Work Records / validate (push) Successful in 22s

Details

CUST-WP-0061-T05: retarget queue closures to WORK-RECORDS.md (generated)

Convention change, not new code: closing an item now means setting its
terminal status (status: closed/resolved/done + outcome where
applicable) directly on the item's own yaml block in place, instead of
deleting it and hand-writing a bullet in a separate "Completed"/
"Resolved decisions" log. WORK-RECORDS.md (CUST-WP-0061-T04, generated
by fix-consistency's C-33) already lists every closed/resolved/done
record with status/lane/source -- that supersedes the hand-maintained
logs as the going-forward view.

- AutopilotWorkQueue.md: closing note added; "## Completed" relabeled
  "(historical -- pre-canon, 2026-07-21)", frozen as-is, nothing
  migrated or deleted
- DecisionQueue.md: closing note added -- its "## Resolved decisions"
  entries were already structured as in-place yaml blocks with
  status: resolved (ahead of AWQ's convention already), so this only
  clarifies the log is superseded going forward, no structural change
- OfficeHourQueue.md: closing note added -- items already live under
  "## Queued items" with status: queued|prepared|done in place, no
  separate log ever existed here
- OperatingRhythm.md: queue-hygiene checklist updated to describe
  in-place status transitions instead of "moved to the log"; added
  item 5 noting WORK-RECORDS.md needs no hand-maintenance

Re-ran fix-consistency: WORK-RECORDS.md content unchanged (correctly
idempotent -- these were prose-only edits, no yaml block content
changed).

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

2026-07-21 01:54:40 +02:00

3.1 KiB

Raw Blame History

Operating Rhythm

Status: v0 — 2026-07-16 (BINKY-WP-0002-T05). The cadence that keeps the control plane honest. Blue lane: agents run it; the founder consumes it.

Daily brief

One brief per active day, written by whichever agent closes the day's work, stored in briefs/YYYY-MM-DD-daily-brief.md. Hard cap: one screen. Format:

# Daily Brief — <date>

## Decide now          (0–3 items, each linked to DecisionQueue)
## Progress            (what moved, milestone-relevant only)
## Risks               (changes to RiskRegister only — no restating)
## Best next hour      (single highest-leverage founder action)

Rules:

Decide now only lists prepared decision packages. Never raw questions.
Best next hour is one item. If nothing needs the founder, say so — "no founder action needed today" is a valid and desirable outcome.
Anything that can't fit the cap goes into a queue, not the brief.

Queue hygiene (every agent session touching this repo)

DecisionQueue.md — resolved items get status: resolved set in place (not moved to a separate log — CUST-WP-0061-T05); nothing older than 14 days without escalation (RISK-003 rule).
OfficeHourQueue.md — every queued item has prepared material before the next command day; done items get status: done in place; stale items pruned.
AutopilotWorkQueue.md — never empty; agents with idle capacity pull from the top; closed items get status: closed in place (CUST-WP-0061-T05).
Workplan files match hub state (fix-consistency covers drift).
WORK-RECORDS.md (generated, all three queues above) stays current — statehub fix-consistency regenerates it automatically (C-33); nothing to hand-maintain.

Bridge scheduler (workstation cron)

Status: installed 2026-07-16 (founder-approved; agents may not install their own persistence). Runs weekdays 08:23 local: scripts/rhythm-session.sh runs a headless, lane-restricted Claude Code session that does queue hygiene, writes the daily brief, and pulls one autopilot item (agent name agt-rhythm-bridge; flock guard, logs to ~/.cache/binky-control/rhythm/cron.log).

Installed line:

23 8 * * 1-5 /home/worsch/binky-control/scripts/rhythm-session.sh # binky rhythm bridge

Disable: crontab -e and delete the binky rhythm bridge line. Health check: tail ~/.cache/binky-control/rhythm/cron.log — every run appends a finish line; a silent weekday morning means the bridge failed.

This is explicitly a bridge: once activity-core definitions (T05) and an llm-connect executor (T06 follow-up) are live, the cron line is removed and scheduling moves to the sanctioned coordination layer.

Guardrails baked into the script: Green/Blue lane only, allowed tools limited to file edits + git add/commit, no push, no network, one-run-at-a-time lock, bounded "maintenance pass" prompt.

Weekly review (founder, ~15 min)

Read the newest brief + SuccessMilestones.md. One question: did anything move a milestone? If two consecutive weeks show activity without milestone movement, RISK-005 escalates.