菜单
Benchmark native hook wall-clock cost with OFF/ON medians in an isolated CODEX_HOME. Use for latency or disablement decisions. Not for correctness, install health, or live telemetry.
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
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-perf-baseline |
| description | Benchmark native hook wall-clock cost with OFF/ON medians in an isolated CODEX_HOME. Use for latency or disablement decisions. Not for correctness, install health, or live telemetry. |
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/perf-baseline.js" ]; then AGENTSMD_ROOT="$CANDIDATE_ROOT"; else AGENTSMD_ROOT="${CODEX_HOME:-$HOME/.codex}/agentsmd"; fi
Turns "the hooks add ~200–400 ms" (a guess) into a measured per-hook table. For each hook it times, over N runs, the median of OFF (DISABLE_AGENTSMD_HOOKS=1 → the hook exits at its kill-switch line: bash-spawn + startup floor) vs ON (the hook does its real work); delta = ON − OFF is the hook's own logic cost.
node "$AGENTSMD_ROOT/scripts/perf-baseline.js" # all 15 hooks, 10 runs
node "$AGENTSMD_ROOT/scripts/perf-baseline.js" --event=PreToolUse # just the per-Bash-call hooks
node "$AGENTSMD_ROOT/scripts/perf-baseline.js" --runs=3 --json
latency added per event firing (sum of ON medians) is the number that matters: the 5 PreToolUse:Bash hooks fire on every Bash call; the 7 Stop hooks fire once per turn.echo Bash event (the common per-call case, not the block path), in an isolated sandbox CODEX_HOME — measuring never writes to the live ~/.codex (§8.V3) and cleans up after itself (§8.V4).bash hook spawns, not Codex's harness IPC round-trip.Operator/dev tool, read-only on the live env. From the repo instead of an install: node scripts/perf-baseline.js.