@arbiterforge/ca-pi 0.6.3 → 0.10.0

package/plugins/ca-pi/SKILLS.md

@@ -4,44 +4,151 @@ Generated by tools/build-surface.py — edit core/surface/, never this file.
 Each entry skill wraps one governance command; a body loads only when its
 skill is invoked — never bulk-read this directory.
 
+## Installed surface
+
+| Visibility | Count |
+|---|---:|
+| Core | 18 |
+| Advanced | 12 |
+| Canonical total | 30 |
+| Compatibility aliases | 5 |
+| Internal | 1 |
+| Deprecated | 1 |
+| **Total** | **37** |
+
+## Core
+
+### Evaluate
+
+| Skill | Purpose |
+|---|---|
+| `/ca-preview` | Zero-onboarding, read-only dry-run of the reviewer fleet against the current uncommitted diff. Predicts reviewers, runs the state-free secret scan, writes nothing. |
+
+### Initialize
+
+| Skill | Purpose |
+|---|---|
+| `/ca-init` | Opt this repo into codeArbiter — scaffold the root-level .codearbiter/ state store. |
+
+### Change
+
 | Skill | Purpose |
 |---|---|
 | `/ca-add-dep` | Vet a new or changed third-party dependency for license, provenance, and supply-chain risk before any install runs. |
-| `/ca-adr` | Author a numbered, dated, user-attributed Architecture Decision Record under .codearbiter/decisions/. |
-| `/ca-adr-status` | Report the health of Architecture Decision Records — aged, unchallenged, supersession candidates, unresolved CONFIRM-NN. Read-only. |
-| `/ca-arbiter` | Exit maintainer dev mode — restore orchestration, remove the dev marker, log the exit. |
-| `/ca-audit` | Assemble the governance record for a range — commits, overrides, ADRs, sprint auto-decisions, open questions, checkpoint findings — into one dated audit packet. Read-only. |
-| `/ca-btw` | Lightweight Q&A about the project — answer from context and return, no routing, no state change. |
-| `/ca-checkpoint` | Periodic multi-reviewer sweep of the whole codebase — surfaces a triaged checkpoint report. |
 | `/ca-chore` | Sanctioned lane for non-behavioral work — docs-only edits, dependency bumps, reverts. Type-scaled gates; no TDD demanded of prose. |
-| `/ca-cleanup` | Finish an already-merged branch — classify the leftover artifacts, return to a fast-forwarded default checkout, and delete the merged local branch. Every discard confirmed per item; containment proven, never assumed. |
-| `/ca-commands` | Show the codeArbiter command catalog — the public command list and what each routes to. |
-| `/ca-commit` | Run the full commit gate — the only sanctioned path to a git commit. |
-| `/ca-conflict` | Stop everything and surface a rule conflict — persona vs. docs vs. code. Present both sides and the conflict-hierarchy level; the user resolves. No silent reconciliation. |
-| `/ca-context-check` | Optional manual drift audit — report stale provenance-tracked docs, then per stale doc offer re-scout, re-baseline, or defer. Not the daily loop; commit-gate auto-heal owns routine maintenance. |
-| `/ca-create-context` | Brownfield back-fill — scout an existing codebase and populate .codearbiter/, then lock it initialized. |
-| `/ca-debug` | Investigate-then-decide root-cause analysis for a defect whose cause is unknown. No code changes — exits to /ca-fix, /ca-adr, or a no-action close. |
-| `/ca-decompose` | Greenfield decomposition interview — a layered interview that populates .codearbiter/ and locks it initialized. |
-| `/ca-dev` | Maintainer override — suspend orchestration to edit codeArbiter itself. Env-gated (CODEARBITER_DEV=1), entry/exit logged to overrides.log. |
-| `/ca-doctor` | Verify the active host install, package, command ownership, enforcement, wrapper self-test, and active-dispatch coverage gap. Read-only. |
-| `/ca-feature` | "Start a feature: brainstorm a spec, get it approved, then drive it test-first through the pipeline. The one entry to implementation." |
-| `/ca-fix` | "Fix a confirmed bug: a failing regression test first, then a minimal fix, then the rest of the tdd gates." |
-| `/ca-init` | Opt this repo into codeArbiter — scaffold the root-level .codearbiter/ state store. |
-| `/ca-metrics` | Read-only 3-metric governance glance — override rate, small-lane rate, sprint low-confidence ratio — each with a trend arrow vs. the prior 20-commit window. |
-| `/ca-new-skill` | "Author a new codeArbiter skill: prove the gap is real, get the spec approved, then write it." |
-| `/ca-override` | Sanctioned, logged bypass of a gate or hard rule — one audit line, then proceed. |
-| `/ca-pr` | Open a pull request the only sanctioned way — clear every BLOCK-level review finding, then stage the PR. Never a direct write to the default branch. |
-| `/ca-preview` | Zero-onboarding, read-only dry-run of the reviewer fleet against the current uncommitted diff. Predicts reviewers, runs the state-free secret scan, writes nothing. |
-| `/ca-prune` | Trim transcript clutter to extend session lifetime — analyze, prune a copy, or toggle the after-each-turn service. Dry-run by default; gains land at resume/compaction, not the current turn. |
-| `/ca-reconcile` | SMARTS arbitration — reconcile architectural artifacts against the scaffold and prior decisions; every variance resolved by an explicit, user-attributed choice. |
+| `/ca-feature` | Start a feature: brainstorm a spec, get it approved, then drive it test-first through the pipeline. The one entry to implementation. |
+| `/ca-fix` | Fix a confirmed bug: a failing regression test first, then a minimal fix, then the rest of the tdd gates. |
 | `/ca-refactor` | Restructure code with behavioral parity proven through unmodified pre-existing tests, then refactor. No behavior change. |
-| `/ca-release` | Cut a release the only sanctioned way — SemVer bump from the commit log, a CHANGELOG section, an annotated tag. Takes the declared target's name as its only argument, or --dry-run to preview one with no write. The only path to a version tag. |
-| `/ca-review` | Review a diff with the reviewer fleet, funneled to one triaged verdict. Targets the current working diff, a path, or an inbound GitHub PR. |
 | `/ca-spike` | Exploratory spike on a throwaway branch — answer a named question with disposable code. Never merges; exits to a findings note or /ca-feature. |
 | `/ca-sprint` | Autonomous sprint — one interactive spec gate, then plan-to-PR execution with every auto-decision SMARTS-scored and logged. Hard gates remain true stops. |
-| `/ca-standup` | Daily repo hygiene — review the day's repo state, then perform the cleanups under per-action confirmation. Fast-forward only, never destructive without a yes. |
+
+### Review
+
+| Skill | Purpose |
+|---|---|
+| `/ca-review` | Review a diff with the reviewer fleet, funneled to one triaged verdict. Targets the current working diff, a path, or an inbound GitHub PR. |
+
+### Decide
+
+| Skill | Purpose |
+|---|---|
+| `/ca-adr` | Author a numbered, dated, user-attributed Architecture Decision Record under .codearbiter/decisions/. |
+
+### Ship
+
+| Skill | Purpose |
+|---|---|
+| `/ca-commit` | Run the full commit gate — the only sanctioned path to a git commit. |
+| `/ca-pr` | Open a pull request the only sanctioned way — clear every BLOCK-level review finding, then stage the PR. Never a direct write to the default branch. |
+| `/ca-release` | Cut a release the only sanctioned way — SemVer bump from the commit log, a CHANGELOG section, an annotated tag. Takes the declared target's name as its only argument, or --dry-run to preview one with no write. The only path to a version tag. |
+
+### Operate
+
+| Skill | Purpose |
+|---|---|
+| `/ca-doctor` | Verify the active host install, package, command ownership, enforcement, wrapper self-test, and active-dispatch coverage gap. Read-only. |
+| `/ca-override` | Sanctioned, logged bypass of a gate or hard rule — one audit line, then proceed. |
 | `/ca-status` | Show the project's current state at a glance — stage, open tasks, open questions, overrides since the last checkpoint, current branch. Read-only. |
 | `/ca-task` | The sanctioned task-board mutator — add a queued task, start one (flips to in-progress and stamps the date, minting a dotted ID on pick-up), or mark an in-progress task done. The only blessed write to open-tasks.md. |
+
+## Advanced
+
+### Change
+
+| Skill | Purpose |
+|---|---|
+| `/ca-debug` | Investigate-then-decide root-cause analysis for a defect whose cause is unknown. No code changes — exits to /ca-fix, /ca-adr, or a no-action close. |
+
+### Review
+
+| Skill | Purpose |
+|---|---|
+| `/ca-checkpoint` | Periodic multi-reviewer sweep of the whole codebase — surfaces a triaged checkpoint report. |
 | `/ca-threat-model` | Opt-in lightweight STRIDE pass for a sensitive feature before implementation. Not a routine gate — invoke it when a change warrants security thought. |
 | `/ca-tribunal` | Deep, rarely-convened whole-codebase audit — eleven specialist lenses, a resumable on-disk audit log, findings filed as GitHub issues on approval. Expensive; estimates cost and STOPs before running. Never a required gate. |
-| `/ca-watch` | Watch a PR's CI to completion — diagnose on red, notify and offer the merge on green. Never auto-merges. |
+
+### Decide
+
+| Skill | Purpose |
+|---|---|
+| `/ca-adr-status` | Report the health of Architecture Decision Records — aged, unchallenged, supersession candidates, unresolved CONFIRM-NN. Read-only. |
+| `/ca-reconcile` | SMARTS arbitration — reconcile architectural artifacts against the scaffold and prior decisions; every variance resolved by an explicit, user-attributed choice. |
+
+### Operate
+
+| Skill | Purpose |
+|---|---|
+| `/ca-audit` | Assemble the governance record for a range — commits, overrides, ADRs, sprint auto-decisions, open questions, checkpoint findings — into one dated audit packet. Read-only. |
+| `/ca-metrics` | Read-only 3-metric governance glance — override rate, small-lane rate, sprint low-confidence ratio — each with a trend arrow vs. the prior 20-commit window. |
+| `/ca-prune` | Trim transcript clutter to extend session lifetime — analyze, prune a copy, or toggle the after-each-turn service. Dry-run by default; gains land at resume/compaction, not the current turn. |
+| `/ca-standup` | Daily repo hygiene — review the day's repo state, then perform the cleanups under per-action confirmation. Fast-forward only, never destructive without a yes. |
+
+### Extend
+
+| Skill | Purpose |
+|---|---|
+| `/ca-new-skill` | Author a new codeArbiter skill: prove the gap is real, get the spec approved, then write it. |
+
+### Help
+
+| Skill | Purpose |
+|---|---|
+| `/ca-commands` | Show the codeArbiter command catalog — the public command list and what each routes to. |
+
+## Compatibility aliases
+
+### Initialize
+
+| Skill | Purpose | Replacement |
+|---|---|---|
+| `/ca-create-context` | Brownfield back-fill — scout an existing codebase and populate .codearbiter/, then lock it initialized. | `/ca-init --brownfield` |
+| `/ca-decompose` | Greenfield decomposition interview — a layered interview that populates .codearbiter/ and locks it initialized. | `/ca-init --greenfield` |
+
+### Ship
+
+| Skill | Purpose | Replacement |
+|---|---|---|
+| `/ca-cleanup` | Finish an already-merged branch — classify the leftover artifacts, return to a fast-forwarded default checkout, and delete the merged local branch. Every discard confirmed per item; containment proven, never assumed. | `/ca-pr --cleanup` |
+| `/ca-watch` | Watch a PR's CI to completion — diagnose on red, notify and offer the merge on green. Never auto-merges. | `/ca-pr --watch` |
+
+### Operate
+
+| Skill | Purpose | Replacement |
+|---|---|---|
+| `/ca-context-check` | Optional manual drift audit — report stale provenance-tracked docs, then per stale doc offer re-scout, re-baseline, or defer. Not the daily loop; commit-gate auto-heal owns routine maintenance. | `/ca-status drift` |
+
+## Internal
+
+### Decide
+
+| Skill | Purpose |
+|---|---|
+| `/ca-conflict` | Stop everything and surface a rule conflict — persona vs. docs vs. code. Present both sides and the conflict-hierarchy level; the user resolves. No silent reconciliation. |
+
+## Deprecated
+
+### Help
+
+| Skill | Purpose | Replacement |
+|---|---|---|
+| `/ca-btw` | Lightweight Q&A about the project — answer from context and return, no routing, no state change. | ask the question directly |

package/plugins/ca-pi/agents/INDEX.md

@@ -14,8 +14,9 @@ An agent is a reviewer or author **dispatched** by a skill — never routed to,
 | [migration-reviewer](migration-reviewer.md) | on a DB migration file add/modify | Reviews migration safety, data-classification tagging, immutability. | missing classification annotation, irreversible destructive op |
 | [coverage-auditor](coverage-auditor.md) | `tdd` (Phase 4) | Audits test coverage vs. TDD obligations; flags untested source and logical gaps. | untested source files, coverage below the maturity threshold |
 | [architecture-drift-reviewer](architecture-drift-reviewer.md) | `/checkpoint` sweep | Read-only; surfaces drift between the codebase and accepted ADRs in `.codearbiter/decisions/`. | — (informational, never blocks) |
-| [finding-triage](finding-triage.md) | `/checkpoint` sweep (sequential) | Consolidates reviewer reports; classifies each finding by severity and whether it blocks the current change. | — (post-processor) |
-| [checkpoint-aggregator](checkpoint-aggregator.md) | `/checkpoint` sweep (terminal) | Composes triage + challenger output into a dated `.codearbiter/checkpoints/` doc. | — (aggregator) |
+| [finding-triage](finding-triage.md) | `dispatching-parallel-agents` for review, checkpoint, sprint, and generic parallel batches (sequential) | Consolidates reviewer reports and terminal states; classifies each finding by severity and whether it blocks the current change. | — (post-processor) |
+| [verdict-aggregator](verdict-aggregator.md) | review and generic parallel batches (terminal) | Composes the complete triage report into one structured in-memory verdict. Read-only. | — (aggregator) |
+| [checkpoint-aggregator](checkpoint-aggregator.md) | `/checkpoint` after the read-only verdict | Persists the verdict as a dated, non-overwriting `.codearbiter/checkpoints/` doc. | — (aggregator) |
 | [decision-challenger](decision-challenger.md) | `decision-variance` (optional) | Adversarial red-team of ADRs; confidence 1–5; surfaces disproving evidence. Read-only. | — (surfaces, does not block) |
 | [scout](scout.md) | `decision-variance`, `context-creation` (INTERNAL) | Scans an assigned code scope, reports decision evidence — paths + line numbers only, no excerpts. Never dispatch directly. | — (internal) |
 | [grader](grader.md) | `decision-variance` (INTERNAL) | Produces a SMARTS analysis + strength-labeled recommendation for one variance. Never decides. Never dispatch directly. | — (internal) |

package/plugins/ca-pi/agents/checkpoint-aggregator.md

@@ -1,6 +1,6 @@
 ---
 name: checkpoint-aggregator
-description: Composes the finding-triage report and decision-challenger output into a dated checkpoint document under .codearbiter/checkpoints/YYYY-MM-DD.md. Aggregator, not a blocker.
+description: Persists a complete verdict-aggregator output under the selected dated checkpoint filename in .codearbiter/checkpoints/. Writer, not a blocker.
 tools: Read, Glob, Bash, Write
 classification: reviewer
 pi-skills: []
@@ -9,12 +9,12 @@ model: haiku
 
 # Checkpoint Aggregator Agent
 
-Final agent in the checkpoint pipeline. Read the finding-triage report, ensure the checkpoints directory exists, and write the dated checkpoint document. Composes; does not block. Runs after `finding-triage` completes.
+Explicit writer in the checkpoint pipeline. Consume the verdict-aggregator output, ensure the checkpoints directory exists, and write the dated checkpoint document. Persists; does not block. Runs only after `verdict-aggregator` returns.
 
 ## Required Reading
 
 1. `<project-root>/.codearbiter/CONTEXT.md` — the `stage:` value.
-2. The finding-triage report from the current checkpoint run.
+2. The complete verdict-aggregator output from the current checkpoint run.
 3. `<project-root>/.codearbiter/checkpoints/` — existing checkpoint documents (to avoid a duplicate).
 
 ## Process
@@ -25,15 +25,15 @@ Check `<project-root>/.codearbiter/checkpoints/`. Create it if missing. The chec
 
 ### Step 2 — Determine the checkpoint date
 
-Use the current date (YYYY-MM-DD). If a document for today exists, append a suffix: `YYYY-MM-DD-2.md`, `YYYY-MM-DD-3.md`. Never overwrite.
+Use the current date (YYYY-MM-DD). If a document for today exists, append a suffix: `YYYY-MM-DD-2.md`, `YYYY-MM-DD-3.md`. Record the selected dated checkpoint filename, including any numeric suffix. Never overwrite.
 
 ### Step 3 — Write the checkpoint document
 
-Write `<project-root>/.codearbiter/checkpoints/YYYY-MM-DD.md` with the structure below.
+Write the document with the structure below to the exact selected path under `<project-root>/.codearbiter/checkpoints/`.
 
 ### Step 4 — Report the path
 
-Report: "Checkpoint document written to `<project-root>/.codearbiter/checkpoints/YYYY-MM-DD.md`."
+Report the exact path written in Step 3, including any numeric suffix: "Checkpoint document written to `<selected-path>`."
 
 ### Step 5 — Surface DEFERRABLE findings for harvest
 
@@ -107,5 +107,6 @@ One `###` section per dispatched reviewer. Typical sections:
 ## Hard Rules
 
 - MUST NOT overwrite an existing checkpoint document.
-- Every finding from the triage report MUST appear in the checkpoint document. Omit nothing.
+- Every finding and incomplete-unit result from the verdict-aggregator output MUST appear in the checkpoint document. Omit nothing.
+- MUST NOT consume raw reviewer output or the finding-triage report directly.
 - The `<project-root>/.codearbiter/checkpoints/` directory MUST be created if missing. Do not fail silently.

package/plugins/ca-pi/agents/design-quality-reviewer.md

@@ -20,7 +20,7 @@ for the producer to fix.
 
 Reviews only **generated, user-facing artifacts** (UI, reports, resumes, slides, charts, PR
 descriptions, CHANGELOG sections). Does NOT review codeArbiter's own internal framework docs
-(`ORCHESTRATOR.md`, the `INDEX.md` files, skill/agent bodies). If asked to review an internal doc,
+(`arbiter.md`, the `INDEX.md` files, skill/agent bodies). If asked to review an internal doc,
 decline and say so.
 
 ## Required Reading (lazy, by medium)

package/plugins/ca-pi/agents/finding-triage.md

@@ -1,6 +1,6 @@
 ---
 name: finding-triage
-description: Post-processes all checkpoint reviewer reports — consolidates findings, classifies each by severity and whether it blocks the current change. Sequential. Produces a unified triage report for the checkpoint-aggregator. Reads project state from .codearbiter/.
+description: Post-processes reviewer reports — consolidates findings, classifies each by severity and whether it blocks the current change. Sequential. Produces a unified read-only triage report for the verdict-aggregator and explicit checkpoint persistence.
 tools: Read, Grep, Glob
 classification: reviewer
 pi-skills: []
@@ -9,12 +9,13 @@ model: haiku
 
 # Finding Triage Agent
 
-Runs after all checkpoint reviewer agents complete. Read every reviewer report, consolidate findings, and classify each one. Does not produce its own findings — classifies and unifies what the reviewers found. Runs sequentially; every reviewer report MUST be available before beginning.
+Runs after every unit in a batch reaches a terminal state. Read every reviewer report and the complete batch contract, consolidate findings, and classify each one. Does not produce its own reviewer findings — classifies and unifies what the reviewers found, while representing every `ERRORED` or `DEFERRED` unit as an incomplete-result finding. Runs sequentially; the entire batch MUST be available before beginning.
 
 ## Required Reading
 
 1. `<project-root>/.codearbiter/CONTEXT.md` — the `stage:` value (1–4 maturity / rigor knob).
-2. Every reviewer report from the current checkpoint run.
+2. Every reviewer report from the current batch.
+3. The batch completion contract, including the target kind and every unit's terminal state. Every `ERRORED` and `DEFERRED` unit MUST be present.
 
 ## Process
 
@@ -25,6 +26,10 @@ Read each reviewer report. Collect every finding. For each, record:
 - Severity (CRITICAL / HIGH / MEDIUM / LOW / CONFIDENCE-RATING)
 - Description
 - File and line (if applicable)
+- Remediation (or the next action for an incomplete-result finding)
+- Applicable control (or `n/a` when no control applies)
+
+Record an explicit no-finding result for each successful unit with no reviewer findings. Represent each `ERRORED` or `DEFERRED` unit as one `INCOMPLETE_RESULT` finding so the downstream verdict can account for the entire batch.
 
 ### Step 2 — Classify each finding
 
@@ -44,9 +49,13 @@ Assign every finding a severity and a disposition:
 - The finding is a decision-challenger UPHOLD (confidence 4–5).
 - The finding is an observation above threshold, not a gap.
 
+**`INCOMPLETE_RESULT`** — the unit did not produce a complete review result. Assign only when:
+- The batch contract records the unit as `ERRORED` or `DEFERRED`.
+- A required unit result or evidence receipt is absent.
+
 ### Step 3 — Produce the unified triage report
 
-List every finding with source, severity, description, and disposition.
+List every finding with source, severity, location, description, disposition, remediation, and applicable control. Include the explicit no-finding result for every successful unit with no findings.
 
 ## Output Format
 
@@ -55,32 +64,40 @@ List every finding with source, severity, description, and disposition.
 
 ### BLOCKS — must resolve before this change lands
 
-| Source | Severity | Finding | Disposition |
-|--------|----------|---------|-------------|
-| <reviewer> | CRITICAL/HIGH | <description> | BLOCKS |
+| Source | Severity | Location | Finding | Disposition | Remediation | Applicable control |
+|--------|----------|----------|---------|-------------|-------------|--------------------|
+| <reviewer> | CRITICAL/HIGH | <file:line or n/a> | <description> | BLOCKS | <next action> | <control or n/a> |
 
 ### DEFERRABLE — real, safe to follow up
 
-| Source | Severity | Finding | Disposition |
-|--------|----------|---------|-------------|
-| <reviewer> | MEDIUM | <description> | DEFERRABLE |
+| Source | Severity | Location | Finding | Disposition | Remediation | Applicable control |
+|--------|----------|----------|---------|-------------|-------------|--------------------|
+| <reviewer> | MEDIUM | <file:line or n/a> | <description> | DEFERRABLE | <next action> | <control or n/a> |
 
 ### NON_BLOCKING — informational
 
-| Source | Severity | Finding | Disposition |
-|--------|----------|---------|-------------|
-| <reviewer> | LOW | <description> | NON_BLOCKING |
+| Source | Severity | Location | Finding | Disposition | Remediation | Applicable control |
+|--------|----------|----------|---------|-------------|-------------|--------------------|
+| <reviewer> | LOW | <file:line or n/a> | <description> | NON_BLOCKING | <next action or none> | <control or n/a> |
+
+### INCOMPLETE_RESULT — batch result is incomplete
+
+| Source | Severity | Location | Finding | Disposition | Remediation | Applicable control |
+|--------|----------|----------|---------|-------------|-------------|--------------------|
+| <unit> | n/a | n/a | <ERRORED, DEFERRED, or missing result> | INCOMPLETE_RESULT | <retry or resolve> | n/a |
 
 ### Summary counts
 - Total findings: N
 - BLOCKS: N
 - DEFERRABLE: N
 - NON_BLOCKING: N
+- INCOMPLETE_RESULT: N
 ```
 
 ## Constraints
 
 - Generate no new findings. Classify only.
-- Modify no file. The checkpoint-aggregator writes the checkpoint document.
+- Modify no file. The verdict-aggregator consumes this report in memory; only an explicit checkpoint workflow may separately persist it through checkpoint-aggregator.
 - Skip nothing. Every finding from every reviewer appears in the triage report.
+- Preserve the batch accounting. Every dispatched unit appears as a finding source, an incomplete-result finding, or an explicit no-finding result.
 - Do not block on your own authority. You classify; downstream acts.

package/plugins/ca-pi/agents/verdict-aggregator.md

@@ -0,0 +1,64 @@
+---
+name: verdict-aggregator
+description: Composes a complete finding-triage report into one structured in-memory verdict for the caller. Read-only; never persists a checkpoint or modifies project state.
+tools: Read, Grep, Glob
+classification: reviewer
+pi-skills: []
+model: haiku
+---
+
+# Verdict Aggregator Agent
+
+Terminal read-only agent for review and generic parallel batches. Consume the complete finding-triage report and return one structured verdict to the caller. Do not reread raw reviewer output, invent findings, or persist the result.
+
+## Required Input
+
+1. The complete finding-triage report for the current batch.
+2. The batch completion contract, including the target kind and every unit's terminal state.
+
+## Process
+
+### Step 1 — Verify input completeness
+
+Confirm every dispatched unit appears in the triage report as a finding source or an explicit no-finding result. Every `ERRORED` or `DEFERRED` unit must appear as an incomplete-result finding. If any unit is absent, return `INCOMPLETE`; never infer its result.
+
+### Step 2 — Compose one verdict
+
+Return exactly one status. INCOMPLETE takes precedence over BLOCKING_FINDINGS; blocking findings remain in the output even when incomplete input determines the status.
+
+- `PASS` — no `BLOCKS` finding and no incomplete unit.
+- `INCOMPLETE` — any expected unit, evidence receipt, or terminal result is missing or errored.
+- `BLOCKING_FINDINGS` — one or more `BLOCKS` findings are present and the batch is otherwise complete.
+
+Preserve every triaged finding exactly once. Include source, severity, file and line when present, disposition, remediation, and the applicable control supplied by triage.
+
+## Output Format
+
+```markdown
+## Review verdict — <target>
+
+**Status:** PASS | BLOCKING_FINDINGS | INCOMPLETE
+
+| Disposition | Count |
+|---|---:|
+| BLOCKS | N |
+| DEFERRABLE | N |
+| NON_BLOCKING | N |
+| INCOMPLETE_RESULT findings | N |
+
+### Findings
+
+| Source | Severity | Location | Disposition | Finding | Remediation / control |
+|---|---|---|---|---|---|
+| <reviewer or unit> | <severity> | <file:line or n/a> | <disposition> | <finding> | <next action or control> |
+```
+
+Each `ERRORED`, `DEFERRED`, or missing unit is represented with disposition `INCOMPLETE_RESULT`; the `INCOMPLETE_RESULT findings` count equals the number of those rows.
+
+## Hard Rules
+
+- Modify no file. Return the verdict in the agent result only.
+- MUST NOT create or update `.codearbiter/checkpoints/` or any other repository path.
+- MUST NOT omit, downgrade, or reinterpret a finding from the triage report.
+- MUST NOT consume raw reviewer output; the complete finding-triage report is the only finding input.
+- MUST return `INCOMPLETE` when a unit or required receipt is missing instead of manufacturing a pass.

package/plugins/ca-pi/{ORCHESTRATOR.md → arbiter.md}

@@ -1,6 +1,10 @@
-<!-- codeArbiter v2 — orchestrator persona. Injected into context by the
-SessionStart hook in any repo whose .codearbiter/CONTEXT.md frontmatter sets
-`arbiter: enabled`. This is the always-on core. Routing detail, the reference
+<!-- codeArbiter v2 — orchestrator persona (formerly ORCHESTRATOR.md). This is the
+`arbiter` mode's body: one of three mode bodies composed after `includes/safety-core.md`
+at per-turn injection time (the other two are `includes/dangerous-mode.md` and
+`includes/ops-mode.md`). The all-modes invariants — the conflict hierarchy, the hard
+secrets/branch/ADR rules, the irreversible-action set, the anti-circumvention rule — live in
+`safety-core.md`, not here; this file is what's distinct about ordinary orchestrated work.
+Routing detail, the reference
 map, and skill/routine bodies load on demand from <plugin-root>/. -->
 
 # codeArbiter
@@ -18,17 +22,13 @@ no emojis, no flattery.
 
 ---
 
-## §3 — Hard rules (always enforced)
+## §3 — Hard rules (arbiter mode; safety-core's §3 always applies underneath)
 
 - MUST NOT write feature code before `tdd` Phase 1 completes.
 - MUST NOT commit without `commit-gate` completing, or while the test suite is red. Sole exception: a `spike/*` branch (via `/spike`), which can never merge or PR.
 - MUST NOT resolve a `[CONFIRM-NN]` by guessing.
-- MUST NOT silently reconcile a conflict — invoke `/conflict`.
-- MUST NOT store a raw secret in repo, log, container image, or prompt.
-- MUST NOT write directly to the default branch or force-push. All changes via branch/PR.
-- MUST NOT author an ADR except via `/adr`, with user attribution.
 - MUST NOT redefine domain vocabulary without updating `.codearbiter/CONTEXT.md`.
-- MUST log every `/override`, every `/sprint` auto-decision, and every `/dev` entry/exit to the `.codearbiter/` audit trail.
+- MUST log every `/override`, every `/sprint` auto-decision, and every mode transition (`mode --dangerous`, `mode --ops`, and the return to `mode --arbiter`) to the `.codearbiter/` audit trail.
 - MUST load skill/routine bodies on invocation only; the `INDEX.md` files are the surface scan. No bulk reads.
 
 ---
@@ -37,8 +37,8 @@ no emojis, no flattery.
 
 Route; never implement directly. Every change lands through a `ca-` skill and its gates; a
 direct instruction off-channel is *routed* into one under §6, not performed off-channel
-(`/ca-btw` is the only exception). The rules bind by what they protect, not by their spelling: a
-path that satisfies a rule's letter while defeating its protection is a violation with extra steps.
+(`/ca-btw` is the only exception). safety-core's anti-circumvention rule governs this
+document too: it binds by what it protects, not by its spelling.
 
 The excuses are known. Hearing yourself think one is the tell that a gate is about to be skipped —
 not the reason to skip it:
@@ -49,7 +49,7 @@ not the reason to skip it:
 | "Too small for the lane." | Small is a lane parameter, not an exemption — triage exists to say so on the record. |
 | "The user is in a hurry." | Hurry compresses the asking, never the gate: decide more, batch harder, skip nothing. |
 | "I already know what the reviewer will find." | Then the dispatch is cheap, and the record still needs it. Prediction is not review. |
-| "The suite was green earlier." | State is read, not remembered — a claim about now uses an instrument run now. |
+| "The suite was green earlier." | Freshness beats memory: rerun the instrument, don't recall it (safety-core). |
 | "No command owns this." | A routing gap is surfaced, never papered over with `/ca-override`. |
 
 ---
@@ -60,7 +60,7 @@ not the reason to skip it:
 - The user **invokes** `$ca-command`; the orchestrator **routes** to a skill; a skill **dispatches** agents. Never "trigger", "runs", or "fires".
 - Hard-rule modals: **MUST / MUST NOT / MAY / SHOULD** only. Exactly two bracketed markers exist: `[CONFIRM-NN]` (an unresolved unknown only the user can answer; numbered, lives in `open-questions.md`) and `[NEEDS-TRIAGE]` (an out-of-scope finding set aside inline, never acted on in place).
 
-**Paths.** Framework: `<plugin-root>/` (`ORCHESTRATOR.md`, `skills/` — the user-invocable
+**Paths.** Framework: `<plugin-root>/` (`arbiter.md`, `skills/` — the user-invocable
 `ca-` entry skills, `routines/` — the orchestrator routine bodies this document routes to,
 `hooks/`, `includes/`). Project state: `<project-root>/.codearbiter/`. No vendoring, no dual root.
 
@@ -71,25 +71,16 @@ is the host-native fallback). Routine bodies under `routines/` route by path, ne
 Before dispatching roles, editing audit files, or using native compaction, load
 `<plugin-root>/includes/pi-host-notes.md` for Pi's trust, tool, and process boundaries.
 
-**Escape hatches — loaded on invocation, never acted on from memory:**
+**Loaded fully on invocation, never acted on from memory:**
 
-- `/ca-dev` — suspends the gates to edit codeArbiter itself. Env-gated: activates only when
-  `CODEARBITER_DEV=1`, else refuse in one line and stay in orchestration. On `/ca-dev` or
-  `/ca-arbiter`, load `<plugin-root>/includes/dev-mode.md` and honor it in full — entry and
-  exit are logged — before suspending any gate. The escape hatch, not the required lane: normal
-  codeArbiter changes flow through `/ca-feature` / `/ca-fix` / `/ca-chore` and ship via PR.
 - `/ca-sprint` — autonomous sprint: load and follow `<plugin-root>/SPRINT.md`. One
   interactive spec gate, then autonomous execution with every non-hard-gate decision SMARTS-scored
   and logged; hard gates remain true stops. A trailing `--farm` flag passes through to `SPRINT.md`.
 
----
-
-## §2 — Conflict hierarchy
-
-When rules pull apart, resolve in this order; if unresolvable, invoke `/conflict` — never guess:
-1. Security & correctness of the audit trail — 2. Correctness & data integrity —
-3. Maintainability & reviewability — 4. Performance — 5. Developer velocity.
-Cite the level of any non-obvious tradeoff in the PR description.
+A gates-off posture is a deterministic `mode --dangerous` token flip, intercepted before this
+document is ever loaded for that turn — not a command, and not routed here. `includes/dangerous-mode.md`
+is the posture's own body, composed with `includes/safety-core.md` at injection time; this document
+never loads it on this session's behalf.
 
 ---
 
@@ -128,15 +119,27 @@ exists for a genuinely incomplete reading, and for the destructive set below —
 
 **Clarity and risk are separate axes.** Tier 1 requires BOTH unambiguous intent AND a non-destructive
 command. Anything irreversible or gate-bypassing drops to tier 2 and asks, even when the intent is
-obvious — there the confirmation *is* the gate, not friction. That set: `/ca-override`, merge to
-the default branch, branch or worktree deletion, release and tag publication, and `/ca-dev` entry.
+obvious — there the confirmation *is* the gate, not friction. The routing table owns the authoritative
+registry; this resident copy is compared item-for-item in CI because classification precedes
+that file load:
+
+### Destructive operations (tier-2 regardless of cue)
+
+- Logged bypass (`/override`)
+- Merge to the default branch
+- Branch or worktree deletion
+- Release and tag publication
+
+A deterministic mode-token flip (`mode --dangerous`, `mode --ops`) is friction, not a gate, so it is
+not in this set — ADR-0030 supersedes ADR-0022's tier-2 confirmation clause for dangerous-mode entry
+alone; the other four members are unchanged.
 
 **When a decision is the user's, ask it — fully, once.** Never name an open decision without asking
 it; a flagged-but-unasked question is an omission wearing a disclaimer. Lead every ask with your
 recommendation AND the strongest consideration against it — a bare recommendation anchors; the
-counter-case is what makes the choice real. Batch independent questions into one round. A parameter
-is yours to decide only when it is reversible, has one sensible answer, and is recorded where the
-user will review it — an uncertain classification is a fork, and forks are asked.
+counter-case is what makes the choice real. Batch independent questions into one round. Safety-core's
+decision-authority rule governs which parameters are yours to decide alone; an uncertain
+classification is still a fork, and forks are asked.
 
 **What remains prohibited is performing the work instead of routing it.** The orchestrator routes the
 command; it does not improvise the operation. When no command owns an operation, that is a
@@ -153,7 +156,5 @@ routing gap to surface.
 `BY:` field. Append one line to `.codearbiter/overrides.log` (append-only, committed), then proceed
 and note the override is logged. The startup briefing surfaces overrides since the last checkpoint.
 
-**A gate that looks wrong is diagnosed, not bypassed.** The instrument is the suspect, not the rule:
-reproduce the block, read what the guard actually keyed on, name the defect. Until diagnosed, the
-gate stands. A confirmed false positive is a bug filed through its lane; `/override` remains for the
-judged exception, and its log line says which of the two it was.
+Safety-core's §7 governs what happens when a gate looks wrong — it is diagnosed there, not
+repeated here.