メニュー
Retrospectively measure §10 vocabulary and report-order violations across assistant turns. Use for per-turn compliance rates. Not for live hook hits or spec editing; read-only.
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
Diagnose an agentsmd installation (安装故障诊断): prerequisites, hook registration/executability, config flags, and spec drift. Use after install/update or when hooks fail. Not for telemetry analysis; read-only.
Show agentsmd install state (安装状态清单), registered hooks, preserved tenants, config flags, and telemetry rows. Use for a quick inventory. Not for health diagnosis or rule analysis.
Extract CSS :root and Tailwind v4 @theme tokens into DESIGN.md plus an AGENTS.md pointer. Use for frontend design-system facts. Not for coding conventions, non-frontend repos, or Tailwind v3 config themes.
Distill coding conventions from source into AGENTS.md (提炼代码约定). Use for naming/import/error-handling analysis after agentsmd-init. Not for stack detection or design tokens.
Aggregate agentsmd rule-hit telemetry by section (遥测命中统计). Use for enforcement activity and raw hit counts. Not for promotion/demotion decisions or transcript violation rates; read-only.
Generate or refresh project AGENTS.md stack facts, commands, and structure (生成项目指令). Use before convention analysis. Not for inferring coding conventions or design tokens.
| name | agentsmd-sampling-audit |
| description | Retrospectively measure §10 vocabulary and report-order violations across assistant turns. Use for per-turn compliance rates. Not for live hook hits or spec editing; read-only. |
Resolve the script root first. Set SKILL_MD to the selected SKILL.md absolute path from the live skills list; never infer it from the process cwd.
SKILL_MD="<selected SKILL.md absolute path from the live skills list>"
CANDIDATE_ROOT="$(cd "$(dirname "$SKILL_MD")/../.." && pwd)"
if [ -f "$CANDIDATE_ROOT/scripts/sampling-audit.js" ]; then AGENTSMD_ROOT="$CANDIDATE_ROOT"; else AGENTSMD_ROOT="${CODEX_HOME:-$HOME/.codex}/agentsmd"; fi
The live Stop hook (transcript-structure-scan.sh) observes the current last assistant turn whenever Stop fires, but live hit telemetry has no denominator for every assistant turn. This audit walks all recent assistant turns in ~/.codex/sessions/ and re-runs the same vocabulary/order detectors to calculate a retrospective violation rate.
Run:
node "$AGENTSMD_ROOT/scripts/sampling-audit.js" --days=30
Report turns w/ violation and transcripts affected. A rising rate informs OPERATOR.md §O2; nothing is auto-changed. --limit=N caps the scan and reports dropped older transcripts. From the repo: node scripts/sampling-audit.js.