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。
wrg32786/aigent-os252026年10月29日 更新
免费在 GitHub 公开
sweep-now
Run the three read-mostly vault sweeps for stale tracker items, dormant-note candidates, and broken wikilinks, then append one dated result to SWEEP_LOG.md.
中文简介正在准备中。当前显示原文说明。
wrg32786/aigent-os星标 25(GitHub 25 + cccskills 0)
实测评分 未实测
查看安装方法包含的文件（1）
- SKILL.md1.6 KB
SKILL.md（原文）
安装前可以查看交给 AI 代理的指令内容。
/sweep-now
Run all three sweeps in sequence and append one result to
vault/memory/SWEEP_LOG.md.
Checks
- Scan active Delegation Tracker items. Flag live items whose last meaningful update is older than 14 days.
- Read
HEAT_INDEX.jsoncold_bottom_20. For each note last touched more than 60 days ago, propose a dormant flip. Do not apply it unattended. - Scan vault wikilinks and list references whose target does not exist.
Output
Append:
### YYYY-MM-DD - full sweep
- Delegation tracker: <N> stale items flagged (<stable references>)
- Dormant-note candidates: <N> proposed
- Broken wikilinks: <N>
- Notes inspected: <wikilink list or none>
- Open issues for the operator: <list or none>
Append only after all three scans complete. The nightly controller independently checks the newest real H3 date header.
Cadence
The default cadence is seven days. A nightly skip is legal only when
SWEEP_LOG.md exists, contains a valid real dated H3 header, and the controller
derives that it is within cadence. Missing or malformed evidence is failure.
Boundaries
- Do not auto-fix broken links.
- Do not auto-flip dormant notes.
- Do not auto-close stale work.
- Keep every proposal human-reviewable.
评价
还没有评价。欢迎分享你的使用感受。
评论
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。
同一仓库的技能
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。
wrg32786/aigent-os252026年10月29日 更新
brief
免费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。
wrg32786/aigent-os252026年10月29日 更新
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。
wrg32786/aigent-os252026年10月29日 更新
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。
wrg32786/aigent-os252026年10月29日 更新
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。
wrg32786/aigent-os252026年10月29日 更新