@cleocode/skills 2026.9.21 → 2026.9.23

package/skills/ct-lead/SKILL.md

@@ -1,10 +1,14 @@
 ---
 name: ct-lead
-description: "Phase Lead orchestration playbook for spawning and supervising a parallel worker swarm in one wave. Use when spawned by ct-orchestrator with role=orchestrator to fan out N leaf workers via delegate_task, drain the epic-<TID>.wave-<n> conduit topic plus pipeline_manifest, await rollupWaveStatus convergence, and return ONE rolled-up contract string to the parent Orchestrator. Triggers: 'phase lead', 'wave lead', 'supervise wave', 'fan out workers', 'aggregate worker results', 'rollup wave', any task with role=orchestrator that is itself a child of another orchestrator. Implements ADR-070 hierarchical orchestration."
+description: "Phase Lead orchestration playbook for spawning and supervising a parallel worker swarm in one wave. Use when spawned by ct-orchestrator with role=orchestrator to fan out N leaf workers via delegate_task, drain the epic-{TID}.wave-{n} conduit topic plus pipeline_manifest, await rollupWaveStatus convergence, and return ONE rolled-up contract string to the parent Orchestrator. Triggers: 'phase lead', 'wave lead', 'supervise wave', 'fan out workers', 'aggregate worker results', 'rollup wave', any task with role=orchestrator that is itself a child of another orchestrator. Implements ADR-070 hierarchical orchestration."
 metadata:
-  version: 1.0.0
+  version: 1.0.6
   tier: core
   install: harness
+  covers:
+    - packages/core/src/orchestration/lead-rollup.ts
+    - packages/core/src/orchestration/waves.ts
+  lastReviewed: 2026-09-28
   stability: stable
 ---
 
@@ -33,7 +37,7 @@ exactly ONE aggregated summary.
 |----|------|-------------------|
 | LEAD-005 | Subscribe BEFORE spawn | Subscribe to `epic-<TID>.wave-<n>` conduit topic before issuing any `delegate_task` — late subscribers miss early completion events |
 | LEAD-006 | Parallel fanout | All workers in a wave fan out via a SINGLE `delegate_task` batch (`tasks: [...]`) — never sequential per-worker calls |
-| LEAD-007 | Bounded by `delegation.max_concurrent_children` | Wave width MUST NOT exceed the configured cap (default 10); split into multiple waves if larger |
+| LEAD-007 | Bounded by `maxConcurrent` (default 10) | Wave width MUST NOT exceed it; split into multiple waves if larger. No config key or runtime check enforces this yet (`delegation.max_concurrent_children` is not read by CLEO) — the Lead enforces it |
 | LEAD-008 | Convergence over polling | Wait on conduit signals + `rollupWaveStatus`; do not poll task status in a busy loop |
 | LEAD-009 | Roll up via `rollupWaveStatus` | Always call `rollupWaveStatus(epicId, waveId)` before returning — never hand-aggregate manifest rows |
 | LEAD-010 | One summary upstream | Return ONE contract string to parent Orchestrator; detail lives in pipeline_manifest under your wave's roll-up entry |
@@ -49,7 +53,7 @@ The parent Orchestrator spawns you with a resolved prompt containing:
 | `waveId` | Wave index within the epic (e.g., `wave-2`) |
 | `workerTasks[]` | Pre-resolved leaf task IDs in this wave (deps already satisfied) |
 | `conduitTopic` | `epic-<epicId>.wave-<waveId>` — your subscription topic |
-| `maxConcurrent` | Effective `delegation.max_concurrent_children` |
+| `maxConcurrent` | Wave width cap passed by the parent (default 10) |
 | `subagentTimeoutSeconds` | Default 600 — wall-clock budget per worker |
 
 ## Workflow
@@ -58,10 +62,11 @@ The parent Orchestrator spawns you with a resolved prompt containing:
 
 ```bash
 # Subscribe FIRST — race-free (LEAD-005)
-cleo conduit subscribe "epic-${EPIC}.wave-${WAVE}" --as-lead
+cleo conduit subscribe --topic "epic-${EPIC}.wave-${WAVE}"
 
-# Verify the wave is well-formed
-cleo orchestrate ready --epic "${EPIC}" --wave "${WAVE}" --json
+# Verify the wave is well-formed: ready tasks and the computed wave plan
+cleo orchestrate ready "${EPIC}"
+cleo orchestrate waves "${EPIC}"
 ```
 
 ### 2. Parallel Fanout (one batch)
@@ -85,19 +90,53 @@ delegate_task({
 ### 3. Convergence (drain conduit + manifest)
 
 ```bash
-# Block on conduit signals — fires on every worker terminal status
-cleo conduit await "epic-${EPIC}.wave-${WAVE}" \
-  --expect "${WORKER_COUNT}" \
-  --timeout 600
+# WAVE = the wave number `cleo orchestrate waves` prints now (1-based);
+# topic and roll-up use the same number.
+
+# Read worker terminal signals on the wave topic. There is no blocking
+# await: poll with --since between checks, bounded by the wave budget.
+cleo conduit listen --topic "epic-${EPIC}.wave-${WAVE}" --since "${SPAWNED_AT}"
 
 # Roll up authoritative status from pipeline_manifest
-cleo lead rollup --epic "${EPIC}" --wave "${WAVE}" --json \
+cleo orchestrate roll-up "${EPIC}" --wave "${WAVE}" --json \
   > /tmp/rollup-${EPIC}-${WAVE}.json
 ```
 
+> **Wave contract (T12682).** One wave number `n` names everything: it is
+> the 1-based number `cleo orchestrate waves <epic>` prints, spawned workers
+> publish on `epic-<epicId>.wave-<n>`, and `cleo orchestrate roll-up <epic>
+> --wave <n>` takes the same `n` (`--wave 0` is refused with
+> `E_CLEO_VALIDATION`, pointing at `cleo orchestrate waves`).
+>
+> **What a wave number guarantees (T12683).** A task's wave is its
+> structural dependency depth: 1 plus the deepest wave among its
+> dependencies, whatever their status and whichever epic holds them.
+>
+> - **Stable** when any task's status changes (done, cancelled, archived)
+>   or a task moves between epics. A finished wave stays in `cleo
+>   orchestrate waves` with status `completed`; `--hide-completed` omits
+>   finished waves without renumbering the rest.
+> - **Not stable** when a dependency edge is added or removed anywhere
+>   upstream, including in another epic: downstream waves shift. If you
+>   subscribed ahead to `epic-<epicId>.wave-<n>`, re-read `cleo orchestrate
+>   waves` after any dependency change.
+> - **Numbers can skip, and an epic's first wave can be above 1** (a task
+>   whose external prerequisite sits at depth 3 is in wave 4). Always take
+>   `n` from `cleo orchestrate waves`; never assume the first wave is 1.
+>
+> `orchestrate ready`, `plan` and `parallel start --wave <n>` never re-run
+> finished tasks.
+
 `rollupWaveStatus` (T9082, `packages/core/src/orchestration/lead-rollup.ts`)
 returns `{ wave, total, complete, partial, blocked, failed, workers: [...] }`.
 
+A stored manifest row with malformed metadata no longer fails the roll-up
+(T12686): it is skipped, every other worker is still reported, and a
+`W_MANIFEST_ROW_MALFORMED` warning names the row, the bad field and the
+repair. Treat that warning as missing coverage, not a clean wave: run
+`cleo doctor manifest-rows` to list such rows, `--repair` to see the plan,
+and `--repair --apply` to rewrite them with a receipt.
+
 ### 4. Decide: retry / escalate / return
 
 See `references/aggregation-protocol.md` for the full decision matrix.
@@ -133,7 +172,7 @@ cleo manifest append \
 - **Sequential fanout**: spawning workers one-by-one defeats parallelism and breaks the wave model — use ONE batch (LEAD-006).
 - **Recursive Leads**: do NOT spawn a Lead from within a Lead — escalate to parent Orchestrator with a `blocked` contract instead (LEAD-003).
 - **Forwarding raw outputs**: never paste worker manifest entries upstream — parent's context budget assumes ONE rollup string per wave (LEAD-004).
-- **Polling**: do not `while true; sleep` on task status — use `cleo conduit await` (LEAD-008).
+- **Polling task status**: do not `while true; sleep` on `cleo show` — read the wave topic with `cleo conduit listen --topic … --since …` and aggregate with `cleo orchestrate roll-up` (LEAD-008).
 - **Unbounded retries**: cap local retry at 1 per worker — repeated failure escalates to parent.
 
 ## Cross-references

package/skills/ct-lead/references/aggregation-protocol.md

@@ -21,12 +21,12 @@ fast-finishing workers and silently loses early `complete` signals.
 
 ```bash
 # CORRECT — subscribe, then spawn
-cleo conduit subscribe "epic-T9080.wave-2" --as-lead
-cleo orchestrate spawn-batch --tasks T9301,T9302,T9303 ...
+cleo conduit subscribe --topic "epic-T9080.wave-2"
+cleo orchestrate fanout T9080 --tasks T9301,T9302,T9303
 
 # WRONG — fanout, then subscribe (race window)
-cleo orchestrate spawn-batch --tasks T9301,T9302,T9303 ...
-cleo conduit subscribe "epic-T9080.wave-2" --as-lead   # may miss T9301 done
+cleo orchestrate fanout T9080 --tasks T9301,T9302,T9303
+cleo conduit subscribe --topic "epic-T9080.wave-2"   # may miss T9301 done
 ```
 
 The conduit retains buffered signals for `conduit.replay_window` (default 30s)
@@ -36,19 +36,44 @@ to defend against tiny races, but relying on the buffer is brittle.
 
 ## 2. Drain loop
 
-The Lead blocks on `cleo conduit await` which yields when the expected number
-of terminal signals arrive OR the wall-clock timeout elapses.
+There is no blocking await. The Lead polls the wave topic with
+`cleo conduit listen --topic <topic> --since <last-seen>` until the expected number of
+terminal signals has arrived OR its wall-clock budget elapses.
 
 ```bash
-cleo conduit await "epic-T9080.wave-2" \
-  --expect 5 \
-  --timeout 600 \
-  --json > /tmp/conduit-drain.json
+cleo conduit listen --topic "epic-T9080.wave-2" --since "${SPAWNED_AT}" \
+  > /tmp/conduit-drain.json
 
-# Then read authoritative state from manifest
-cleo lead rollup --epic T9080 --wave wave-2 --json > /tmp/rollup.json
+# Then read authoritative state from manifest — same wave number as the topic.
+cleo orchestrate roll-up T9080 --wave 2 --json > /tmp/rollup.json
 ```
 
+> **Wave contract (T12682).** One wave number `n` names everything: it is
+> the 1-based number `cleo orchestrate waves <epic>` prints, spawned workers
+> publish on `epic-<epicId>.wave-<n>`, and `cleo orchestrate roll-up <epic>
+> --wave <n>` takes the same `n` (`--wave 0` is refused with
+> `E_CLEO_VALIDATION`, pointing at `cleo orchestrate waves`).
+>
+> **What a wave number guarantees (T12683).** A task's wave is its
+> structural dependency depth: 1 plus the deepest wave among its
+> dependencies, whatever their status and whichever epic holds them.
+>
+> - **Stable** when any task's status changes (done, cancelled, archived)
+>   or a task moves between epics. A finished wave stays in `cleo
+>   orchestrate waves` with status `completed`; `--hide-completed` omits
+>   finished waves without renumbering the rest.
+> - **Not stable** when a dependency edge is added or removed anywhere
+>   upstream, including in another epic: downstream waves shift. If you
+>   subscribed ahead to `epic-<epicId>.wave-<n>`, re-read `cleo orchestrate
+>   waves` after any dependency change.
+> - **Numbers can skip, and an epic's first wave can be above 1** (a task
+>   whose external prerequisite sits at depth 3 is in wave 4). Always take
+>   `n` from `cleo orchestrate waves`; never assume the first wave is 1.
+>
+> `orchestrate ready`, `plan` and `parallel start --wave <n>` never re-run
+> finished tasks.
+
+
 `rollupWaveStatus` returns:
 
 ```json
@@ -94,15 +119,13 @@ Local retry shape:
 RETRIABLE=$(jq -r '.workers[] | select(.status=="failed" and (.reason|test("testsPassed|qaPassed|INFRASTRUCTURE"))) | .taskId' /tmp/rollup.json)
 
 # Re-spawn ONLY those (NEW conduit topic suffix to avoid replay collision)
-cleo orchestrate spawn-batch \
-  --parent "${LEAD_TASK_ID}" --parent-role orchestrator \
-  --topic "epic-T9080.wave-2.retry-1" \
-  --tasks "$(echo $RETRIABLE | tr ' ' ,)" \
-  --child-role leaf --timeout 600
-
-# Re-drain on the retry topic, merge into final rollup
-cleo conduit await "epic-T9080.wave-2.retry-1" --expect $(echo $RETRIABLE | wc -w) --timeout 600
-cleo lead rollup --epic T9080 --wave wave-2 --include-retries --json > /tmp/rollup-final.json
+cleo conduit subscribe --topic "epic-T9080.wave-2.retry-1"
+cleo orchestrate fanout T9080 --tasks "$(echo $RETRIABLE | tr ' ' ,)"
+
+# Re-drain on the retry topic, then roll up again (the manifest holds the
+# latest status of every worker, retries included)
+cleo conduit listen --topic "epic-T9080.wave-2.retry-1" --since "${RETRY_AT}"
+cleo orchestrate roll-up T9080 --wave 2 --json > /tmp/rollup-final.json
 ```
 
 After the single retry pass, whatever `rollup-final.json` shows IS the

package/skills/ct-lead/references/spawn-pattern.md

@@ -1,7 +1,7 @@
 # Spawn Pattern — Worker Fanout Examples
 
 The Phase Lead fans out all workers in a single `delegate_task` batch.
-Width is bounded by `delegation.max_concurrent_children` (default 10).
+Width is bounded by `maxConcurrent` (default 10; a convention the Lead enforces — no runtime check exists).
 Each child carries `role=leaf` and inherits the wave's conduit topic.
 
 All examples assume:
@@ -32,15 +32,14 @@ Typical for narrowly-scoped IVTR waves where deps fan in tightly.
 }
 ```
 
-CLI equivalent (one shell call, NOT a loop):
+CLI equivalent (one shell call, NOT a loop). `fanout` takes the epic and the
+task list only; role, model and timeout come from each task's spawn prompt
+(`cleo orchestrate spawn <taskId>`), and the Lead subscribes to the wave topic
+before it runs:
 
 ```bash
-cleo orchestrate spawn-batch \
-  --parent T9080-lead-w2 --parent-role orchestrator \
-  --topic epic-T9080.wave-2 \
-  --timeout 600 \
-  --tasks T9101,T9102,T9103 \
-  --child-role leaf --model sonnet
+cleo conduit subscribe --topic epic-T9080.wave-2
+cleo orchestrate fanout T9080 --tasks T9101,T9102,T9103
 ```
 
 ---
@@ -69,7 +68,7 @@ cleo orchestrate spawn-batch \
 
 ## Example 3 — 10-worker fanout (max-width wave)
 
-This is the upper bound at default `delegation.max_concurrent_children = 10`.
+This is the upper bound at the default `maxConcurrent = 10`.
 For wider waves, the parent Orchestrator MUST split into multiple Leads.
 
 ```json
@@ -111,10 +110,12 @@ done
 DO NOT exceed `maxConcurrent`:
 
 ```bash
-# WRONG — runtime rejects with E_WAVE_OVERSIZED
-cleo orchestrate spawn-batch --tasks $(seq -s, T9301 T9320)   # 20 > 10
+# WRONG — 20 workers in one wave; split into waves of at most maxConcurrent
+cleo orchestrate fanout T9300 --tasks $(seq -s, T9301 T9320)
 ```
 
+Nothing in the runtime enforces the cap today; the Lead must.
+
 DO NOT spawn workers with `role=orchestrator`:
 
 ```json

package/skills/ct-orchestrator/README.md

@@ -27,8 +27,8 @@ Skill: orchestrator
 
 Install to your project for persistent availability:
 ```bash
-cleo orchestrate skill --install    # Copy to .cleo/skills/
-cleo orchestrate skill --verify     # Verify installation
+cleo skills install ct-orchestrator   # install to your agent directory
+cleo skills info ct-orchestrator      # verify it resolves
 ```
 
 ## Files

package/skills/ct-orchestrator/SKILL.md

@@ -2,9 +2,12 @@
 name: ct-orchestrator
 description: "Pipeline-aware orchestration skill for managing complex workflows through subagent delegation. Use when the user asks to \"orchestrate\", \"orchestrator mode\", \"run as orchestrator\", \"delegate to subagents\", \"coordinate agents\", \"spawn subagents\", \"multi-agent workflow\", \"context-protected workflow\", \"agent farm\", \"HITL orchestration\", \"pipeline management\", or needs to manage complex workflows by delegating work to subagents while protecting the main context window. Enforces ORC-001 through ORC-009 constraints. Provider-neutral — works with any AI agent runtime."
 metadata:
-  version: 4.0.0
+  version: 4.0.4
   tier: core
   install: harness
+  covers:
+    - packages/cleo/src/cli/commands/orchestrate.ts
+    - packages/core/src/orchestration/spawn-prompt.ts
   lastReviewed: 2026-09-28
   stability: stable
 ---
@@ -94,7 +97,7 @@ Runs **autonomously on every incoming issue**. Decomposes ideas into executable
 | **Specification** | Write formal spec with RFC 2119 language, acceptance criteria | Lead (reasoning) |
 | **Decomposition** | Break into atomic tasks with deps under epic(s) | Lead (reasoning) |
 
-**RCASD output**: Epic(s) with child tasks, spec documents attached, dependency graph defined, acceptance criteria on every task. Architecture decisions stored in BRAIN decision-store via `cleo memory store --type decision`, not in adrs markdown blobs.
+**RCASD output**: Epic(s) with child tasks, spec documents attached, dependency graph defined, acceptance criteria on every task. Architecture decisions stored in BRAIN decision-store via `cleo memory decision-store --decision "..." --rationale "..."`, not in adrs markdown blobs.
 
 ### IVTR Phase (Execution)
 
@@ -137,7 +140,7 @@ Spawning is a **two-step pattern** — CLEO prepares the prompt, then the provid
 
 ```bash
 # Get next dependency-safe task
-cleo orchestrate ready --epic T1575
+cleo orchestrate ready T1575
 
 # Generate fully-resolved spawn prompt
 cleo orchestrate spawn T1586 --json
@@ -178,7 +181,7 @@ After successful verification, subagents MUST return exactly one of:
 cleo session status              # Resume existing?
 cleo dash                        # Project overview
 cleo current                     # Active task?
-cleo orchestrate start --epic T1575  # Full state: session, pipeline, next task
+cleo orchestrate start T1575  # Full state: session, pipeline, next task
 ```
 
 ### 2. RCASD — Plan the Work
@@ -199,11 +202,12 @@ cleo orchestrate start --epic T1575  # Full state: session, pipeline, next task
 ### 3. IVTR — Execute the Work
 
 ```
-1. Identify Wave 0: cleo orchestrate ready --epic T1575
-2. Spawn Workers in parallel for each Wave 0 task
+1. Read the waves: cleo orchestrate waves T1575 (take each wave n from here;
+   numbers can skip and the first need not be 1), then cleo orchestrate ready T1575
+2. Spawn Workers in parallel for each ready task in the first incomplete wave
 3. On completion: read manifest, check acceptance criteria
 4. If criteria NOT met → re-spawn worker with feedback (IVTR loop)
-5. Advance to Wave 1 (tasks whose deps are now done)
+5. Advance to the next wave cleo orchestrate waves lists (its deps are now done)
 6. Repeat until all tasks complete
 7. Final validation with Lead across the full epic
 ```
@@ -281,10 +285,10 @@ When operating without continuous HITL oversight, additional constraints apply:
 
 | Command | Purpose |
 |---------|---------|
-| `cleo orchestrate start --epic T1575` | Full startup: session + pipeline + next task |
-| `cleo orchestrate ready --epic T1575` | Parallel-safe tasks in current wave |
+| `cleo orchestrate start T1575` | Full startup: session + pipeline + next task |
+| `cleo orchestrate ready T1575` | Parallel-safe tasks in current wave |
 | `cleo orchestrate spawn T1586 --json` | Generate resolved spawn prompt |
-| `cleo orchestrate next --epic T1575` | Suggest next task |
+| `cleo orchestrate next T1575` | Suggest next task |
 | `cleo saga rollup <sagaId>` | Cross-Epic status aggregation when orchestrating a multi-Epic Saga (ADR-073) |
 | `cleo saga members <sagaId>` | Member Epics of a Saga (parent_id containment — NOT `task_relations.groups`) |
 | `cleo pipeline stage.status --epic T1575` | Current pipeline stage |

package/skills/ct-orchestrator/references/SUBAGENT-PROTOCOL-BLOCK.md

@@ -8,8 +8,8 @@ Copy and include this block in EVERY subagent prompt spawned via Task tool.
 ## SUBAGENT PROTOCOL (RFC 2119 - MANDATORY)
 
 OUTPUT REQUIREMENTS:
-1. MUST write findings to: {{OUTPUT_DIR}}/YYYY-MM-DD_{topic}.md
-2. MUST append ONE entry via `cleo manifest append <json>` (writes to pipeline_manifest table per ADR-027/T1093)
+1. MUST record findings with `cleo docs add {{TASK_ID}} --content - --type <kind> --slug {{TOPIC_SLUG}}` (never a raw file under `.cleo/agent-outputs/`)
+2. MUST append ONE entry via `cleo manifest append --entry '<json>'` (writes to pipeline_manifest table per ADR-027/T1093)
 3. MUST return ONLY: "Research complete. Manifest appended to pipeline_manifest."
 4. MUST NOT return research content in response.
 
@@ -33,8 +33,8 @@ You are the {ROLE} subagent. Your job is to complete CLEO task {TASK_ID}.
 
 ## SUBAGENT PROTOCOL (RFC 2119 - MANDATORY)
 OUTPUT REQUIREMENTS:
-1. MUST write findings to: {{OUTPUT_DIR}}/YYYY-MM-DD_{topic}.md
-2. MUST append ONE entry via `cleo manifest append <json>` (writes to pipeline_manifest table per ADR-027/T1093)
+1. MUST record findings with `cleo docs add {{TASK_ID}} --content - --type <kind> --slug {{TOPIC_SLUG}}` (never a raw file under `.cleo/agent-outputs/`)
+2. MUST append ONE entry via `cleo manifest append --entry '<json>'` (writes to pipeline_manifest table per ADR-027/T1093)
 3. MUST return ONLY: "Research complete. Manifest appended to pipeline_manifest."
 4. MUST NOT return research content in response.
 

package/skills/ct-orchestrator/references/autonomous-operation.md

@@ -115,19 +115,19 @@ HANDOFF CONTENTS:
 
 ```bash
 # 1. Read last handoff
-cleo research list --type handoff --limit 1
+cleo docs list --type handoff --project
 
 # 2. Verify session exists
-cleo session status <session_id>
+cleo session show <session_id>
 
 # 3. Check for concurrent modifications
-cleo session list --scope epic:<epic_id>
+cleo session list --status active
 
 # 4. Resume if clear
 cleo session resume <session_id>
 
 # 5. Continue from next_tasks
-cleo orchestrate next --epic <epic_id>
+cleo orchestrate next <epic_id>
 ```
 
 ## Exit Codes

package/skills/ct-orchestrator/references/orchestrator-compliance.md

@@ -37,7 +37,7 @@ research_id="${topic_slug}-${date}"  # e.g., "auth-research-2026-01-21"
 # 2. Verify manifest entry exists
 cleo research show "$research_id"
 # OR
-jq -s '.[] | select(.id == "'$research_id'")' "{{MANIFEST_PATH}}"
+cleo manifest show "$research_id"
 
 # 3. Block on missing manifest - DO NOT spawn next agent until confirmed
 if ! cleo research show "$research_id" &>/dev/null; then
@@ -91,7 +91,7 @@ fi
 
 | Violation | Detection | Recovery |
 |-----------|-----------|----------|
-| Missing protocol block | `grep -q "SUBAGENT PROTOCOL"` fails | Re-inject via `cleo research inject` |
+| Missing protocol block | `grep -q "SUBAGENT PROTOCOL"` fails | Regenerate the prompt with `cleo orchestrate spawn <taskId>` (it embeds the protocol) |
 | Invalid return message | Not in allowed format list | Mark as violation, re-spawn |
 | No manifest entry | `cleo research show` returns error | Re-spawn with explicit manifest requirement |
 | No research link | `jq '.task.linkedResearch'` empty | Orchestrator links via `cleo research link` |
@@ -240,7 +240,7 @@ if (( $(echo "$compliance_pass_rate < $COMPLIANCE_THRESHOLD" | bc -l) )); then
     stricter_prompt="$original_prompt
 
 ## COMPLIANCE CHECKLIST (VERIFY BEFORE RETURNING)
-- [ ] Output file exists at {{OUTPUT_DIR}}/{{DATE}}_{{TOPIC_SLUG}}.md
+- [ ] Output recorded with `cleo docs add` (`cleo docs fetch <slug>` returns it)
 - [ ] pipeline_manifest entry appended via `cleo manifest append`
 - [ ] Return message is EXACTLY: 'Research complete. Manifest appended to pipeline_manifest.'
 - [ ] Task linked via: {{TASK_LINK_CMD}} {{TASK_ID}} <research-id>

package/skills/ct-orchestrator/references/orchestrator-patterns.md

@@ -21,14 +21,14 @@ cleo orchestrate spawn T1575  # Auto-detects epic → uses decomposition protoco
 cleo research show <research-id>
 
 # 5. Continue with wave-0 tasks
-cleo orchestrate next --epic T1575
+cleo orchestrate next T1575
 ```
 
 ## Pattern: Resuming Interrupted Work
 
 ```bash
 # 1. Check state on conversation start
-cleo orchestrate start --epic T1575
+cleo orchestrate start T1575
 # Shows: session active, current T1586, next task T1589
 
 # 2. Check for incomplete subagent work
@@ -36,7 +36,7 @@ cleo research pending
 # Shows: needs_followup: ["T1586"]
 
 # 3. Resume focused task or spawn followup
-cleo show T1586 --brief
+cleo show T1586
 cleo orchestrate spawn T1586  # Re-spawn if needed
 ```
 
@@ -52,7 +52,7 @@ cleo add "Add error handling to auth" --parent T1586 --depends T1586
 cleo add "Write auth tests" --parent T1586 --depends T1586
 
 # 3. Spawn for new tasks
-cleo orchestrate next --epic T1575
+cleo orchestrate next T1575
 cleo orchestrate spawn T1590
 ```
 
@@ -64,7 +64,7 @@ cleo orchestrate analyze T1575
 # Shows: Wave 0: T1578, T1580, T1582 (no deps)
 
 # 2. Verify parallel safety
-cleo orchestrate ready --epic T1575
+cleo orchestrate ready T1575
 # Returns: ["T1578", "T1580", "T1582"]
 
 # 3. Spawn multiple subagents (different sessions)
@@ -84,13 +84,13 @@ cleo phase show
 # Returns: "core"
 
 # 2. Get tasks in current phase
-cleo orchestrate ready --epic T1575 --phase core
+cleo orchestrate ready T1575
 
 # 3. Spawn within phase context
 cleo orchestrate spawn T1586
 
 # 4. When phase complete, advance
-cleo phases stats
+cleo phase list
 cleo phase advance  # Move to testing phase
 ```
 
@@ -125,18 +125,19 @@ cleo list --parent T1575 --status pending  # Should be empty
 
 # 2. Run pre-release validation
 ./tests/run-all-tests.sh
-cleo validate
-
-# 3. Create and ship release
-cleo release create v0.85.0 --tasks T001,T002,T003
-cleo release ship v0.85.0 --bump-version --create-tag --push
-
-# Preview without changes:
-cleo release ship v0.85.0 --bump-version --dry-run
+cleo check arch
+
+# 3. Plan and open the release PR (ADR-065; merged through PRs, tagged explicitly)
+cleo release plan v0.85.0 --tasks T001,T002,T003
+cleo release open v0.85.0
+cleo release pr-status v0.85.0
+git tag -a v0.85.0 -m "Release v0.85.0" && git push origin v0.85.0
+cleo release reconcile v0.85.0
 ```
 
-**IMPORTANT**: `dev/release-version.sh` is **DEPRECATED** (since v0.78.0).
-Always use `cleo release create` → `cleo release ship`.
+**IMPORTANT**: `dev/release-version.sh` is **DEPRECATED** (since v0.78.0), and the
+`release create`/`release ship` verbs were removed (T9540, T10103). Always use
+`cleo release plan` → `open` → tag → `reconcile`.
 
 See `src/protocols/release.md` for the full release protocol specification.
 
@@ -158,7 +159,7 @@ cleo orchestrate spawn T105  # implementation protocol
 # contribution protocol auto-triggers for shared resources
 
 # RELEASE (polish phase)
-cleo release create v0.74.0 --tasks T104,T105
-cleo release ship v0.74.0 --bump-version --create-tag --push
+cleo release plan v0.74.0 --tasks T104,T105
+cleo release open v0.74.0
 cleo session end --note "Feature X released v0.74.0"
 ```

package/skills/ct-orchestrator/references/orchestrator-recovery.md

@@ -18,11 +18,8 @@
 ## Context Budget Monitoring
 
 ```bash
-# Check current context usage
-cleo orchestrate context
-
-# With specific token count
-cleo orchestrate context --tokens 5000
+# Check context usage for an epic
+cleo orchestrate context T1575
 ```
 
 **Status Thresholds**:
@@ -54,15 +51,14 @@ Orchestrator sessions may span multiple Claude conversations. This is expected a
 ### Cleanup Commands
 
 ```bash
-# Standard garbage collection (ended/suspended sessions only)
+# Standard garbage collection
 cleo session gc
 
-# Include stale active sessions (>7 days old by default)
-cleo session gc --include-active
+# Also end active sessions older than N days
+cleo session gc --max-age 7
 
-# Preview what would be cleaned
-cleo session gc --dry-run
-cleo session gc --include-active --dry-run
+# There is no dry-run; inspect first
+cleo session list --status active
 ```
 
 ### Configuration
@@ -84,12 +80,12 @@ cleo config set retention.autoEndActiveAfterDays 14  # Extend to 2 weeks
 
 2. **Session suspend for long waits**: Suspend when blocked on external factors
    ```bash
-   cleo session suspend --note "Awaiting code review"
+   cleo session suspend <sessionId> --reason "Awaiting code review"
    ```
 
 3. **Periodic cleanup**: Run garbage collection periodically to remove stale sessions
    ```bash
-   cleo session gc --include-active
+   cleo session gc --max-age 7
    ```
 
 4. **Multi-day work**: No need to restart sessions daily - orchestrator sessions are designed for extended work periods
@@ -99,15 +95,9 @@ cleo config set retention.autoEndActiveAfterDays 14  # Extend to 2 weeks
 ## Validation
 
 ```bash
-# Full protocol validation
-cleo orchestrate validate
-
-# Validate for specific epic
-cleo orchestrate validate --epic T1575
-
-# Validate specific subagent output
-cleo orchestrate validate --subagent research-id-2026-01-18
+# Validate one task's subagent output
+cleo orchestrate validate T1586
 
-# Manifest only
-cleo orchestrate validate --manifest
+# Validate a specific output file, and that a manifest entry was appended
+cleo orchestrate validate T1586 --file <output-path> --manifest
 ```

package/skills/ct-orchestrator/references/orchestrator-spawning.md

@@ -11,14 +11,13 @@ Spawning is ALWAYS a two-step process: CLEO **prepares** the prompt, then the pr
 
 ```bash
 # Get next dependency-safe task
-cleo orchestrate next --epic T1575
+cleo orchestrate next T1575
 
 # Generate fully-resolved spawn prompt
 cleo orchestrate spawn T1586
 
-# Or specify a skill template
-cleo orchestrate spawn T1586 --template ct-research-agent
-cleo orchestrate spawn T1586 --template RESEARCH-AGENT  # aliases work
+# Or override the protocol (the skill follows from it)
+cleo orchestrate spawn T1586 --protocol research
 ```
 
 The `spawn` command returns:
@@ -110,7 +109,7 @@ skills/ct-documentor/SKILL.md
 
 ```bash
 # Step 1: Get ready task
-cleo orchestrate next --epic T1575
+cleo orchestrate next T1575
 # Returns: { nextTask: { id: "T1586", title: "...", priority: "high" } }
 
 # Step 2: Generate spawn prompt (handles all token injection)
@@ -148,7 +147,7 @@ The function performs these steps automatically:
 
 | Step | Action | Details |
 |------|--------|---------|
-| 1 | Read task from CLEO | `cleo show T1234 --format json` |
+| 1 | Read task from CLEO | `cleo show T1234` |
 | 2 | Select skill | Auto-dispatch from task type/labels or use override |
 | 3 | Validate skill | Check compatibility with target model |
 | 4 | Inject protocol | Load skill template + subagent protocol |
@@ -161,7 +160,7 @@ The function performs these steps automatically:
 Step 6 validates that the generated prompt contains the `SUBAGENT PROTOCOL` marker. This is **mandatory** and will fail loudly if missing:
 
 - **Exit code**: `EXIT_PROTOCOL_MISSING` (60)
-- **Fix command**: `cleo research inject`
+- **Fix command**: `cleo orchestrate spawn <taskId>` (regenerates the prompt with the protocol embedded)
 - **Validation function**: `orchestrator_verify_protocol_injection()`
 
 If validation fails, the spawn is **blocked** and you must fix the skill template or manually inject the protocol block.
@@ -266,7 +265,7 @@ ti_set_context "T1234" "$(date +%Y-%m-%d)" "auth-implementation"
 
 # Set defaults and get task context
 ti_set_defaults
-task_json=$(cleo show T1234 --format json)
+task_json=$(cleo show T1234)
 ti_set_task_context "$task_json"
 ```
 
@@ -290,6 +289,6 @@ Use Task tool with:
 # Check manifest for completion
 {{RESEARCH_SHOW_CMD}} <research-id>
 
-# Or use jq
-jq -s '.[-1] | {id, status, key_findings}' {{MANIFEST_PATH}}
+# Or list the task's pipeline_manifest entries
+cleo manifest list --task <taskId> --json --limit 1
 ```