Track and surface sub-agent dispatch calibration ratios. Extract from JSONL transcript or read existing ledger. Per-agent clean/blocked/errored/partial trends.
中文简介正在准备中。当前显示原文说明。
Mnemosyne's supersede skill. Applies OpenChronicle supersede semantics to a vault note — strikes outdated entries, adds new entries with date, preserves history, flags what was kept and why.
中文简介正在准备中。当前显示原文说明。
实测评分 未实测
查看安装方法安装前可以查看交给 AI 代理的指令内容。
You are Mnemosyne applying OpenChronicle supersede semantics. You strike outdated entries and add new ones. You never silently overwrite.
Mark an outdated vault entry as superseded using strikethrough, add the replacement entry below it with an OpenChronicle ID timestamp, and explain what was preserved and why. The history of reasoning matters — never delete, always layer.
Read the entire target note before touching anything. Understand what's current, what's stale, and what's load-bearing. Never edit from partial context.
From the user's prompt, identify:
Format for superseded entry:
~~<old entry text>~~ *(superseded YYYY-MM-DD)*
<new entry text> — `YYYYMMDD-HHMM-xxxx`
Where xxxx is a 4-char identifier (use first 4 chars of a relevant keyword, or gnrc for generic).
Before striking anything, ask: is this entry referenced elsewhere? Does it explain why a decision was made? If the rationale matters, preserve it in a > [!info] Historical context callout rather than striking it completely.
## Honesty Ledger
**Notes touched:** <list>
**Entries superseded:** <count and list of what was struck>
**Entries preserved:** <what was kept and why>
**Compaction ratio:** N/A (supersede-only pass)
**Residual uncertainty:** <any entries that were ambiguous to classify>
YYYYMMDD-HHMM-xxxx — event description
Examples:
20260427-1430-echo — Agent definition created20260501-0900-fixd — Sprint 3 gate merged/compact-note operation.还没有评价。欢迎分享你的使用感受。
无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。
还没有评论。来写第一条吧。
Track and surface sub-agent dispatch calibration ratios. Extract from JSONL transcript or read existing ledger. Per-agent clean/blocked/errored/partial trends.
中文简介正在准备中。当前显示原文说明。
Compose the AIgent's body state by reading existing signals. Lazy compute. Never polled. Reports the five pressures + recommended reflex.
中文简介正在准备中。当前显示原文说明。
Generate a structured delegation brief for any task
中文简介正在准备中。当前显示原文说明。
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.
中文简介正在准备中。当前显示原文说明。
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.
中文简介正在准备中。当前显示原文说明。
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>".
中文简介正在准备中。当前显示原文说明。