fleetlisted
Install: claude install-skill lukasrepublic/agentic-foundry
# /foundry:fleet
The operator's single-pane view for supervising many parallel sessions (the cognitive-load surface).
A **thin overlay** over native Claude Code session machinery — it does NOT rebuild what the harness
ships (`claude agents` already enumerates sessions + their needs-input state + a summary). Foundry adds
the one thing native cannot know: each session's **work-context** — which release/feature/atom it
serves, its governance state, and any operator-reported why/pending-decision/blocker.
## What it shows
`scripts/foundry-fleet-roster.py` renders one row per native session (via the session-registry):
- **native base** (harness-authoritative): session id, repo (cwd), branch, name, state, a best-effort
liveness value (native `updated_at`, "—" when absent — no fabricated "live", no dead-PID stale flag);
- **foundry overlay**: epic/atom, governance state, a `◀` **pending-decision** marker;
- **headline machinery scan columns** (joined from the `session-machinery` overlay by `session_id`):
`ISO` (isolation), `GATE` (gate/merge-readiness), `WF·step` (workflow+stage). These are **DEFAULT-DENY**:
a value renders clear **only** when it is in that field's explicit known-safe set (e.g. `GATE` clear only
for a derived `authorized`/`gate_pass`/`merged`; `ISO` clear only for `worktree`); every other value —
`unknown`, `gate_block`, `direct_main`, `worktree_on_main`, a null/un-derived risk value, **or any
novel/out-of-vocabulary token** — renders `⚠` (attention),