Refactor agent management commands to replace assign_task with followup_task across multiple skills and roles. Update wait_agent calls to remove target specifications for improved clarity and consistency. Adjust documentation to reflect these changes in message semantics and tool usage.

Author: catlog22

.codex/skills/brainstorm/SKILL.md

@@ -5,7 +5,7 @@ description: |
   (spawn_agents_on_csv) → cross-role synthesis. Single role mode: individual role analysis.
   CSV-driven parallel coordination with NDJSON discovery board.
 argument-hint: "[-y|--yes] [--count N] [--session ID] [--skip-questions] [--style-skill PKG] \"topic\" | <role-name> [--session ID]"
-allowed-tools: spawn_agents_on_csv, spawn_agent, wait_agent, send_message, assign_task, close_agent, request_user_input, Read, Write, Edit, Bash, Glob, Grep
+allowed-tools: spawn_agents_on_csv, spawn_agent, wait_agent, send_message, followup_task, close_agent, request_user_input, Read, Write, Edit, Bash, Glob, Grep
 ---
 
 ## Auto Mode
@@ -556,7 +556,7 @@ Follow the same analysis protocol as wave role analysis but with interactive ref
 `
   })
 
-  wait_agent({ targets: [agentId] })
+  wait_agent()
   close_agent({ target: agentId })
 
   console.log(`\n✓ ${roleName} analysis complete: ${roleDir}/analysis.md`)
@@ -631,7 +631,7 @@ Evaluate complexity score (0-8):
 `
    })
 
-   wait_agent({ targets: [synthesisAgent] })
+   wait_agent()
    close_agent({ target: synthesisAgent })
    ```
 

.codex/skills/ccw-coordinate/SKILL.md

@@ -2,7 +2,7 @@
 name: ccw-coordinate
 description: Team-agent pipeline coordinator — classifies intent via structured extraction (action × object × style), maps to skill chain, spawns one agent per step whose prompt contains the skill invocation ($skill-name "intent"). Step results propagate as context to each successor. Session state at .workflow/.ccw-coordinate/{session-id}/state.json.
 argument-hint: "\"intent text\" [-y] [-c|--continue] [--dry-run] [--chain <name>]"
-allowed-tools: spawn_agent, wait, send_input, close_agent, Read, Write, Bash, Glob, Grep
+allowed-tools: spawn_agent, wait_agent, send_message, followup_task, close_agent, Read, Write, Bash, Glob, Grep
 ---
 
 ## Auto Mode
@@ -318,10 +318,10 @@ for (const step of state.steps.filter(s => s.status === 'pending')) {
   const agent = spawn_agent({ message: stepPrompt })
 
   // Wait — with timeout urge
-  let result = wait({ ids: [agent], timeout_ms: 600000 })
+  let result = wait_agent({ timeout_ms: 600000 })
   if (result.timed_out) {
-    send_input({ id: agent, message: "Please wrap up and output your findings JSON now." })
-    result = wait({ ids: [agent], timeout_ms: 120000 })
+    followup_task({ target: agent, message: "Please wrap up and output your findings JSON now." })
+    result = wait_agent({ timeout_ms: 120000 })
   }
 
   // Parse structured output from agent
@@ -331,7 +331,7 @@ for (const step of state.steps.filter(s => s.status === 'pending')) {
     hints_for_next: ""
   }
 
-  close_agent({ id: agent })
+  close_agent({ target: agent })
 
   // Persist step result
   step.status = result.timed_out ? "failed" : "completed"
@@ -460,6 +460,6 @@ Resume: $ccw-coordinate --continue
 5. **Skip on Failure**: Step failure immediately marks all remaining steps `skipped` and aborts the loop
 6. **Close before spawn**: Always `close_agent` the current step agent before spawning the next
 7. **Dry-run is read-only**: Stop after displaying the chain plan — never spawn agents
-8. **Timeout handling**: One urge via `send_input`; if still timed out → mark `failed`
+8. **Timeout handling**: One urge via `followup_task`; if still timed out → mark `failed`
 9. **No CLI fallback**: All execution is agent-native — no `exec_command("maestro cli ...")`
 10. **Semantic Routing**: Use LLM structured extraction (`action × object × style`) not regex for intent classification

.codex/skills/clean/SKILL.md

@@ -204,11 +204,11 @@ Format:
   })
 
   // Wait with timeout handling
-  let result = wait_agent({ targets: [exploreAgent], timeout_ms: 600000 })
+  let result = wait_agent({ timeout_ms: 600000 })
 
   if (result.timed_out) {
-    assign_task({ target: exploreAgent, items: [{ type: "text", text: "Complete now and write cleanup-manifest.json." }] })
-    result = wait_agent({ targets: [exploreAgent], timeout_ms: 300000 })
+    followup_task({ target: exploreAgent, message: "Complete now and write cleanup-manifest.json." })
+    result = wait_agent({ timeout_ms: 300000 })
     if (result.timed_out) throw new Error('Agent timeout')
   }
 

.codex/skills/investigate/agents/investigator.md

@@ -1,14 +1,14 @@
 # Investigator Agent
 
-Executes all 5 phases of the systematic debugging investigation under the Iron Law methodology. Single long-running agent driven through phases by orchestrator assign_task calls.
+Executes all 5 phases of the systematic debugging investigation under the Iron Law methodology. Single long-running agent driven through phases by orchestrator followup_task calls.
 
 ## Identity
 
 - **Type**: `investigation`
 - **Role File**: `~/.codex/skills/investigate/agents/investigator.md`
 - **task_name**: `investigator`
 - **Responsibility**: Full 5-phase investigation execution — evidence collection, pattern search, hypothesis testing, minimal fix, verification
-- **fork_context**: false
+- **fork_turns**: "none"
 - **Reasoning Effort**: high
 
 ## Boundaries
@@ -23,7 +23,7 @@ Executes all 5 phases of the systematic debugging investigation under the Iron L
 - Implement only minimal fix — change only what addresses the confirmed root cause
 - Add a regression test that fails without the fix and passes with it
 - Write the final debug report to `.workflow/.debug/` using the schema in `~/.codex/skills/investigate/specs/debug-report-format.md`
-- Produce structured output after each phase, then await next assign_task
+- Produce structured output after each phase, then await next followup_task
 
 ### MUST NOT
 
@@ -75,7 +75,7 @@ Executes all 5 phases of the systematic debugging investigation under the Iron L
 
 | Source | Required | Description |
 |--------|----------|-------------|
-| assign_task message | Yes | Bug description, symptoms, error messages, context |
+| followup_task message | Yes | Bug description, symptoms, error messages, context |
 | Phase file | Yes | `~/.codex/skills/investigate/phases/01-root-cause-investigation.md` |
 
 **Steps**:
@@ -89,7 +89,7 @@ Executes all 5 phases of the systematic debugging investigation under the Iron L
 4. Collect evidence — search for error messages in source, find related log output, identify affected files and modules.
 5. Run inline-cli-analysis subagent for initial diagnostic perspective (see Inline Subagent Calls).
 6. Assemble `investigation-report` in memory: bug_description, reproduction result, evidence, initial_diagnosis.
-7. Output Phase 1 summary and await assign_task for Phase 2.
+7. Output Phase 1 summary and await followup_task for Phase 2.
 
 **Output**: In-memory investigation-report (phase 1 fields populated)
 
@@ -103,7 +103,7 @@ Executes all 5 phases of the systematic debugging investigation under the Iron L
 
 | Source | Required | Description |
 |--------|----------|-------------|
-| assign_task message | Yes | Phase 2 instruction |
+| followup_task message | Yes | Phase 2 instruction |
 | Phase file | Yes | `~/.codex/skills/investigate/phases/02-pattern-analysis.md` |
 | investigation-report | Yes | Phase 1 output in context |
 
@@ -118,7 +118,7 @@ Executes all 5 phases of the systematic debugging investigation under the Iron L
 7. Classify scope: `isolated` | `module-wide` | `systemic` with justification.
 8. Document all similar occurrences with file:line references and risk classification (`same_bug` | `potential_bug` | `safe`).
 9. Add `pattern_analysis` section to investigation-report in memory.
-10. Output Phase 2 summary and await assign_task for Phase 3.
+10. Output Phase 2 summary and await followup_task for Phase 3.
 
 **Output**: investigation-report with pattern_analysis section added
 
@@ -132,7 +132,7 @@ Executes all 5 phases of the systematic debugging investigation under the Iron L
 
 | Source | Required | Description |
 |--------|----------|-------------|
-| assign_task message | Yes | Phase 3 instruction |
+| followup_task message | Yes | Phase 3 instruction |
 | Phase file | Yes | `~/.codex/skills/investigate/phases/03-hypothesis-testing.md` |
 | investigation-report | Yes | Phase 1-2 output in context |
 
@@ -154,7 +154,7 @@ Executes all 5 phases of the systematic debugging investigation under the Iron L
 
 6. If strike counter reaches 3 — STOP immediately. Output escalation block (see 3-Strike Escalation Output below). Set status BLOCKED.
 7. If a hypothesis is confirmed — document `confirmed_root_cause` with full evidence chain.
-8. Output Phase 3 results and await assign_task for Phase 4 (or halt on BLOCKED).
+8. Output Phase 3 results and await followup_task for Phase 4 (or halt on BLOCKED).
 
 **3-Strike Escalation Output**:
 
@@ -203,7 +203,7 @@ STATUS: BLOCKED
 
 | Source | Required | Description |
 |--------|----------|-------------|
-| assign_task message | Yes | Phase 4 instruction |
+| followup_task message | Yes | Phase 4 instruction |
 | Phase file | Yes | `~/.codex/skills/investigate/phases/04-implementation.md` |
 | investigation-report | Yes | Must contain confirmed_root_cause |
 
@@ -233,7 +233,7 @@ STATUS: BLOCKED
    - Test must be deterministic
 6. Re-run the original reproduction case from Phase 1. Verify it now passes.
 7. Add `fix_applied` section to investigation-report in memory.
-8. Output Phase 4 summary and await assign_task for Phase 5.
+8. Output Phase 4 summary and await followup_task for Phase 5.
 
 **Output**: Modified source files, regression test file; investigation-report with fix_applied section
 
@@ -247,7 +247,7 @@ STATUS: BLOCKED
 
 | Source | Required | Description |
 |--------|----------|-------------|
-| assign_task message | Yes | Phase 5 instruction |
+| followup_task message | Yes | Phase 5 instruction |
 | Phase file | Yes | `~/.codex/skills/investigate/phases/05-verification-report.md` |
 | investigation-report | Yes | All phases populated |
 
@@ -301,7 +301,7 @@ This agent spawns a utility subagent for cross-file diagnostic analysis during P
 ```
 spawn_agent({
   task_name: "inline-cli-analysis",
-  fork_context: false,
+  fork_turns: "none",
   model: "haiku",
   reasoning_effort: "medium",
   message: `### MANDATORY FIRST STEPS
@@ -317,7 +317,7 @@ CONSTRAINTS: Read-only analysis | Focus on <affected_module>>
 
 Expected: Structured findings with file:line references`
 })
-const result = wait_agent({ targets: ["inline-cli-analysis"], timeout_ms: 180000 })
+const result = wait_agent({ timeout_ms: 180000 })
 close_agent({ target: "inline-cli-analysis" })
 ```
 
@@ -337,7 +337,7 @@ Substitute the analysis task description with phase-appropriate content:
 
 ## Structured Output Template
 
-After each phase, output the following structure before awaiting the next assign_task:
+After each phase, output the following structure before awaiting the next followup_task:
 
 ```
 ## Phase <N> Complete

.codex/skills/investigate/orchestrator.md

@@ -26,7 +26,7 @@ Systematic debugging skill that enforces the Iron Law: never fix without a confi
                     |   5-phase loop)  |
                     +------------------+
                         |   ^   |
-          assign_task   |   |   |  assign_task
+          followup_task   |   |   |  followup_task
           (Phase 2-5)   v   |   v  (Phase 3 gate check)
                     +------------------+
                     | Phase 1: Root    |
@@ -44,26 +44,26 @@ Systematic debugging skill that enforces the Iron Law: never fix without a confi
 
 ## Agent Registry
 
-| Agent | task_name | Role File | Responsibility | Pattern | fork_context |
+| Agent | task_name | Role File | Responsibility | Pattern | fork_turns |
 |-------|-----------|-----------|----------------|---------|-------------|
-| investigator | `investigator` | `~/.codex/skills/investigate/agents/investigator.md` | Full 5-phase investigation execution | Deep Interaction (2.3) | false |
+| investigator | `investigator` | `~/.codex/skills/investigate/agents/investigator.md` | Full 5-phase investigation execution | Deep Interaction (2.3) | "none" |
 
 > **COMPACT PROTECTION**: Agent files are execution documents. When context compression occurs and agent instructions are reduced to summaries, **you MUST immediately `Read` the corresponding agent.md to reload before continuing execution**.
 
 ---
 
 ## Fork Context Strategy
 
-| Agent | task_name | fork_context | fork_from | Rationale |
+| Agent | task_name | fork_turns | fork_from | Rationale |
 |-------|-----------|-------------|-----------|-----------|
-| investigator | `investigator` | false | — | Starts fresh; receives all phase context via assign_task messages. No prior conversation history needed. |
+| investigator | `investigator` | "none" | — | Starts fresh; receives all phase context via followup_task messages. No prior conversation history needed. |
 
 **Fork Decision Rules**:
 
-| Condition | fork_context | Reason |
+| Condition | fork_turns | Reason |
 |-----------|-------------|--------|
-| investigator spawned (Phase 1) | false | Clean context; full task description in message |
-| Phase 2-5 transitions | N/A | assign_task used, agent already running |
+| investigator spawned (Phase 1) | "none" | Clean context; full task description in message |
+| Phase 2-5 transitions | N/A | followup_task used, agent already running |
 
 ---
 
@@ -112,7 +112,7 @@ Build the initial spawn message embedding the bug report and Phase 1 instruction
 ```
 spawn_agent({
   task_name: "investigator",
-  fork_context: false,
+  fork_turns: "none",
   message: `## TASK ASSIGNMENT
 
 ### MANDATORY FIRST STEPS (Agent Execute)
@@ -132,7 +132,7 @@ Execute Phase 1 per the phase file. Produce investigation-report (in-memory) and
 - Await next phase assignment.`
 })
 
-const p1Result = wait_agent({ targets: ["investigator"], timeout_ms: 300000 })
+const p1Result = wait_agent({ timeout_ms: 300000 })
 ```
 
 **Output**:
@@ -158,7 +158,7 @@ const p1Result = wait_agent({ targets: ["investigator"], timeout_ms: 300000 })
 **Execution**:
 
 ```
-assign_task({
+followup_task({
   target: "investigator",
   items: [{
     type: "text",
@@ -176,7 +176,7 @@ Report back with pattern_analysis section and scope classification. Await next p
   }]
 })
 
-const p2Result = wait_agent({ targets: ["investigator"], timeout_ms: 300000 })
+const p2Result = wait_agent({ timeout_ms: 300000 })
 ```
 
 **Output**:
@@ -202,7 +202,7 @@ const p2Result = wait_agent({ targets: ["investigator"], timeout_ms: 300000 })
 **Execution**:
 
 ```
-assign_task({
+followup_task({
   target: "investigator",
   items: [{
     type: "text",
@@ -222,7 +222,7 @@ Report back with hypothesis test results and either:
   }]
 })
 
-const p3Result = wait_agent({ targets: ["investigator"], timeout_ms: 480000 })
+const p3Result = wait_agent({ timeout_ms: 480000 })
 ```
 
 **Phase 3 Gate Decision**:
@@ -232,7 +232,7 @@ const p3Result = wait_agent({ targets: ["investigator"], timeout_ms: 480000 })
 | p3Result contains `confirmed_root_cause` | Proceed to Phase 4 |
 | p3Result contains `BLOCKED` | Halt workflow, output escalation dump to user, close investigator |
 | p3Result contains `ESCALATION: 3-Strike Limit Reached` | Halt workflow, output diagnostic dump, close investigator |
-| Timeout | assign_task "Finalize Phase 3 results now", re-wait 120s; if still timeout → halt |
+| Timeout | followup_task "Finalize Phase 3 results now", re-wait 120s; if still timeout → halt |
 
 If BLOCKED: close investigator and surface the diagnostic dump to the user. Do not proceed to Phase 4.
 
@@ -253,7 +253,7 @@ If BLOCKED: close investigator and surface the diagnostic dump to the user. Do n
 **Execution**:
 
 ```
-assign_task({
+followup_task({
   target: "investigator",
   items: [{
     type: "text",
@@ -272,7 +272,7 @@ Report back with fix_applied section. Await Phase 5 assignment.`
   }]
 })
 
-const p4Result = wait_agent({ targets: ["investigator"], timeout_ms: 480000 })
+const p4Result = wait_agent({ timeout_ms: 480000 })
 ```
 
 **Output**:
@@ -298,7 +298,7 @@ const p4Result = wait_agent({ targets: ["investigator"], timeout_ms: 480000 })
 **Execution**:
 
 ```
-assign_task({
+followup_task({
   target: "investigator",
   items: [{
     type: "text",
@@ -316,7 +316,7 @@ Final phase:
   }]
 })
 
-const p5Result = wait_agent({ targets: ["investigator"], timeout_ms: 300000 })
+const p5Result = wait_agent({ timeout_ms: 300000 })
 ```
 
 **Output**:
@@ -335,11 +335,11 @@ const p5Result = wait_agent({ targets: ["investigator"], timeout_ms: 300000 })
 
 | Phase | Default Timeout | On Timeout |
 |-------|-----------------|------------|
-| Phase 1 (spawn + wait) | 300000 ms | assign_task "Finalize Phase 1 now" + wait 120s; if still timeout → halt |
-| Phase 2 (assign + wait) | 300000 ms | assign_task "Finalize Phase 2 now" + wait 120s; if still timeout → halt |
-| Phase 3 (assign + wait) | 480000 ms | assign_task "Finalize Phase 3 now" + wait 120s; if still timeout → halt BLOCKED |
-| Phase 4 (assign + wait) | 480000 ms | assign_task "Finalize Phase 4 now" + wait 120s; if still timeout → halt |
-| Phase 5 (assign + wait) | 300000 ms | assign_task "Finalize Phase 5 now" + wait 120s; if still timeout → partial report |
+| Phase 1 (spawn + wait) | 300000 ms | followup_task "Finalize Phase 1 now" + wait 120s; if still timeout → halt |
+| Phase 2 (assign + wait) | 300000 ms | followup_task "Finalize Phase 2 now" + wait 120s; if still timeout → halt |
+| Phase 3 (assign + wait) | 480000 ms | followup_task "Finalize Phase 3 now" + wait 120s; if still timeout → halt BLOCKED |
+| Phase 4 (assign + wait) | 480000 ms | followup_task "Finalize Phase 4 now" + wait 120s; if still timeout → halt |
+| Phase 5 (assign + wait) | 300000 ms | followup_task "Finalize Phase 5 now" + wait 120s; if still timeout → partial report |
 
 ### Cleanup Protocol
 
@@ -355,13 +355,13 @@ close_agent({ target: "investigator" })
 
 | Scenario | Resolution |
 |----------|------------|
-| Agent timeout (first) | assign_task "Finalize current work and output results" + re-wait 120000 ms |
+| Agent timeout (first) | followup_task "Finalize current work and output results" + re-wait 120000 ms |
 | Agent timeout (second) | close_agent, report partial results to user |
 | Phase 3 BLOCKED | close_agent, surface full escalation dump to user, halt |
 | Phase 4 Iron Law violation | close_agent, report "Cannot proceed: no confirmed root cause" |
 | Phase 4 introduces regression | Investigator returns to fix adjustment; orchestrator re-waits same phase |
 | User cancellation | close_agent({ target: "investigator" }), report current state |
-| send_message ignored | Escalate to assign_task |
+| send_message ignored | Escalate to followup_task |
 
 ---