kvb-skill-dream becomes the uncategorized collector kvb-dream. It reads the last 24 hours of every repository and session the agent touched, writes each finding into the memory of its own project, hands its findings to the new kvb-optimize (skill-cleanup, transcend, skill-auto, skill-tune, skill-compile, skill-essence, code-refactor, code-tune, think-gaps, one round of questions) and then runs kvb-cleanup and kvb-git-branch-gc. The separate kvb-skill-tune reminder is gone: one reminder reads the session id from the hook payload and hints each agent at most every twelve hours, and the global install enables kvb-dream-notify.timer, a systemd user timer that recommends /kvb-dream in a GNOME notification daily at 17:00 local time and catches up once after a missed run. enable-plugins.js retires the tune reminder hooks and repoints every earlier dream hook path. Operator order 2026-11-03; three descriptions trimmed for the listing budget. BREAKING CHANGE: /kvb-skill-dream is now /kvb-dream; kvb-skill-tune no longer has its own reminder hook. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
3.1 KiB
name, description
| name | description |
|---|---|
| kvb-org-rasci | RASCI/OKR register of tasks: roles, key results, worker, status. Trigger on /kvb-org-rasci, "rasci", "raci", "zuständigkeiten". |
The register is the single point of truth of the organisation: every agent
records here what it works on, and claims, queue, handover and reports run
over it. ${CLAUDE_SKILL_DIR}/scripts/rasci.py keeps it in
<council root>/rasci.json. A kvb-org-organize claim enters its task by
itself (holder as R and A, running, start, workdir, branch); its release
sets done and the end, or stopped while a key result is still open.
rasci.py set <task> --title <t> --objective <o> --description <d> --prio <n> --status queued|running|blocked|done|stopped --worker "<agent | subagent <type> (<model>)>" --workdir <dir> --branch <b> --artifact <kind>:<ref> --tool <script or command> [--start <iso>] [--end <iso>] [--drop-artifact <a>] [--drop-tool <t>]
rasci.py kr <task> add "<measurable result>" | met <n> | open <n> | rm <n>
rasci.py role <task> "<party>" <letters>
rasci.py get <task>
rasci.py rm <task>
rasci.py show [--all]
rasci.py artifacts [--ended] [--task <task>]
rasci.py estimate <task> "<party>" --value <fib> --complexity <fib>
rasci.py wsjf [--all]
rasci.py tools
Objective and key results
The objective says what the task is for; its key results are the measurable
outcomes that prove it reached (a test green, a run passing, a release
published). done is refused while one is open; a task ended short of them is
stopped. show puts both in the OKR column as <objective> (<met>/<all> KR).
Roles
- R Responsible: does the task: the claim holder, or the subagent it runs.
- A Accountable: exactly one; takes the final decision and carries the overall responsibility. The claim holder, unless the operator decides.
- S Supportive: actively helps carry it out: a peer's fix, the chair's grant, a stack or runner.
- C Consulted: asked for input before acting: line representatives, lineage owners, the operator on a pending decision.
- I Informed: kept up to date on progress or result, without a say.
- clears a party; the operator is the party Operator.
Rules
- On start,
settitle, objective, description, priority and worker,kr addevery key result, androleevery party beyond R and A; on each change, update the status. The worker is the one session or subagent executing the task right now. - Artifacts share this table and follow the
kvb-org-artefactsskill: record each one when it appears, drop it once deleted. Add every script or tool the task ran (--tool):toolsranks them forkvb-dream. - Priority is the rank of the
kvb-org-wsjfskill: an operator's pin (--prio) first, then WSJF from the estimates the chair collects;showprints the rank as Prio and the score as WSJF. - Write only your own rows; another session's task belongs to that session.
- On /kvb-org-rasci print
showunchanged; itsgaps:line names tasks without exactly one A, without R, or open without a key result.getprints one task in full, key results numbered.