Kevin Veen-BirkenbachandClaude Opus 5.5
b18a481d8c
Efficiency and speed are after/before ratios where over 100 % is worse, so the labels now read 💸 cost and ⏱️ time in score.py, tokens.py, measure.py, the gate texts, the message block and every skill that quotes them; 💰 stays the value quotient and the --efficiency/--speed flags keep their names. --commit-table drops the worktree column, which took the table's width, and prints the path below it alone in a text block for copy and paste. 🎯 Fix: 94 % 💥 Break: 2 % 💸 Cost: 100 % ⏱️ Time: – 🛡️ Security: 100 % 💰 Value: ? 🏆 Score: 92 🚦 Gate: ✅ 90/5, cost and time <= 100, security 100 % Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2.5 KiB
2.5 KiB
name, description
| name | description |
|---|---|
| kvb-org-matrix | One matrix of everything in flight with the kvb-check-score line per item. Trigger on "status", "übersicht", "wo stehen wir". |
One-shot overview, no side effects: it reads state and reports it, never edits, stages, commits, deploys or starts work. The operator decides what to act on.
Collect the state
In parallel; skip a source the session lacks, and never invent a row for one you could not read:
- Tasks: the
kvb-org-rasciregister first, then the session's todo list, the operator's goals this session, and the requirement or plan documents the work follows. - Peers:
council.py list(thekvb-org-organizeskill) and the radio store,radio.py show --all(thekvb-org-radioskill); never message a peer for status. - Working tree:
git status --shortandgit log --oneline -10: uncommitted and untracked files are open work, commits since the branch point closed work. - Running: background jobs, spawned agents not yet reported, scheduled
/loopwake-ups, remote runs (CI, deploys). Poll their live state; a job is not "running" because you started it. - Remote: open PRs and issues for the branch and their check conclusions, when a forge CLI is available.
The matrix
One table, most-blocking first, one row per item:
| Item | State | Score | Evidence / next step |
- State:
open,running,blocked,done.donemeans verified (a passing run, a green check, a reproduction that now succeeds); work that merely looks finished isopen. - Score: the
kvb-check-scoreline (🎯 fix, 💥 break, 💸 cost, ⏱️ time, 🏆 score) per thekvb-check-confidenceskill, only for rows that changed something;-for pure observation rows. - Evidence / next step: for
donethe strongest proof line (what ran, what it returned), otherwise the single next action.
Then at most three lines:
- Blocked on: what needs the operator (a decision, a credential, an approval); omit when nothing does.
- Residuals: what keeps the lowest confidence below 100.
- Running: what reports back on its own, so the operator need not wait on it.
Rules
- Cover everything in scope, including work the operator did not ask about: a forgotten background job or an unpushed commit is what the matrix exists to surface.
- Report what the poll returned, never a predicted result; a running item has no score yet.
- One row per item, no per-item paragraphs; the operator asks when a row needs explaining.