What the operator checks each tick, why PR #913 slipped through, how to collapse five tracked-thing schemas into one, which cron kind fits, and where rk should grow.
Every tick runs the seven steps in §4 Tick Behavior. Each step reads one section of the state file and talks to one external source. The picture is worth drawing because the gaps are structural, not accidental: whole classes of tracked things have no arrow to anything that observes the world.
The self-analysis in the screenshot is accurate about the symptom. The cause sits in the skill text, not in the session's discipline.
Three lines in the skill together produce this outcome:
source exists today)” go to a note. The gap is documented as policy.The Go side agrees with the prose: operator_watch.go rejects any --source other than linear or slack, and tick-start only enumerates tmux panes. So your read is right. The tracked-thing model is fab-change-shaped, and everything else is a special case bolted to its side.
The fix is not a sixth section for GitHub. It is to make every tracked thing the same shape, so that the binary can poll all of them in one loop and the LLM only decides what to do about changes. The operator's job statement then becomes literally what you said: hand me something long-running, I will watch it and act when it moves.
What this buys you, in the terms of the #913 incident: fab operator track add pr-913 --probe 'gh pr view 913 --json state' --done '.state==\"MERGED\"' --then 'spawn n34…' would have produced a done delta on the first tick after 22:07:54, and the operator would have spawned n34 without being asked.
The table the operator prints every tick is the only surface where a stale item can be seen. Today it has two tables (changes per repo, then watches), no column for when a thing was last verified, and no row for notes. Proposed: one table over every tracked item, a column for freshness, and a column for what the operator will do next. Rendered as the terminal shows it:
| ID | Kind | State | Checked | Next | |
|---|---|---|---|---|---|
| ▶ | t9hb | fab · ~/code/hexokit | 🟢 review · active | live | — |
n34 | fab · ~/code/hexokit | ⏸ held | — | waits on pr-913 | |
| ▶ | pr-913 | gh pr · hexokit#913 | 🟡 OPEN · checks pending | 2m ago | spawn n34 when MERGED |
| ▶ | DEV-988 | linear · DEV | 🟢 In Progress | 11m ago ⚠ | notify when Done |
deploy | shell · curl staging | 🔴 exit 1 · 3 fails | 1m ago | escalated | |
n1 | note | phase 2 of 4 — auto-merge armed behind s2gw | 3d | — |
And the quiet tick, still one line, now carrying the live cadence read from rk cron list --json:
🛰️ **Operator** · 22:06 · tick #5122 · **6 tracked** · idle-every 3m · no change · 1 waiting
The markdown source the operator emits for the full frame, shown fenced here only so the page can display it:
🛰️ **Operator** · 22:03 · tick #5121 · **6 tracked** · idle-every 3m · skip-if-busy
| | ID | Kind | State | Checked | Next |
|:--:|---|---|---|---|---|
| ▶ | `t9hb` | fab · ~/code/hexokit | 🟢 review · active | live | — |
| | `n34` | fab · ~/code/hexokit | ⏸ held | — | waits on `pr-913` |
| ▶ | `pr-913` | gh pr · hexokit#913 | 🟡 OPEN · checks pending | 2m ago | spawn `n34` when MERGED |
| ▶ | `DEV-988` | linear · DEV | 🟢 In Progress | 11m ago ⚠ | notify when Done |
| | `deploy` | shell · curl staging | 🔴 exit 1 · 3 fails | 1m ago | escalated |
| | `n1` | note | phase 2 of 4 — auto-merge armed behind s2gw | 3d | — |
*pr-913: OPEN → checks pending · DEV-988: unverified 11m (cadence 5m) · deploy: probe failed ×3, auto-paused*
| Rule | Today | Proposed |
|---|---|---|
| Render channel | bare markdown, no fence, no headings; tables, emoji, bold, italic, code spans, URLs | kept |
| Emoji is the only colour | 🟢 🟡 🔴 ✅ ⚪; geometric glyphs banned | kept, adds ⏸ held on a dependency |
| Header | 🛰️ **Operator** · HH:MM · tick #N · **N tracked** | same, plus · <schedule> · <deliver> read from rk cron list --json, never composed |
| Two shapes | full on a delta, every 10th tick, or on request; one-line compact otherwise | kept; a stale or probe_error delta also forces the full frame |
| Grouping | one anchor + table per repo, then a Watches table | one table; scope moves into the Kind column (fab · ~/repo, gh pr · repo#N, linear · PROJECT) |
| ▶ marker | autopilot-queue member | the item has a then: the operator will act on its next change |
| State column | Stage, optional ⚠️ for >15m idle | health emoji + last observed state verbatim from the probe's declared field; fab items keep stage · agent |
| Checked column | none (watches had "Nm ago" in Status) | age since last successful probe; live for pane items; ⚠ once past the item's check_every; 🔴 at twice it |
| Next column | PR URL | the armed action in five words or fewer; the URL moves to the footnote line when it changes |
| Notes | absent from the frame; only in fab operator state | rows like any other item, Checked shows age since update |
| Footnote | italic, ·-separated actions | kept; changed-field deltas render here too (OPEN → MERGED) |
| Idle message | separate "Waiting for next tick" line between ticks | deleted; the compact line already carries time and tick |
| Nothing else per tick | no echo of the tick document, no per-candidate lines | kept |
Ordering: kind, then scope, then id, so fab items stay together and a Linear item never lands between two changes of the same repo. Items removed this tick render once with ✅ and their closing footnote, then vanish. A held item shows what it waits on, so a dependency chain reads top to bottom without opening the state file.
Where it lands. The cadence suffix on the header rides fab change A, since it only reads released rk output. Everything else is change B: the Kind, Checked and Next columns exist only once items carry kind, checked_at and then.
tracked list.
Each item: id, kind, probe (pane | shell <cmd> | agent <instruction> | none), done_when, then (prose), depends_on, last, checked_at. Monitored entries, watches, autopilot queue entries and coordination notes become kinds with defaults. The clock predicate becomes “tracked is non-empty”, which is simpler than today's four-clause disjunction. branch_map can stay as a side lookup, or ride as item metadata.
tick-start --diff poll every item with a mechanical probe.
Today it enumerates panes. Extend it to run shell probes (bounded timeout, argv-only, stderr swallowed) and evaluate done_when as a small predicate over the probe's JSON. Items whose probe is agent come back in a needs_check block with their age, so the LLM is told what to verify rather than trusted to remember. This single change closes the #913 class of bug.
Dependency resolution, the three merge modes, ordered merge and auto-merge are 235 lines, but they are the operator's main job, and they must survive a compaction reload: an armed merge sequence whose procedure lives in a helper the operator has to remember to load is the #913 shape again. So they stay where the reload guarantees them. In the generic model they operate on items with depends_on rather than on a separate autopilot block, which removes the duplicated "satisfied" definitions and the note-based persistence of the merge sequence. Realistic trim in place: 235 to about 180 lines. The three mode diagrams stay; the mode question requires them.
fab-change kind.
“Route pipeline-first”, “spawn in a worktree”, the hard wt gate at startup, stage-validated flags and “completion = review-pr done” are all correct for a fab change and wrong for everything else you listed. Keep them as the defaults that kind carries. A task kind whose then is “open an agent tab with this prompt” covers a normal change; a linear kind with no then covers a ticket you merely want to watch.
Replace the change table plus watches table plus the ten-row element-format table with a single table over items: id, kind, state, age since check, next. Keep the health emoji as the only colour channel and keep the compact quiet-tick line. An item not verified within its expected cadence shows ⚠ unverified 14m, which is the visual that would have caught #913 by tick #5121.
probe: none, and they render.
Drop the four note kinds and the routing-doctrine table. A note is a tracked item a human will resolve; it shows in the frame with its age, and the “stale after 14 days” flag already exists in note list. This also removes the paragraph that currently tells the agent merge-gate waits are its unaided responsibility.
Candidates: the two-rung version-skew fallback, the pre-cron /loop fallback (rk is a hard dependency of the operator in practice), the duplicate no-fence warnings, the Spawn-Session inference's four evidence tiers (default to “session of the target repo's other agents, else ask once”), and the “Idle Message” section. Each is defensible alone; together they are why the file is 903 lines.
| Section | Lines today | Fate | Est. after |
|---|---|---|---|
| Header, §1 Principles, §2 Startup | 110 | Keep; principles lose fab-only rows | 70 |
| §3 Safety | 45 | Keep as is | 45 |
| §4 Clock, mute/lease, reload | 57 | Keep; predicate simplifies | 45 |
| §4 State file, monitored, branch_map, notes | 108 | Collapse to one item schema | 40 |
| §4 Tick + frame + idle message | 113 | Generic loop, one table | 55 |
| §5 Auto-nudge | 74 | Keep, it is the best part | 70 |
| §6 Spawn + Working a change | 65 | Keep; session inference trimmed | 45 |
| §6 Dependencies, autopilot, merge modes, merges | 235 | Keep inline; re-point at items, dedupe the "satisfied" definitions | 180 |
| §7 Watches | 54 | Become a kind; conversational map stays | 20 |
| §8–9 Config, key properties | 42 | Keep | 35 |
| Total | 903 | ≈600 |
The estimate is a target, not a measurement. A third of the file describes kind-specific exceptions to a loop that can be written once; the choreography third stays.
operator tick, mute on empty, lease as bounded snooze, no slash command in the payload. This was hard-won and is correct.waiting-first sweep, the answer model, non-blocking strategic handling and the re-capture guard. None of it is fab-specific.rk cron respawn argv in §4 already follows that shape.Verified against run-kit's backoff.go, not only the doc page. The ladder's anchor is the operator pane's own last non-clock activity: an agent-state epoch within 120 seconds of the entry's latest delivery is attributed to the tick and the ladder keeps climbing; an epoch outside that window is genuine activity and resets to rung 0.
| Kind | Anchor | Sees external change | Pane-only operator | Generic tracking |
|---|---|---|---|---|
every | last delivery | by polling at a fixed floor | fine, slightly wasteful | good: predictable floor |
cron | wall clock | no | wrong shape | per-item schedules only |
backoff | operator pane's last genuine idle | by polling, thinning to 30m | best with wake_on | poor: floor erodes |
--idle-every 9aup | same, flat ladder (min = max) | by polling at a fixed floor, re-phased on your activity | fine | best with skip-if-busy |
wake_on | other panes' state edges | no | essential | essential for agent items only |
deliver: skip-if-busy is a third delivery policy beside immediate (type it in, harness queues it) and when-idle (hold, retry each poll, drop after two hours). Busy is active or waiting. A dropped tick costs nothing: ticks are idempotent and the important deltas are level-triggered.--idle-every d is backoff with min equal to max. Both objections to backoff vanish at a flat ladder: there is no rung to lose, so a long tick turn only re-phases, and the interval never thins.rk cron edit turns the clock into a knob the operator owns. §4's "cadence is not owned by this skill" flips.schedule: idle-every 3m # every 3m when no epoch is available
wake_on: { event: agent-state-change, scope: server, debounce: 60s }
deliver: skip-if-busy # no queued tick backlog, no tick after every exchange
if_absent: respawn · pinned
Two consequences to accept: a wake_on fire that lands mid-turn is dropped too, so the interval must stay short; and an operator parked on its own permission prompt skips every tick until answered, which is why it runs with bypass permissions.
The operator changing its own schedule "as the work changes" is right in aim and wrong if it is a per-tick LLM judgment, which is the #913 failure class again. The split that works:
track add."CI here takes about 8 minutes", "poll the deploy every 2 minutes until green". It becomes the item's check_every.
No external items: backoff 1m→30m, keeping the fade. Any external item: idle-every min(check_every) with skip-if-busy. Applied through rk cron edit on the same hook that mutes and unmutes, only when the derived value changes.
"Hold the ticks for 30 minutes" stays a lease. "Check every 15 minutes for the rest of the day" is an edit with an expiry the reconcile respects.
Ready line and compact tick line carry every 3m · skip-if-busy or backoff 1m→30m, read from rk cron list --json, never from memory.
Mechanical note for run-kit: switching kinds re-anchors. A switch to every 3m fires on the next poll if the gap already exceeds 3 minutes. Harmless, but the edit spec should say so.
Both, layered. The operator still calls fab pane map --all-sessions and tick-start --diff, but since the cli-layering work those source their pane list from rk mux panes --json whenever rk is present, with a silent tmux fallback. rk is the substrate; fab adds change, stage and PR enrichment from the worktree's status files.
| Job | Operator uses | Underneath |
|---|---|---|
| Enumerate panes | fab pane map, tick-start --diff | rk mux panes --json, tmux fallback |
| Read a screen, process tree, kill | rk mux capture / process / kill | fab's twins demoted to dispatch-internal |
| Send text, answers, keys | rk mux send, --answer, --key, --force | raw send-keys fallback |
| Readiness after spawn | fab pane ready | delegates to rk mux await --ready |
| Spawn a worker | raw tmux new-window -t -P -F -n -c "cmd; exec $SHELL" | no rk verb |
| Mark tracked windows | fab pane window-name prefix » / › | raw window rename |
| Detect prompts on uninstrumented panes | fab pane questions | capture-scan |
| Agent-exited liveness | tick-start walks the process tree itself | duplicates rk mux process |
| Clock | rk cron entry, mute/unmute from fab verbs |
Decision: probes stay in fab. A raw output fingerprint has too many unrelated ways to change, so it would wake the operator on noise. The mitigation belongs where the item is defined: at track add the LLM names the field to compare (.state, .mergedAt), and tick-start diffs only that. Original proposal kept for the record: wake_on: { event: probe-change, argv: [gh, pr, view, "913", --json, state], every: 2m }. rk polls external state inside its own 30-second ticker and fires the operator only on change. Polling leaves LLM turns entirely, the operator stays on backoff, and the #913 class is closed at the substrate. It has a target and a delivery, so it fits rk's own scope rule. A repo-boundary decision: settle it before the fab tracked-item work.
rk tab new takes no session target, cwd or command. A verb taking -t session, -c cwd, the command, a name, optional --ready, printing {session, window_id, pane_id} deletes §6 step 7 and its escaping paragraph.
rk renders @rk_win_marker, @rk_win_color, @rk_win_note but they are set only by raw tmux set-option. A rk tab mark verb plus a "tracked by operator" treatment retires the »/› rename hack.
Add has_agent to rk mux panes --json so tick-start can drop its own process-tree walk, the most intricate code in the operator binary.
rk cron list --json. released · r5aoToday schedule is the display string backoff 1m→30m. Deriving and editing needs {kind, min, max, interval}, deliver and wake_on as fields.
fab pane questions is substrate work living in fab. An rk mux capture --classify is its natural home. Small and last.
Not a gap: fleet waiting. rk mux await --any blocks the caller and needs re-arming; the cron wake_on edge already does that job without a foreground process.
Two facts change the arithmetic. First, the operator already cannot run without run-kit in any useful way: the clock, the role mark, the send gate and the spawn readiness probe are all rk. Second, the skill loads four helpers, and the biggest of them is a reference for every fab command when the operator uses four. The cuts below assume 9aup and the five backlog items are shipped.
27 rk-absent or raw-tmux fallback passages in the skill and 12 in _cli-agents: raw send-keys, the /loop degraded clock, the ntfy / Discord / PushNotification / Slack notify ladder, rk-less pane-map notes, the two-rung version-skew procedure, and every scattered command -v rk gate. One startup check replaces them: rk present and at or above the version carrying the six verbs, else stop with the install line.
_cli-fab.md, not the file.
1,475 lines loaded, about 400 used: fab operator, fab pane, fab agent, fab resolve. Split those into _cli-operator.md, or make helpers section-addressable in the frontmatter. This is the single largest context saving available and needs no run-kit change.
rk mux send; a refusal is the answer".
§3 items 1 and 2 and _cli-agents § Pre-Send Validation paraphrase rk's own gate table. Keep the policy line: --answer for waiting, --force only on explicit user confirmation. The Delivery Probe section goes too; the paste probe and bounded recovery are rk's.
rk tab new --session =S --cwd <wt> --name <n> --ready --json -- <cmd> returns {session, window_id, pane_id}; track add reads them. §6 step 7, the escaping paragraph, and the -P -F explanation go. Session inference keeps the three-line majority rule over rk mux sessions; the four-tier prose goes.
rk tab mark and rk tab note replace the »/› choreography, its exit-code handling and the "window rename skipped" log line. fab pane window-name leaves the operator entirely.
Structured rk cron list --json renders the ready line from fields, so the four literal variants collapse to one template. Delete the seeded-entry YAML copy and the "how the union predicate covers the retired loop" history. Add the derived-schedule rule and rk cron edit in three lines.
rk mux capture --classify.
The §5 detection paragraph and the fab pane questions contract pointer become one line over the tick's waiting-first candidates. The answer model and the strategic table stay; they are the skill's judgment, not substrate.
agent_exited reads has_agent.
The longest bullet in _cli-fab § tick-start, the shell-basename list and the process-tree walk semantics, becomes: command is a shell and has_agent is false.
Every mechanical probe declares the fields it compares; tick-start never diffs raw output. That is the false-positive guard the rejected rk wake could not offer, and it is why the field choice sits with the LLM at track add.
| File | Today | What changes | Target |
|---|---|---|---|
fab-operator.md | 903 | §4 items 1–7 plus the cuts above; rk mandatory; choreography kept inline (≈180) | ≈480 |
_cli-fab.md | 1,475 | operator loads only its slice | ≈350 |
_preamble.md | 545 | unchanged, shared by every skill | 545 |
_cli-agents.md | 255 | pre-send, peek and probe sections point at rk skill mux | ≈120 |
_cli-external.md | 247 | /loop section deleted; wt moves to the fab-change helper | ≈80 |
| Loaded per reload | 3,425 | ≈1,575 |
Targets are estimates. The operator's reload cost is dominated by files it does not own, so the largest cut is a loading change, not a rewrite. The choreography is the one large block that stays, by design.
Decided: probes live in fab, not rk. Assumed done: 9aup (edit, skip-if-busy, --idle-every) and backlog items wzve, hzih, 7pek, r5ao, a7g2.
rk becomes mandatory; the operator loads _cli-operator.md instead of _cli-fab.md; every fallback passage is deleted; the compact line and ready line gain the live cadence from rk cron list --json. Otherwise no behaviour change, largest context win, safe to ship alone.
tracked list, probe loop, derived schedule.Go verbs and tick-start extension with field-scoped probes, one-table frame, §4 and §7 rewritten as kinds. Ready line from structured cron JSON, spawn via rk tab new, markers via rk tab mark. Autopilot becomes a chain of items with depends_on; the choreography sections are re-pointed at items and tightened in place, never moved out. The one-table frame (§4) lands here.