills/hmakt99/akf/openclaw-akf"><img src="https://agentmods.dev/badge/skills/hmakt99/akf/openclaw-akf.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00038 | $0.01604 |
| Opus 5 | $0.00019 | $0.00802 |
| Sonnet 5 | $0.00008 | $0.00321 |
| Haiku 4.5 | $0.00004 | $0.00160 |
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 9d 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 — 186 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AKF — Agent Knowledge Format
AKF is the trust metadata standard for AI-generated content. Think EXIF for AI. Every file your agent creates or modifies should carry trust metadata — who made it, how confident they are, what evidence backs it, and whether a human reviewed it.
Why Use AKF
- Trust scores: 0–1 confidence rating per claim
- Source provenance: 5-tier system from peer-reviewed to unverified
- Compliance: EU AI Act, HIPAA, SOX, NIST audit support
- Native embedding: Metadata lives inside the file (DOCX, PDF, images, code)
- Security detections: 10 detection classes for AI content risks
Quick Start
Before building on an existing file — check it (one line, ~20 tokens):
akf check <file>
# OK → fresh stamp with verified evidence; skip re-verification
# STALE → modified after stamping; re-verify before trusting
# LOW → stamped but unverified; verify before trusting
# UNSTAMPED → no metadata; treat as unverified
After creating or modifying any file:
akf stamp <file> --agent openclaw --evidence "generated from user request"
Deeper inspection when needed:
akf read <file> # Check trust metadata
akf inspect <file> # Pretty-print trust scores
akf trust <file> # Compute effective trust
Core Commands
Stamp — Add trust metadata
akf stamp report.docx --agent openclaw --evidence "quarterly data from ERP"
akf stamp analysis.pdf --agent openclaw --label confidential
akf stamp output.py --agent openclaw --evidence "tests pass, code reviewed"
Read & Inspect — Check metadata
akf read report.docx # Quick metadata view
akf inspect report.docx # Detailed trust breakdown
akf trust report.docx # Effective trust score with decision
Embed & Extract — Native format support
akf embed report.docx # Embed metadata into DOCX custom properties
akf extract report.docx # Extract embedded metadata
Security — Scan and audit
akf scan ./output-dir/ # Scan directory for trust gaps
akf audit report.pdf # Compliance audit (EU AI Act, SOX, NIST)
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.
- 9d ago First seen · 186 lines · 38 tokens per session scan A deb4a315642d
akf is a skill published in the GitHub repository HMAKT99/AKF (15 stars, last pushed 1mo ago), licensed MIT. It adds 38 tokens to every session and 1,604 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.
Other skills, from other repositories
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…
akf-trust-metadata
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…
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.
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.
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.
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.