claude: keep althing monitor armed by default per session

Adds a default-posture paragraph to the althing async-reply monitoring
section: unless a session says otherwise, every session attempts to keep
its althing monitor armed for the session's duration (arm early, re-arm
after each fire, stay armed even without a pending reply). Reconciles the
Scope paragraph so it no longer instructs sign-off after each exchange.

home_root/.claude/CLAUDE.md

@@ -155,6 +155,16 @@ the skill. Always triage Heid output before acting on it.
 
 ## Althing async-reply monitoring
 
+**Default posture — keep the monitor armed (operator directive,
+2026-07-14).** Unless a session says otherwise, every session should
+**attempt to keep its althing monitor armed for the session's
+duration** — arm it early (`/althing:monitor`) and re-arm after each
+fire (drain the fire via `/althing:inbox`, then re-arm), so peer mail
+is caught proactively rather than only surfacing on the next user
+prompt. The arm-on-dispatch rule below is the *minimum* case of this
+broader default; the default is to stay armed **even without a
+specific pending reply**, because peer agents reach out unprompted.
+
 When you ship an althing message that you expect to come back with a
 reply — a consult (`/heid*`), a question to a peer agent, a request
 awaiting an answer — and you do **not** already have an althing
@@ -170,12 +180,15 @@ reply lands, so the await-reply promise ("reply will land in your
 inbox") is backed by a real notification, not by hoping the operator
 prompts again.
 
-Scope: only messages where you're waiting on a response. Pure
-fire-and-forget posts (an FYI ping, a post-1.0 downstream-consumer
-announcement) don't need a monitor. When the exchange is done, sign
-off (`/althing:sign-off`) so monitors don't accumulate — stop a stuck
-one with `althing-light-monitor --stop`, never `pkill` (that kills
-every agent's monitor, not just yours).
+Scope of the *arm-on-dispatch* rule: it fires for any message where
+you're waiting on a response (a pure fire-and-forget FYI doesn't
+*oblige* a fresh arm) — but under the keep-armed default the monitor is
+typically already up regardless. Do **not** sign off after each
+exchange (that fights the default); sign off (`/althing:sign-off`) at
+session wind-down or on operator direction. Monitors don't accumulate
+— the singleton guard is one-per-handle, so re-arming freely is safe.
+Stop a stuck one with `althing-light-monitor --stop`, never `pkill`
+(that kills every agent's monitor, not just yours).
 
 ## Development workflow shapes
 
@@ -236,23 +249,42 @@ For work an AFK agent will implement off a contract.
    irreversible dispatch authorization. See § "Issue → AFK dispatch
    hygiene (Sleipnir)" for the gate's hard requirements.
 
-### Direct implementation shape
+### Direct implementation shape — the House Code Discipline
 
-For work implemented directly in-session.
+For work implemented directly in-session. This is the **House Code
+Discipline** — the canonical full pipeline, end to end:
 
-1. Issue created.
-2. Heid consult on the issue (`/heid`).
-3. `/vor` — or `/vor-frame` (ask too shapeless to draft a `/vor`
-   questionnaire) or `/vor-cross` (cross-frontier peer in the loop) —
-   if the ask warrants a pre-contract design pass. Skip when the
-   frame is already crisp.
-4. Write the contract.
-5. Heid contract review (`/heid-contract-review`).
-6. Fixup the contract per triaged findings.
-7. TDD implement (`/tdd`) — red-green-refactor against the contract.
-8. Heid code review (`/heid-code-review`) — code-vs-contract drift.
-9. Fixup the code per triaged findings.
-10. Commit if clean.
+> **concept** (heid refinement optional) → **contract** → **contract
+> review** → **TDD slices** (all of them) → **heid code-review** →
+> **fixup** → **heid bug-hunt** → **fixup** → **merge/commit**
+
+As numbered stages:
+
+1. **Concept.** Frame the work. A heid consult (`/heid`) or a `/vor` /
+   `/vor-frame` / `/vor-cross` pass is *optional refinement* — take it
+   when the ask warrants it, skip it when the frame is already crisp.
+2. **Contract.** Write the `.contract.md` (graphify the blast radius
+   first per the rule above).
+3. **Contract review.** `/heid-contract-review`, then **fixup** the
+   contract per triaged findings.
+4. **TDD slices.** `/tdd` — red-green-refactor against the contract,
+   through *all* the slices, not just a single tracer bullet.
+5. **Heid code-review.** `/heid-code-review` (code-vs-contract drift),
+   then **fixup** the code per triaged findings.
+6. **Heid bug-hunt.** `/heid-bug-hunt` (diff-scoped robustness hunt —
+   crashes, leaks, removed guards, caller breaks, false rejects), then
+   **fixup** per triaged findings.
+7. **Merge/commit** when clean.
+
+**Partial discipline for surgical fixes.** Surgical / localized work —
+one-liners, small bug fixes, surgical test updates — does not need the
+full front matter: **TDD + bug-hunt is the acceptable reduced
+discipline** (drop the concept → contract → contract-review ceremony,
+keep the two implementation-quality gates). Composes with the
+Contract-skip privilege above: skip *authoring* a contract, but update
+any live contract governing the touched behavior in the same commit so
+it stays canonical. When in doubt about whether a fix is "surgical
+enough," keep the gate rather than drop it.
 
 ## Tooling preferences
 
@@ -389,7 +421,8 @@ section doesn't cover.
 
 This section is Corviduo's **operational cadence layer on top of that
 policy**: which commits become releases and at what tier (tier-bar
-test, patch-default, operator approval for non-patch). Where the two
+test, patch-default, operator approval for minor/major only — patch,
+pre-release, and dev bumps are agent-discretion). Where the two
 differ on cadence or tier choice, this section governs; for format,
 contract semantics, pre-release staging, and release mechanics, the
 policy governs. Operator ruling (2026-07-02): pre-1.0 **milestone
@@ -432,13 +465,21 @@ announcing the change**. That's the actual mechanism. Operator or
 Brokkr pings worldtree-dev / galdrabok-dev / sleipnir-dev / etc.
 when a post-1.0 minor lands.
 
-### Operator approval required for any non-patch bump
+### Operator approval required for minor + major bumps only
 
-**Patch bumps are at agent discretion.** Apply them autonomously as
-part of the work.
+**Patch, pre-release, and dev bumps are at agent discretion.** Apply
+them autonomously as part of the work. This covers: patch (`X.Y.Z` →
+`X.Y.(Z+1)`); **ALL pre-release increments** (`-alpha.N` / `-beta.N` /
+`-rc.N` / `aN` / `bN`, e.g. `2.0.0a2 → 2.0.0a3` — the pillar-cadence
+alpha bumps); and dev/in-progress labels. The approval gate keys on the
+**version NUMBER**, not the "is-it-a-patch" question: only a change to
+the **major (`X`) or minor (`Y`) field** needs approval. A pre-release
+increment inside an unshipped `X.Y.0` train never changes `X` or `Y`,
+so it never needs approval.
 
 **Minor and major bumps REQUIRE explicit operator approval** before
-the bump commit lands. The mechanism:
+the bump commit lands — i.e. only when the `X` or `Y` field changes.
+The mechanism:
 
 1. Identify that the work warrants a non-patch bump per the
    tier-bar test (release-note / push-notification / blog-post).
@@ -592,10 +633,11 @@ paragraph, or am I just accumulating substantive work?
 
 ### Mechanics every bump
 
-0. **If non-patch, get operator approval first** per the § *Operator
-   approval required for any non-patch bump* rule above. Do not
-   proceed to step 1 until the operator has explicitly approved the
-   minor or major bump. (Patch bumps skip this step — apply
+0. **If minor or major (an `X` or `Y` field change), get operator
+   approval first** per the § *Operator approval required for minor +
+   major bumps only* rule above. Do not proceed to step 1 until the
+   operator has explicitly approved the minor or major bump. (Patch,
+   pre-release/alpha/beta/rc, and dev bumps skip this step — apply
    autonomously.)
 1. Edit `pyproject.toml` (or equivalent project-file) version field.
 2. Run `uv lock` (Python) or equivalent so the lockfile records the