fix: resolve review round 2 findings

- CLAUDE.md: add missing message-schema and project to skill list
- debugger, documenter: add qa-checklist to skills (worker-protocol references it)
- message-schema: make moderate_count/minor_count required on review_verdict,
  make has_blockers required on plan_result, remove dangling format field
- orchestrate: split blocked routing by type (plan_result vs worker_submission)
- worker-protocol: remove stale migration note about freetext RFR
- qa-checklist: add plan_result has_blockers hard rule
- architect: remove dangling format field from plan_result envelope

CLAUDE.md

@@ -1,4 +1,4 @@
 # Global Claude Code Instructions
 
 Rules are modularized in `~/.claude/rules/` and loaded automatically.
-Agent-team specific protocols live in skills (orchestrate, conventions, worker-protocol, qa-checklist).
+Agent-team specific protocols live in skills (orchestrate, conventions, worker-protocol, qa-checklist, message-schema, project).

agents/architect.md

@@ -104,7 +104,6 @@ After writing the plan file, return a `plan_result` envelope:
 type: plan_result
 signal: plan_complete | blocked
 plan_file: .claude/plans/kebab-case-title.md
-format: brief | full
 wave_count: 3
 step_count: 7
 risk_tags:

agents/debugger.md

@@ -9,6 +9,7 @@ skills:
   - conventions
   - worker-protocol
   - message-schema
+  - qa-checklist
   - project
 ---
 

agents/documenter.md

@@ -10,6 +10,7 @@ skills:
   - conventions
   - worker-protocol
   - message-schema
+  - qa-checklist
   - project
 ---
 

skills/message-schema/SKILL.md

@@ -90,8 +90,7 @@ ac_coverage:
 ---
 ```
 
-Required: `type`, `signal`, `critical_count`, `ac_coverage`
-Optional: `moderate_count`, `minor_count`
+Required: `type`, `signal`, `critical_count`, `moderate_count`, `minor_count`, `ac_coverage`
 
 **Hard rule:** `critical_count > 0` requires `signal: fail`.
 
@@ -153,7 +152,6 @@ Emitted by: architect (Phase 2)
 type: plan_result
 signal: plan_complete | blocked
 plan_file: .claude/plans/kebab-case-title.md
-format: brief | full
 wave_count: 3
 step_count: 7
 risk_tags:
@@ -163,8 +161,8 @@ has_blockers: false
 ---
 ```
 
-Required: `type`, `signal`, `plan_file`, `wave_count`, `risk_tags`
-Optional: `format`, `step_count`, `has_blockers`
+Required: `type`, `signal`, `plan_file`, `wave_count`, `risk_tags`, `has_blockers`
+Optional: `step_count`
 
 **Routing:** `has_blockers: true` triggers user escalation before worker dispatch.
 

skills/orchestrate/SKILL.md

@@ -228,7 +228,8 @@ All agent communication uses typed YAML frontmatter envelopes defined in the `me
 | `signal: triage_complete` | architect → you | Check `research_needed`, spawn researchers or resume architect |
 | `signal: plan_complete` | architect → you | Read plan file, begin wave dispatch |
 | `signal: research_complete` | researcher → you | Collect, assemble into Research Context |
-| `signal: blocked` | architect/worker → you | If from `plan_result`: escalate to user before dispatching workers. Otherwise: investigate or unblock. |
+| `signal: blocked` (`plan_result`) | architect → you | Escalate to user before dispatching workers |
+| `signal: blocked` (`worker_submission`) | worker → you | Investigate blocker, unblock or reassign |
 | `signal: escalate` | any → you | Escalate to user with context |
 
 When dispatching agents, use the orchestrator→agent envelope types (`task_assignment`, `revision_request`, `approval`, `triage_request`, `architecture_request`, `research_request`) from the message-schema skill.

skills/qa-checklist/SKILL.md

@@ -48,6 +48,7 @@ Before returning your output, validate against every item below. If you find a v
 - Are hard rules satisfied?
   - `review_verdict`: `critical_count > 0` requires `signal: fail`
   - `audit_verdict`: `security_findings.critical > 0` or `build_status: fail` or `test_status: fail` requires `signal: fail`
+  - `plan_result`: `has_blockers: true` requires orchestrator escalation to user before worker dispatch
 
 ## After validation
 

skills/worker-protocol/SKILL.md

@@ -51,7 +51,7 @@ Before returning your output, run the `qa-checklist` skill against your work. Fi
 
 ## Commits
 
-Do not commit until your orchestrator sends `signal: lgtm`. Your output envelope's `signal: rfr` replaces the old freetext `RFR` — the envelope IS the signal.
+Do not commit until your orchestrator sends `signal: lgtm`.
 
 - `signal: rfr` — you → orchestrator: work complete, ready for review
 - `signal: lgtm` — orchestrator → you: approved, commit now