一键导入
akf
Trust metadata for files, memories, and skills — check before you trust, stamp what you verify. A stamp costs ~15 tokens; re-verifying costs 15,000.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Trust metadata for files, memories, and skills — check before you trust, stamp what you verify. A stamp costs ~15 tokens; re-verifying costs 15,000.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | akf |
| description | Trust metadata for files, memories, and skills — check before you trust, stamp what you verify. A stamp costs ~15 tokens; re-verifying costs 15,000. |
| version | 1.6.0 |
| author | HMAKT99 |
| license | MIT |
| metadata | {"homepage":"https://akf.dev","repository":"https://github.com/HMAKT99/AKF"} |
| akf | {"v":"1.0","claims":[{"c":"Trust metadata for skills/hermes-akf/SKILL.md","t":0.7,"id":"10fa8a0b","src":"unspecified","tier":3,"ver":false,"ai":true,"decay":365,"kind":"skill","evidence":[{"type":"human_review","detail":"reviewed by @HMAKT99, full suite 1969 passed","at":"2026-07-14T13:32:22.815514+00:00"}]}],"id":"akf-c51818c7389e","agent":"claude-code","at":"2026-07-14T13:32:22.817285+00:00","label":"public","inherit":true,"ext":false,"hash":"sha256:95c4fc0282e1cb45","sv":"1.1"} |
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.
| 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).
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.akf stamp report.py --agent hermes --evidence "42/42 tests passed"--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.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.akf stamp SKILL.md --preset skill --agent <you> --evidence "reviewed by <maintainer>".Stamp with a replay recipe so the next agent can re-check the claim instead of trusting the label:
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.
akf sign adds an Ed25519 signature for the provenance part.internal; use --label public for docs/examples and --label confidential for sensitive material.akf check <file> on something you just stamped returns OK ... and exit code 0.echo x >> <file> then akf check <file> returns STALE and exit code 1 — the loop is working.akf doctor diagnoses install/PATH problems if the akf command isn't found.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.
Agent Knowledge Format — stamp trust metadata into every file AI touches. Trust scores, provenance, and compliance that embed natively into DOCX, PDF, images, and code.