@arbiterforge/ca-pi 0.8.1 → 0.10.0

package/plugins/ca-pi/SKILLS.md

@@ -4,42 +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-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-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/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/arbiter.md

@@ -119,9 +119,18 @@ 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 (safety-core's §6): `/ca-override`,
-merge to the default branch, branch or worktree deletion, and release and tag publication. A
-deterministic mode-token flip (`mode --dangerous`, `mode --ops`) is friction, not a gate, so it is
+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.
 

package/plugins/ca-pi/extensions/codearbiter.js

@@ -9722,6 +9722,88 @@ async function appendPiCompactionAudit(record2) {
 }
 
 // src/extension.ts
+var COMMAND_VISIBILITY_ORDER = ["core", "advanced", "alias", "internal", "deprecated"];
+var COMMAND_WORKFLOW_ORDER = [
+  "evaluate",
+  "initialize",
+  "change",
+  "review",
+  "decide",
+  "ship",
+  "operate",
+  "extend",
+  "help"
+];
+function plainRecord2(value) {
+  return value !== null && typeof value === "object" && !Array.isArray(value) && Object.getPrototypeOf(value) === Object.prototype;
+}
+function sameStrings2(actual, expected) {
+  return actual.length === expected.length && actual.every((item, index) => item === expected[index]);
+}
+function validLegacyRoutes(value) {
+  return Array.isArray(value) && value.every((item) => typeof item === "string" && /^[a-z][a-z0-9-]*$/u.test(item)) && new Set(value).size === value.length && sameStrings2(value, [...value].sort());
+}
+function commandCatalogEntries(value) {
+  const envelopeKeys = ["commands", "compatibility", "schemaVersion", "visibilityOrder", "workflowOrder"];
+  if (!plainRecord2(value) || !sameStrings2(Object.keys(value).sort(), envelopeKeys) || value.schemaVersion !== 1 || !Array.isArray(value.visibilityOrder) || !sameStrings2(value.visibilityOrder, COMMAND_VISIBILITY_ORDER) || !Array.isArray(value.workflowOrder) || !sameStrings2(value.workflowOrder, COMMAND_WORKFLOW_ORDER) || !plainRecord2(value.compatibility) || !plainRecord2(value.commands)) {
+    throw new Error("codeArbiter Pi command catalog envelope is invalid; run /ca-doctor.");
+  }
+  const commands = value.commands;
+  const names = Object.keys(commands);
+  if (!sameStrings2(names, [...names].sort()) || names.length === 0) {
+    throw new Error("codeArbiter Pi command catalog envelope has no sorted commands; run /ca-doctor.");
+  }
+  const entries = [];
+  for (const name of names) {
+    const fail2 = () => {
+      throw new Error(`codeArbiter Pi command catalog entry ${name} is invalid; run /ca-doctor.`);
+    };
+    const value2 = commands[name];
+    if (!plainRecord2(value2)) {
+      throw new Error(`codeArbiter Pi command catalog entry ${name} is invalid; run /ca-doctor.`);
+    }
+    const raw = value2;
+    if (raw.name !== name || typeof raw.description !== "string" || raw.description === "" || raw.skillPath !== `skills/ca-${name}/SKILL.md` || !COMMAND_VISIBILITY_ORDER.includes(raw.visibility) || !COMMAND_WORKFLOW_ORDER.includes(raw.workflow)) {
+      fail2();
+    }
+    const visibility = raw.visibility;
+    const commonKeys = ["description", "name", "skillPath", "visibility", "workflow"];
+    let expectedKeys;
+    if (visibility === "core" || visibility === "advanced" || visibility === "internal") {
+      expectedKeys = [...commonKeys, "canonical", "legacyRoutes"].sort();
+      if (raw.canonical !== name || !validLegacyRoutes(raw.legacyRoutes)) fail2();
+    } else if (visibility === "alias") {
+      expectedKeys = [...commonKeys, "canonical", "replacement"].sort();
+      if (typeof raw.canonical !== "string" || !/^[a-z][a-z0-9-]*$/u.test(raw.canonical) || typeof raw.replacement !== "string" || !raw.replacement.startsWith(`${raw.canonical} `)) fail2();
+    } else {
+      expectedKeys = [...commonKeys, "replacement"].sort();
+      if (typeof raw.replacement !== "string" || raw.replacement === "") fail2();
+    }
+    if (!sameStrings2(Object.keys(raw).sort(), expectedKeys)) fail2();
+    entries.push(Object.freeze({ ...raw }));
+  }
+  const entriesByName = new Map(entries.map((entry) => [entry.name, entry]));
+  const expectedLegacyRoutes = /* @__PURE__ */ new Map();
+  for (const entry of entries) {
+    if (entry.visibility === "alias") {
+      const target = entriesByName.get(entry.canonical);
+      if (target === void 0 || target.visibility === "alias" || target.visibility === "deprecated") {
+        throw new Error(`codeArbiter Pi command catalog entry ${entry.name} has an invalid alias target; run /ca-doctor.`);
+      }
+      const routes = expectedLegacyRoutes.get(entry.canonical) ?? [];
+      routes.push(entry.name);
+      expectedLegacyRoutes.set(entry.canonical, routes);
+    }
+  }
+  for (const entry of entries) {
+    if (entry.visibility === "alias" || entry.visibility === "deprecated") continue;
+    const expected = (expectedLegacyRoutes.get(entry.name) ?? []).sort();
+    if (!sameStrings2(entry.legacyRoutes ?? [], expected)) {
+      throw new Error(`codeArbiter Pi command catalog entry ${entry.name} has broken legacy-route closure; run /ca-doctor.`);
+    }
+  }
+  return Object.freeze(entries);
+}
 var PI_TRUST_REQUIRED_STATUS = "codeArbiter host: pi waiting for project trust - run /trust in Pi, approve this project, then start a new session";
 function hasAffirmativeProjectTrust(context) {
   try {
@@ -10257,7 +10339,9 @@ async function codeArbiterPi(pi) {
     if (parent === packageRoot) throw new Error("codeArbiter could not locate the ca-pi package; run /ca-doctor.");
     packageRoot = parent;
   }
-  const catalog = JSON.parse(await readFile6(resolve15(packageRoot, "generated", "command-catalog.json"), "utf8"));
+  const catalog = commandCatalogEntries(
+    JSON.parse(await readFile6(resolve15(packageRoot, "generated", "command-catalog.json"), "utf8"))
+  );
   const toolClasses = loadPiToolClasses(define_CODEARBITER_PI_TOOL_CLASSES_default);
   const rawPermissionSurfaces = define_CODEARBITER_PI_PERMISSION_POLICY_SURFACES_default;
   if (rawPermissionSurfaces === null || typeof rawPermissionSurfaces !== "object" || Array.isArray(rawPermissionSurfaces)) {
@@ -10532,6 +10616,7 @@ export {
   PERSONA_SENTINEL,
   PI_RUNTIME_DIAGNOSIS,
   boundedPiEnvironment,
+  commandCatalogEntries,
   compatibilityDirection,
   createCodeArbiterPi,
   createPiFooterMetricsLoader,