メニュー
Deterministically check whether an AET proof still applies to the current workspace. Use only for an explicit /aet-fresh request.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Create a bounded, read-only investigation from normalized Codex or Claude Code Run Records, optionally inspect explicit AET Proof and Freshness records, and export a Portable Evidence Bundle for an independent reviewer.
Run a bounded AET check of Agent instructions, Skills, verification contracts, and dangerous authority. Use only when the user explicitly invokes /aet-check or asks for this AET Quick check.
Execute one explicit verification command and record a minimal hash-bound AET proof receipt. Use only when the user explicitly invokes /aet-proof or asks AET to prove a command ran.
Investigate whether an AI coding change matches the user's task and whether cross-module changes are necessary. Use only for an explicit /aet-scope request.
Compatibility entrypoint for AET Quick and advanced AET Lab workflows. Prefer the four dedicated Quick Skills for daily work; use this Skill only when the user explicitly asks for legacy CLI or Lab capabilities.
Held-out fixture with a mismatched directory name.
| name | aet-fresh |
| description | Deterministically check whether an AET proof still applies to the current workspace. Use only for an explicit /aet-fresh request. |
Answer one question: does this historical proof still apply to the current workspace?
Run:
aet quick fresh --proof <proof.json> --format json
The CLI alone compares Git HEAD, workspace state, declared relevant files, artifacts, runtime identity, and dependency lockfiles. The host LLM may explain impact and the smallest rerun, but it cannot change the deterministic state.
States are EXACT_MATCH, RELEVANT_FILES_MATCH,
HEAD_CHANGED_RELEVANT_FILES_MATCH, RELEVANT_FILES_CHANGED,
ARTIFACT_CHANGED, ENVIRONMENT_CHANGED, and UNKNOWN.
Budget: three seconds, zero LLM calls by default, zero network calls, and zero writes. An explicit explanation may use one host LLM call after the deterministic result exists.
For a Chinese /aet-fresh request, explain the result in natural Simplified
Chinese while keeping code and required technical terms in English. Otherwise
use English.
Report what changed and the minimum proof to rerun, then stop. Never rerun it automatically.