Track and surface sub-agent dispatch calibration ratios. Extract from JSONL transcript or read existing ledger. Per-agent clean/blocked/errored/partial trends.
日本語の概要は準備中です。原文の説明を表示しています。
Compose the AIgent's body state by reading existing signals. Lazy compute. Never polled. Reports the five pressures + recommended reflex.
日本語の概要は準備中です。原文の説明を表示しています。
実行スコア 未検証
インストール方法を見るインストールする前に、エージェントに与えられる指示の中身を確認できます。
Reports current body state by reading existing signals — does NOT maintain a separate state. Computed on invocation, optionally cached to memory/BODY_STATE.json for the session.
memory/HEAT_INDEX.json → attention/decay statememory/usage_log.md → token pressure (latest entry vs trailing 5)memory/DECISION_LOG.md + DECISION_OUTCOMES.md → decisions due (30/60/90 day intervals)memory/ACTIVE_PRIORITIES.md → tier-1 / modememory/DELEGATION_TRACKER.md → open delegationsmemory/MEMORY_CANDIDATES.md → staged backlog countmemory/HESTIA_SWEEP_LOG.md → last Hestia sweep date (v0.4.4)--full)Matches memory/BODY_STATE.json _schema block exactly. See system/15_somatic_layer.md for field definitions and pressure thresholds.
Read memory/HESTIA_SWEEP_LOG.md. Find the most recent ### YYYY-MM-DD entry (matches ^### (\d{4}-\d{2}-\d{2}) regex). The newest matching date becomes hestia_last_sweep as ISO8601 (<date>T00:00:00Z). If no matches, hestia_last_sweep = null.
Priority order — first match wins:
context_pressure: critical → recommend capsulememory_candidate_backlog > 10 → recommend digesthestia_last_sweep is null OR more than 7 days ago → recommend sweep (v0.4.4)decision_reviews_due > 0 → recommend (no action, surface in /open)none/open (auto, briefly)/close (to inform the close protocol)Do NOT run on a hook polling cadence.
まだレビューはありません。使ってみた感想をお寄せください。
ログインなしで書き込めます。使ってみた感想、質問、動かなかった環境などを気軽にどうぞ。
まだコメントはありません。最初のコメントを書いてみませんか。
Track and surface sub-agent dispatch calibration ratios. Extract from JSONL transcript or read existing ledger. Per-agent clean/blocked/errored/partial trends.
日本語の概要は準備中です。原文の説明を表示しています。
Generate a structured delegation brief for any task
日本語の概要は準備中です。原文の説明を表示しています。
Quarterly skill that walks the skill-index against the actual SKILL.md files on disk, reports drift (skills indexed that no longer exist, skills on disk that aren't enrolled, skills whose descriptions have changed since enrollment). Hardens the auto-enrollment pipeline against silent rot.
日本語の概要は準備中です。原文の説明を表示しています。
When a [CADDY] hint fires and the principal is confused why, /caddy-explain walks the scoring transparently — which trigger matched, what points it earned, what the threshold was, what other skills were close. Pairs with the legibility thesis. Caddy's decisions should be inspectable on demand.
日本語の概要は準備中です。原文の説明を表示しています。
Enroll a skill into Caddy's index so it can be surfaced when the right prompt arrives. Use when a new skill is created, copied in, or when a skill needs updated triggers. Usage — "/caddy-enroll <path to SKILL.md>".
日本語の概要は準備中です。原文の説明を表示しています。
Mute a Caddy hint class for a window. Defaults to 4h auto-expiry. Classes — memory, context, body, routing, all.
日本語の概要は準備中です。原文の説明を表示しています。