/status

description: Show the project's current state at a glance — stage, open tasks, open questions, overrides since the last checkpoint, current branch. Read-only.
argument-hint: "(none) | drift"

{{CMD:status}} — state snapshot

A read-only summary of `.codearbiter/` state. No skill is routed to; no file is modified.

<!-- catalog-command-modes:start -->

Drift mode

<!-- command-mode:drift legacy-route:context-check --> With the exact argument `drift`, load and follow `{{PLUGIN_ROOT}}/skills/context-check/SKILL.md`. The audit begins read-only; re-scout or re-baseline may write only after the user's explicit selection. In drift mode the `context-check` contract governs; the opening summary and Hard gate below apply only to the no-argument snapshot. With no argument, continue with the unchanged read-only snapshot below. Reject other arguments rather than treating them as drift mode.

An initialized refresh is a separate explicit scoped or full selection handled by that existing owner after its read-only report. Neither this argument nor an ordinary status snapshot authorizes a write, a create-context retry or marker reset. <!-- catalog-command-modes:end -->

Flow

The orchestrator reads and presents:

1. **Stage** — the `stage:` maturity value from `{{PROJECT_DIR}}/.codearbiter/CONTEXT.md` frontmatter. 2. **Pipelines** — every slug in `{{PROJECT_DIR}}/.codearbiter/specs/` and `plans/`, preserving its existing representation. For HTML, use the installed engine's bounded structured reads (`identity`, `index`, symbol-scoped `read`, or `task-context`) through `{{PLUGIN_ROOT}}/includes/artifacts.md`; do not read rendered markup or execute verification to obtain status. For Markdown, read its actual status ledger without creating a counterpart. Report a spec with no plan, implementation in progress, or implementation complete. Count `DONE` and historical `ACCEPTED` toward implementation completion while retaining their distinct labels. Show verification separately: pending, failed, unknown, or the recorded result and its applicability when available. Completion alone does not establish a passing check, current acceptance, review, or release. Report missing/unreadable state as unknown, not complete. For a selected HTML plan task, include `task-context.check_summary` when the installed engine supplies `task-context`: an unresolved applicable reported failure remains visible after unrelated passes, while stale reports and trimmed history are disclosed separately. When the compatibility path can only use symbol-scoped reads, report the check summary as unknown unless those reads establish it; do not infer a clear summary from missing `task-context` support. These caller reports are not verified evidence. A draft spec or plan is not awaiting permission. Show a genuine unresolved product decision, explicit user checkpoint, or `BLOCKED` stop with its actual reason; status never clears it. An interrupted pipeline is resumable via `{{CMD:feature}}` — say so on its line. 3. **Open tasks** — resolve the installed `hooks/work.py` through the installed helper card: {{IF:claude}}[helper-invocation.md](../includes/helper-invocation.md).{{END}}{{IF:codex}}`{{PLUGIN_ROOT}}/includes/helper-invocation.md`.{{END}}{{IF:pi}}`../../includes/helper-invocation.md`.{{END}} When `open-tasks.md` exists, run `work.py list --limit 1` to check for conflicting owners, then use the board's in-flight count if it reports `owner: legacy` (top-level `- ` bullets excluding done `- [x]`; the same `_taskboardlib` count the {{IF:claude}}statusline and {{END}}SessionStart hook use{{IF:claude}}{{ELSE}}s{{END}}). Otherwise page `work.py list --limit 64` with its returned `next_offset` and `membership_sha256`, up to 256 entries total. Count `queued` and `active`; exclude `complete` and `archived`. If the first page reports more than 256 entries, or a later page remains after the cap, report the count as unknown with the total and suggest `work.py list` for selected pages. Stop on an unavailable page, changed membership, or an unsafe store and report the count as unknown. This cap avoids repeated full-directory scans for one display count. This selected read is for the explicit status command, not a new native-engine call on every statusline or SessionStart frame. 4. **Open questions** — the count of unresolved `[CONFIRM-NN]` placeholders in `{{PROJECT_DIR}}/.codearbiter/open-questions.md`. 5. **Overrides since last checkpoint** — entries in `{{PROJECT_DIR}}/.codearbiter/overrides.log` newer than the marker in `{{PROJECT_DIR}}/.codearbiter/last-checkpoint`. 6. **Current branch** — from git.

Output

## Project status — YYYY-MM-DD

Stage:            N
Branch:           <current branch>
Pipelines:
  <slug>          implementation 3/7 complete (2 DONE, 1 historical ACCEPTED); verification unknown — resume with {{CMD:feature}} "<slug>"
  <slug>          spec present, no plan
Open tasks:       N
Open questions:   N ([CONFIRM-NN] unresolved)
Overrides since last checkpoint: N

No specs and no plans → `Pipelines: none`.

If `[CONFIRM-NN]` placeholders are open, surface them — do not resolve them here.

When NOT to use

• A full cross-cutting review → `{{CMD:checkpoint}}`.
• A specific question → ask it directly; no command needed.

Hard gate

Read-only. MUST NOT modify any file. MUST NOT resolve a `[CONFIRM-NN]` it surfaces. No skill is routed to by this command.