@cleocode/skills 2026.4.110 → 2026.4.112

package/README.md

@@ -400,7 +400,7 @@ cleo skills apply-profile backend-developer --task T1234
 
 Common patterns and utilities in `skills/_shared/`:
 
-- `manifest-operations.md` - Working with MANIFEST.jsonl
+- `manifest-operations.md` - Working with pipeline_manifest via cleo manifest CLI
 - `subagent-protocol-base.md` - Base subagent protocols
 - `skill-chaining-patterns.md` - Chaining best practices
 - `testing-framework-config.md` - Test configuration

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@cleocode/skills",
-  "version": "2026.4.110",
+  "version": "2026.4.112",
   "description": "CLEO skill definitions - bundled with CLEO monorepo",
   "main": "index.js",
   "types": "index.d.ts",

package/skills/_shared/manifest-operations.md

@@ -4,7 +4,7 @@
 **Status**: ACTIVE
 **Version**: 1.0.0
 
-This reference defines all CLI operations for managing the agent outputs manifest (`MANIFEST.jsonl`). Skills and protocols SHOULD reference this file instead of duplicating JSONL instructions.
+This reference defines all CLI operations for managing the agent outputs manifest (`pipeline_manifest` SQLite table via `cleo manifest` CLI). Skills and protocols SHOULD reference this file instead of duplicating manifest instructions.
 
 ---
 
@@ -14,8 +14,8 @@ The manifest system provides O(1) append operations and race-condition-free conc
 
 **Default Paths**:
 - Output directory: `.cleo/agent-outputs/` (configurable via `agentOutputs.directory`)
-- Manifest file: `MANIFEST.jsonl` (configurable via `agentOutputs.manifestFile`)
-- Full path: `{{OUTPUT_DIR}}/MANIFEST.jsonl` (i.e., `.cleo/agent-outputs/MANIFEST.jsonl`)
+- Manifest store: `pipeline_manifest` SQLite table (canonical per ADR-027)
+- CLI: `cleo manifest append <json>` — the only supported write path
 
 **Design Principles**:
 - Append-only writes preserve audit trail
@@ -72,7 +72,7 @@ cleo research add \
 {
   "success": true,
   "entryId": "jwt-authentication-2026-02-07",
-  "manifestPath": ".cleo/agent-outputs/MANIFEST.jsonl"
+  "store": "pipeline_manifest"
 }
 ```
 
@@ -455,7 +455,7 @@ When present, the `audit` field provides operational metadata:
 | `{{DATE}}` | Current date | `2026-02-07` |
 | `{{TOPIC_SLUG}}` | URL-safe topic name | `jwt-authentication` |
 | `{{OUTPUT_DIR}}` | Output directory | `.cleo/agent-outputs` |
-| `{{MANIFEST_PATH}}` | Manifest filename | `MANIFEST.jsonl` |
+
 
 ### Command Tokens (CLEO Defaults)
 
@@ -518,18 +518,15 @@ cleo research add \
 ### ❌ Pretty-Printed JSON
 
 ```bash
-# WRONG - Creates multiple lines
-echo '{
-  "id": "test",
-  "title": "Test"
-}' >> MANIFEST.jsonl
+# WRONG - Bypasses pipeline_manifest table
+echo '{"id": "test", "title": "Test"}' >> .cleo/agent-outputs/legacy-manifest.jsonl
 ```
 
-**Problem**: Breaks JSONL format (one object per line)
+**Problem**: Legacy file — migrated to SQLite per ADR-027. Race conditions and no validation.
 
-**Solution**: Use `jq -c` for compact output
+**Solution**: Use `cleo manifest append`
 ```bash
-jq -nc '{id: "test", title: "Test"}' >> MANIFEST.jsonl
+cleo manifest append '{"id":"test","task_id":"T###","type":"research","status":"complete","output":"path/to/output.md","summary":"brief","key_findings":["..."]}'
 ```
 
 ---
@@ -537,15 +534,15 @@ jq -nc '{id: "test", title: "Test"}' >> MANIFEST.jsonl
 ### ❌ Direct File Writes
 
 ```bash
-# WRONG - Bypasses validation
-echo "$json" >> .cleo/agent-outputs/MANIFEST.jsonl
+# WRONG - Legacy file path; SQLite is now the store
+echo "$json" >> .cleo/agent-outputs/legacy-manifest.jsonl
 ```
 
-**Problem**: No validation, no atomic operation, no audit trail
+**Problem**: The legacy flat-file is retired per ADR-027. Use the manifest CLI.
 
-**Solution**: Use CLI commands
+**Solution**: Use `cleo manifest append`
 ```bash
-cleo research add --task T#### --topic "..." --findings "..."
+cleo manifest append '{"id":"...","task_id":"T####","type":"...","status":"complete","output":"...","summary":"...","key_findings":["..."]}'
 ```
 
 ---
@@ -582,7 +579,7 @@ Here is my research:
 
 **Solution**: Return ONLY summary message
 ```markdown
-[Type] complete. See MANIFEST.jsonl for summary.
+[Type] complete. Manifest appended to pipeline_manifest.
 ```
 
 ---

package/skills/_shared/placeholders.json

@@ -71,9 +71,9 @@
     {
       "token": "MANIFEST_PATH",
       "type": "path",
-      "example": ".cleo/agent-outputs/MANIFEST.jsonl",
-      "description": "Path to MANIFEST.jsonl file",
-      "default": ".cleo/agent-outputs/MANIFEST.jsonl"
+      "example": "pipeline_manifest (use cleo manifest append)",
+      "description": "Manifest CLI: use `cleo manifest append`",
+      "default": "pipeline_manifest (use cleo manifest append)"
     }
   ],
   "taskCommands": {
@@ -182,7 +182,7 @@
     ]
   },
   "manifest": {
-    "_comment": "Tokens used when constructing MANIFEST.jsonl entries",
+    "_comment": "Tokens used when constructing pipeline_manifest entries (via cleo manifest append)",
     "tokens": [
       {
         "token": "MANIFEST_ID",

package/skills/_shared/skill-chaining-patterns.md

@@ -54,7 +54,7 @@ cleo orchestrator spawn T1234 --json
 
 - **Input**: Task ID, skill template, previous manifest key_findings
 - **Output**: Manifest entry with key_findings for next agent
-- **Response**: "[Type] complete. See MANIFEST.jsonl for summary."
+- **Response**: "[Type] complete. Manifest appended to pipeline_manifest."
 
 ---
 
@@ -164,7 +164,7 @@ A subagent can itself become an orchestrator, spawning further subagents for com
 ### Rule 1: Manifest for Handoffs (MUST)
 
 ```json
-// Subagent appends ONE line to MANIFEST.jsonl
+// Subagent appends ONE entry via cleo manifest append
 {"id":"topic-2026-01-20","key_findings":["Finding 1","Finding 2"],"needs_followup":["T1235"]}
 ```
 
@@ -173,7 +173,7 @@ Parent reads only key_findings, not full research files.
 ### Rule 2: Minimal Response (MUST)
 
 ```
-Subagent MUST return ONLY: "[Type] complete/partial/blocked. See MANIFEST.jsonl for summary/details/blocker details."
+Subagent MUST return ONLY: "[Type] complete/partial/blocked. Manifest appended to pipeline_manifest."
 Subagent MUST NOT return output content in response.
 ```
 
@@ -181,7 +181,7 @@ Subagent MUST NOT return output content in response.
 
 Detailed findings go to output files, not manifest or response:
 - Full analysis → `{{OUTPUT_DIR}}/YYYY-MM-DD_topic.md`
-- Summary only → `MANIFEST.jsonl` key_findings array
+- Summary only → pipeline_manifest key_findings (via `cleo manifest append`)
 
 ### Rule 4: Token Injection (SHOULD)
 

package/skills/_shared/subagent-protocol-base.cant

@@ -21,7 +21,7 @@ protocol subagent-base:
       EPIC_ID: pattern("^T[0-9]+$") = ""
       SESSION_ID: string = ""
       OUTPUT_DIR: path = ".cleo/agent-outputs"
-      MANIFEST_PATH: path = "${OUTPUT_DIR}/MANIFEST.jsonl"
+      # MANIFEST_PATH token retired — use pipeline.manifest.append instead (ADR-027)
     computed:
       OUTPUT_PATH: path = "${OUTPUT_DIR}/${DATE}_${TOPIC_SLUG}.md"
       RESEARCH_ID: string = "${TOPIC_SLUG}-${DATE}"
@@ -55,7 +55,7 @@ protocol subagent-base:
     MAN-001: MUST write output file before appending manifest entry
     MAN-002: MUST set manifest status to enum("complete", "partial", "blocked")
     MAN-003: SHOULD include needs_followup array when status is "partial"
-    MAN-004: MUST use pipeline.manifest.append — MUST NOT write MANIFEST.jsonl directly
+    MAN-004: MUST use pipeline.manifest.append — flat-file sink retired per ADR-027
 
   # --- Lifecycle Phases ---
 
@@ -102,7 +102,7 @@ protocol subagent-base:
     - pattern: "Calling tasks.list without filters"
       problem: "Returns all tasks with notes — huge token cost"
       solution: "Use tasks.find for discovery"
-    - pattern: "Appending to MANIFEST.jsonl directly"
+    - pattern: "Appending to legacy flat-file directly"
       problem: "Legacy file — migrated to SQLite per ADR-027"
       solution: "Use pipeline.manifest.append operation"
     - pattern: "Loading skills via @ at runtime"

package/skills/_shared/subagent-protocol-base.md

@@ -16,14 +16,14 @@ All subagents operating under an orchestrator MUST follow this protocol.
 | ID | Rule | Compliance |
 |----|------|------------|
 | OUT-001 | MUST write findings to `{{OUTPUT_DIR}}/{{DATE}}_{{TOPIC_SLUG}}.md` | Required |
-| OUT-002 | MUST append ONE line to `{{MANIFEST_PATH}}` | Required |
-| OUT-003 | MUST return ONLY: "[Type] complete. See MANIFEST.jsonl for summary." | Required |
+| OUT-002 | MUST append ONE entry via `cleo manifest append <json>` (writes to pipeline_manifest table per ADR-027/T1093) | Required |
+| OUT-003 | MUST return ONLY: "[Type] complete. Manifest appended to pipeline_manifest." | Required |
 | OUT-004 | MUST NOT return output content in response | Required |
 
 Valid return messages:
-- `"[Type] complete. See MANIFEST.jsonl for summary."`
-- `"[Type] partial. See MANIFEST.jsonl for details."`
-- `"[Type] blocked. See MANIFEST.jsonl for blocker details."`
+- `"[Type] complete. Manifest appended to pipeline_manifest."`
+- `"[Type] partial. Manifest appended to pipeline_manifest."`
+- `"[Type] blocked. Manifest appended to pipeline_manifest."`
 
 ### Rationale
 
@@ -110,7 +110,7 @@ Reference: @skills/_shared/task-system-integration.md
 4. Write output: {{OUTPUT_DIR}}/{{DATE}}_{{TOPIC_SLUG}}.md
 5. Create manifest entry: cleo research add [flags]
 6. Complete:     {{TASK_COMPLETE_CMD}} {{TASK_ID}}
-7. Return:       "[Type] complete. See MANIFEST.jsonl for summary."
+7. Return:       "[Type] complete. Manifest appended to pipeline_manifest."
 ```
 
 ---
@@ -178,7 +178,6 @@ Before returning, verify:
 | `{{EPIC_ID}}` | `""` | Parent epic ID |
 | `{{SESSION_ID}}` | `""` | Session identifier |
 | `{{OUTPUT_DIR}}` | `.cleo/agent-outputs` | Output directory |
-| `{{MANIFEST_PATH}}` | `{{OUTPUT_DIR}}/MANIFEST.jsonl` | Manifest location |
 
 ### Task System Tokens (CLEO defaults)
 
@@ -201,7 +200,7 @@ If work cannot complete fully:
 2. Set manifest `"status": "partial"`
 3. Add blocking reason to `needs_followup`
 4. Complete task (partial work is still progress)
-5. Return: "[Type] partial. See MANIFEST.jsonl for details."
+5. Return: "[Type] partial. Manifest appended to pipeline_manifest."
 
 ### Blocked Status
 
@@ -211,7 +210,7 @@ If work cannot proceed:
 2. Set manifest `"status": "blocked"`
 3. Add blocker details to `needs_followup`
 4. Do NOT complete task (leave for orchestrator decision)
-5. Return: "[Type] blocked. See MANIFEST.jsonl for blocker details."
+5. Return: "[Type] blocked. Manifest appended to pipeline_manifest."
 
 ---
 

package/skills/_shared/task-system-integration.md

@@ -169,7 +169,7 @@ When tokens are not explicitly configured, assume CLEO defaults:
 | `{{TASK_FIND_CMD}}` | `cleo find` |
 | `{{TASK_ADD_CMD}}` | `cleo add` |
 | `{{OUTPUT_DIR}}` | `.cleo/agent-outputs` |
-| `{{MANIFEST_PATH}}` | `{{OUTPUT_DIR}}/MANIFEST.jsonl` |
+
 
 ---
 

package/skills/ct-cleo/references/loom-lifecycle.md

@@ -107,7 +107,7 @@ Every spawn combines two layers:
 
 | ID | Rule | Enforcement |
 |----|------|-------------|
-| BASE-001 | MUST append ONE line to MANIFEST.jsonl | Required |
+| BASE-001 | MUST append ONE entry via `cleo manifest append <json>` (writes to pipeline_manifest table per ADR-027/T1093) | Required |
 | BASE-002 | MUST NOT return content in response | Required |
 | BASE-003 | MUST complete task via `cleo complete` | Required |
 | BASE-004 | MUST write output file before manifest | Required |
@@ -131,6 +131,6 @@ SPAWN -> INJECT -> EXECUTE -> OUTPUT -> RETURN
 
 | Status | Message |
 |--------|---------|
-| Complete | `[Type] complete. See MANIFEST.jsonl for summary.` |
-| Partial | `[Type] partial. See MANIFEST.jsonl for details.` |
-| Blocked | `[Type] blocked. See MANIFEST.jsonl for blocker details.` |
+| Complete | `[Type] complete. Manifest appended to pipeline_manifest.` |
+| Partial | `[Type] partial. Manifest appended to pipeline_manifest.` |
+| Blocked | `[Type] blocked. Manifest appended to pipeline_manifest.` |

package/skills/ct-cleo/references/session-protocol.md

@@ -64,7 +64,7 @@ Subagent output files follow this structure:
 <main deliverable>
 ```
 
-### Manifest Entry (MANIFEST.jsonl)
+### Manifest Entry (pipeline_manifest)
 
 Append ONE line (no pretty-printing):
 

package/skills/ct-dev-workflow/SKILL.md

@@ -328,7 +328,7 @@ cleo session end --note "Completed X, Y, Z"
 
 1. MUST write workflow summary to: `{{OUTPUT_DIR}}/{{DATE}}_{{TOPIC_SLUG}}.md`
 2. MUST append ONE line to: `{{MANIFEST_PATH}}`
-3. MUST return ONLY: "Workflow complete. See MANIFEST.jsonl for summary."
+3. MUST return ONLY: "Workflow complete. Manifest appended to pipeline_manifest."
 4. MUST NOT return full commit/release details in response
 
 ---

package/skills/ct-documentor/SKILL.md

@@ -172,7 +172,7 @@ cleo research link {TASK_ID} {RESEARCH_ID}
 
 1. MUST write documentation output to: `{{OUTPUT_DIR}}/`
 2. MUST append ONE line to: `{{MANIFEST_PATH}}`
-3. MUST return ONLY: "Documentation complete. See MANIFEST.jsonl for summary."
+3. MUST return ONLY: "Documentation complete. Manifest appended to pipeline_manifest."
 4. MUST NOT return documentation content in response
 
 ### Output File Format

package/skills/ct-epic-architect/SKILL.md

@@ -249,7 +249,7 @@ Recommendation: [Your recommendation]
 
 1. MUST write decomposition to: `{{OUTPUT_DIR}}/{{DATE}}_{{TOPIC_SLUG}}.md`
 2. MUST append ONE line to: `{{MANIFEST_PATH}}`
-3. MUST return ONLY: "Decomposition complete. See MANIFEST.jsonl for summary."
+3. MUST return ONLY: "Decomposition complete. Manifest appended to pipeline_manifest."
 4. MUST NOT return full decomposition in response
 
 ---

package/skills/ct-epic-architect/references/commands.md

@@ -198,4 +198,4 @@ cleo list --tree --parent {{EPIC_ID}}      # Show epic subtree
 | Token | Default |
 |-------|---------|
 | `{{OUTPUT_DIR}}` | `.cleo/agent-outputs` |
-| `{{MANIFEST_PATH}}` | `{{OUTPUT_DIR}}/MANIFEST.jsonl` |
+

package/skills/ct-epic-architect/references/skill-aware-execution.md

@@ -119,7 +119,7 @@ When ct-epic-architect creates an epic, it follows the subagent protocol:
 
 1. **Write output file**: `{{OUTPUT_DIR}}/{{DATE}}_epic-{{FEATURE_SLUG}}.md`
 2. **Append manifest entry**: Single line JSON to `{{MANIFEST_PATH}}`
-3. **Return summary only**: "Epic created. See MANIFEST.jsonl for summary."
+3. **Return summary only**: "Epic created. Manifest appended to pipeline_manifest."
 
 ### Querying Prior Research
 

package/skills/ct-master-tac/bundled/protocols/implementation.cant

@@ -19,7 +19,7 @@ input:
 output:
   files_changed: "string[] — list of modified/created files"
   tests_added: "string[] — new test files or test names"
-  manifest_entry: "object — implementation summary for MANIFEST.jsonl"
+  manifest_entry: "object — implementation summary for pipeline_manifest via cleo manifest append"
 ---
 
 # Implementation Protocol

package/skills/ct-master-tac/bundled/protocols/release.cant

@@ -20,7 +20,7 @@ output:
   release_tag: "string — git tag created (e.g. v2026.4.5)"
   changelog_path: "string — path to updated CHANGELOG file"
   artifacts_published: "boolean — true when artifact phase ran"
-  release_manifest: "object — release summary for MANIFEST.jsonl"
+  release_manifest: "object — release summary for pipeline_manifest via cleo manifest append"
 ---
 
 # Release Protocol

package/skills/ct-master-tac/bundled/protocols/research.cant

@@ -18,7 +18,7 @@ input:
   output_dir: "string — directory for findings (default: .cleo/agent-outputs/)"
 output:
   findings_path: "string — path to the research output markdown file"
-  manifest_entry: "object — 3–7 key findings for MANIFEST.jsonl"
+  manifest_entry: "object — 3–7 key findings for pipeline_manifest via cleo manifest append"
   confidence_levels: "object — per-finding confidence 0.0–1.0"
   sources: "string[] — cited URLs or file paths"
 ---
@@ -45,7 +45,7 @@ output:
 #   RSCH-001: MUST NOT implement code or make changes to codebase
 #   RSCH-002: MUST document all sources with citations
 #   RSCH-003: MUST write findings to claudedocs/agent-outputs/
-#   RSCH-004: MUST append entry to MANIFEST.jsonl
+#   RSCH-004: MUST append entry via `cleo manifest append`
 #   RSCH-005: MUST return only completion message (no content in response)
 #   RSCH-006: MUST include 3-7 key findings in manifest entry
 #   RSCH-007: MUST set agent_type: "research" in manifest

package/skills/ct-master-tac/bundled/protocols/testing.cant

@@ -20,7 +20,7 @@ output:
   test_framework: "vitest | jest | mocha | pytest | cargo-test | go-test | rspec | phpunit | bats | other"
   convergence_iterations: "number — IVT loop iterations to convergence"
   test_results: "object — {passed, failed, skipped} counts"
-  manifest_entry: "object — convergence metrics for MANIFEST.jsonl"
+  manifest_entry: "object — convergence metrics for pipeline_manifest via cleo manifest append"
 ---
 
 # Testing Protocol - Project-Agnostic IVT Loop

package/skills/ct-orchestrator/INSTALL.md

@@ -57,5 +57,5 @@ skills/
 ## Dependencies
 
 - CLEO task management (`cleo` CLI)
-- Agent manifest system (`.cleo/agent-outputs/MANIFEST.jsonl`)
+- Agent manifest system (pipeline_manifest SQLite table, accessed via `cleo manifest` CLI)
 - Task tool for subagent spawning

package/skills/ct-orchestrator/SKILL.md

@@ -26,7 +26,7 @@ You are the **Orchestrator** — a conductor, never a musician. You coordinate c
 | ORC-006 | Max 3 files per subagent | Cross-file reasoning degrades beyond this scope |
 | ORC-007 | All work traced to epic | No orphaned tasks — every task has a parent epic |
 | ORC-008 | Zero architectural decisions | Architecture MUST be pre-decided via RCASD consensus or HITL |
-| ORC-009 | Manifest-mediated handoffs | Read only `key_findings` from MANIFEST.jsonl; subagents read full files |
+| ORC-009 | Manifest-mediated handoffs | Read only `key_findings` from pipeline_manifest; subagents read full files |
 | ORC-010 | Continuous dispatch | While ready tasks exist, orchestrator MUST be spawning — never idle while work remains |
 | ORC-011 | Pre-release verification gate | NEVER `git push --tags` without full pipeline green: biome ci packages/, build, test, changelog, version |
 | ORC-012 | Honest reporting | "Shipped" ≠ "designed" ≠ "in progress" — distinguish always; never claim CI green without seeing the green |
@@ -110,14 +110,14 @@ Agent({
 })
 ```
 
-**Other harnesses**: Pass the resolved prompt to whatever "give this prompt to an agent" mechanism the runtime provides. Results flow back through MANIFEST.jsonl — the universal handoff medium.
+**Other harnesses**: Pass the resolved prompt to whatever "give this prompt to an agent" mechanism the runtime provides. Results flow back through pipeline_manifest (via `cleo manifest append`) — the universal handoff medium.
 
 ### Valid Return Messages
 
 Subagents MUST return exactly one of:
-- `"[Type] complete. See MANIFEST.jsonl for summary."`
-- `"[Type] partial. See MANIFEST.jsonl for details."`
-- `"[Type] blocked. See MANIFEST.jsonl for blocker details."`
+- `"[Type] complete. Manifest appended to pipeline_manifest."`
+- `"[Type] partial. Manifest appended to pipeline_manifest."`
+- `"[Type] blocked. Manifest appended to pipeline_manifest."`
 
 > Detailed spawn workflow, manual protocol injection, skill dispatch matrix: `references/orchestrator-spawning.md`
 
@@ -168,7 +168,7 @@ After each wave or on request: what completed, blockers needing HITL, next actio
 Content flows between subagents via **manifest-mediated handoffs**, NOT through orchestrator context:
 
 ```
-Agent A completes → writes output file + MANIFEST.jsonl entry
+Agent A completes → writes output file + pipeline_manifest entry (via `cleo manifest append`)
     ↓
 Orchestrator reads manifest key_findings (3-7 items) + file path
     ↓

package/skills/ct-orchestrator/orchestrator-prompt.txt

@@ -17,7 +17,7 @@ of LLM provider or harness. Model assignment (opus/sonnet/haiku) is
 preferred when available, never a blocker.
 
 Read only manifests, never full subagent outputs. Subagents write
-to MANIFEST.jsonl; you read key_findings from manifest entries.
+to pipeline_manifest (via `cleo manifest append`); you read key_findings from manifest entries.
 
 Each subagent MUST stay under 185,000 tokens. If approaching that
 limit, the subagent MUST create a handoff and a new agent carries

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

@@ -9,8 +9,8 @@ Copy and include this block in EVERY subagent prompt spawned via Task tool.
 
 OUTPUT REQUIREMENTS:
 1. MUST write findings to: {{OUTPUT_DIR}}/YYYY-MM-DD_{topic}.md
-2. MUST append ONE line to: {{OUTPUT_DIR}}/MANIFEST.jsonl
-3. MUST return ONLY: "Research complete. See MANIFEST.jsonl for summary."
+2. MUST append ONE entry via `cleo manifest append <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.
 
 MANIFEST ENTRY FORMAT:
@@ -34,8 +34,8 @@ 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 line to: {{OUTPUT_DIR}}/MANIFEST.jsonl
-3. MUST return ONLY: "Research complete. See MANIFEST.jsonl for summary."
+2. MUST append ONE entry via `cleo manifest append <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.
 
 ## CONTEXT

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

@@ -20,9 +20,9 @@ Only accept these return message formats from subagents:
 
 | Status | Valid Return Message |
 |--------|---------------------|
-| Complete | "Research complete. See MANIFEST.jsonl for summary." |
-| Partial | "Research partial. See MANIFEST.jsonl for details." |
-| Blocked | "Research blocked. See MANIFEST.jsonl for blocker details." |
+| Complete | "Research complete. Manifest appended to pipeline_manifest." |
+| Partial | "Research partial. Manifest appended to pipeline_manifest." |
+| Blocked | "Research blocked. Manifest appended to pipeline_manifest." |
 
 Any other return format indicates protocol violation.
 
@@ -241,8 +241,8 @@ if (( $(echo "$compliance_pass_rate < $COMPLIANCE_THRESHOLD" | bc -l) )); then
 
 ## COMPLIANCE CHECKLIST (VERIFY BEFORE RETURNING)
 - [ ] Output file exists at {{OUTPUT_DIR}}/{{DATE}}_{{TOPIC_SLUG}}.md
-- [ ] MANIFEST.jsonl entry appended with all required fields
-- [ ] Return message is EXACTLY: 'Research complete. See MANIFEST.jsonl for summary.'
+- [ ] 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>
 - [ ] Task completed via: {{TASK_COMPLETE_CMD}} {{TASK_ID}}
 "

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

@@ -15,7 +15,7 @@ Orchestrator (Tier 0)
     ├─ Spawns Agent A with task instructions
     │   └─ A completes → writes output file + manifest entry
     │
-    ├─ Reads MANIFEST.jsonl → extracts key_findings (3-7 items)
+    ├─ Reads pipeline_manifest → extracts key_findings (3-7 items)
     │   └─ Does NOT read full output file
     │   └─ Does NOT use TaskOutput tool
     │

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

@@ -98,7 +98,7 @@ cleo phase advance  # Move to testing phase
 
 ```bash
 # 1. Subagent completes implementation
-# Returns: "Implementation complete. See MANIFEST.jsonl for summary."
+# Returns: "Implementation complete. Manifest appended to pipeline_manifest."
 
 # 2. Orchestrator verifies output
 cleo research show <research-id>

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

@@ -50,7 +50,7 @@ Agent({
 })
 ```
 
-**Other harnesses** (Cursor, OpenCode, Codex, etc.): Pass the resolved prompt to whatever "give this prompt to an agent" mechanism the runtime provides. Results flow back through MANIFEST.jsonl.
+**Other harnesses** (Cursor, OpenCode, Codex, etc.): Pass the resolved prompt to whatever "give this prompt to an agent" mechanism the runtime provides. Results flow back through pipeline_manifest (via `cleo manifest append`).
 
 ### Fallback Spawn (when CLI spawn unavailable)
 

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

@@ -71,7 +71,7 @@ template=$(ti_load_template "skills/ct-research-agent/SKILL.md")
 | Token | Default Value |
 |-------|---------------|
 | `{{OUTPUT_DIR}}` | `.cleo/agent-outputs` |
-| `{{MANIFEST_PATH}}` | `.cleo/agent-outputs/MANIFEST.jsonl` |
+
 
 ### Task Context Tokens (populated from CLEO task data)
 
@@ -83,7 +83,7 @@ template=$(ti_load_template "skills/ct-research-agent/SKILL.md")
 | `{{DELIVERABLES_LIST}}` | `task.deliverables` | Expected outputs |
 | `{{ACCEPTANCE_CRITERIA}}` | Extracted | Completion criteria |
 | `{{DEPENDS_LIST}}` | `task.depends` | Completed dependencies |
-| `{{MANIFEST_SUMMARIES}}` | MANIFEST.jsonl | Key findings from previous agents |
+| `{{MANIFEST_SUMMARIES}}` | pipeline_manifest | Key findings from previous agents |
 | `{{NEXT_TASK_IDS}}` | Dependency analysis | Tasks unblocked after completion |
 
 ---
@@ -115,7 +115,7 @@ For fine-grained control over token injection, use `lib/token-inject.sh` directl
 | **Task Commands** | `{{TASK_SHOW_CMD}}`, `{{TASK_START_CMD}}`, `{{TASK_COMPLETE_CMD}}`, etc. | CLEO defaults |
 | **Output Paths** | `{{OUTPUT_DIR}}`, `{{MANIFEST_PATH}}` | CLEO defaults |
 | **Task Context** | `{{TASK_TITLE}}`, `{{TASK_DESCRIPTION}}`, `{{DEPENDS_LIST}}`, etc. | From CLEO task data |
-| **Manifest Context** | `{{MANIFEST_SUMMARIES}}` | From recent MANIFEST.jsonl entries |
+| **Manifest Context** | `{{MANIFEST_SUMMARIES}}` | From recent pipeline_manifest entries |
 
 ### Manual Token Injection Example
 
@@ -156,7 +156,7 @@ echo "$template" | grep -c '{{' && echo "WARNING: Uninjected tokens remain"
 
 Token defaults (from `skills/_shared/placeholders.json`):
 - `{{OUTPUT_DIR}}` -> `.cleo/agent-outputs`
-- `{{MANIFEST_PATH}}` -> `.cleo/agent-outputs/MANIFEST.jsonl`
+- `{{MANIFEST_PATH}}` -> retired (ADR-027) — use `cleo manifest append`
 
 ### Inline Protocol Block (when CLI unavailable)
 
@@ -165,8 +165,8 @@ Token defaults (from `skills/_shared/placeholders.json`):
 
 OUTPUT REQUIREMENTS:
 1. MUST write findings to: {{OUTPUT_DIR}}/{{DATE}}_{{TOPIC_SLUG}}.md
-2. MUST append ONE line to: {{MANIFEST_PATH}}
-3. MUST return ONLY: "Research complete. See MANIFEST.jsonl for summary."
+2. MUST append ONE entry via `cleo manifest append <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.
 
 CLEO INTEGRATION:

package/skills/ct-research-agent/SKILL.md

@@ -107,7 +107,7 @@ Context injection for research and investigation tasks spawned via cleo-subagent
 
 1. MUST write findings to: `{{OUTPUT_DIR}}/{{DATE}}_{{TOPIC_SLUG}}.md`
 2. MUST append ONE line to: `{{MANIFEST_PATH}}`
-3. MUST return ONLY: "Research complete. See MANIFEST.jsonl for summary."
+3. MUST return ONLY: "Research complete. Manifest appended to pipeline_manifest."
 4. MUST NOT return research content in response
 
 ---
@@ -155,7 +155,7 @@ Write to `{{OUTPUT_DIR}}/{{DATE}}_{{TOPIC_SLUG}}.md`:
 
 ## Manifest Entry Format
 
-Append ONE line (no pretty-printing) to `{{MANIFEST_PATH}}`:
+Append ONE entry via `cleo manifest append <json>` (writes to pipeline_manifest table per ADR-027):
 
 ```json
 {"id":"{{TOPIC_SLUG}}-{{DATE}}","file":"{{DATE}}_{{TOPIC_SLUG}}.md","title":"{{RESEARCH_TITLE}}","date":"{{DATE}}","status":"complete","agent_type":"research","topics":{{TOPICS_JSON}},"key_findings":["Finding 1","Finding 2","Finding 3"],"actionable":true,"needs_followup":[],"linked_tasks":["{{EPIC_ID}}","{{TASK_ID}}"]}
@@ -195,7 +195,7 @@ If complete answers cannot be found:
 3. Set manifest `"status": "partial"`
 4. Add suggestions for followup to `needs_followup`
 5. Complete task
-6. Return: "Research partial. See MANIFEST.jsonl for details."
+6. Return: "Research partial. Manifest appended to pipeline_manifest."
 
 ### Blocked Research
 
@@ -205,7 +205,7 @@ If research cannot proceed (access denied, topic too broad, etc.):
 2. Set manifest `"status": "blocked"`
 3. Add blocker details to `needs_followup`
 4. Do NOT complete task
-5. Return: "Research blocked. See MANIFEST.jsonl for blocker details."
+5. Return: "Research blocked. Manifest appended to pipeline_manifest."
 
 ---
 

package/skills/ct-spec-writer/SKILL.md

@@ -165,7 +165,7 @@ Specifications go in: `docs/specs/{{SPEC_NAME}}.md`
 
 1. MUST write specification to: `docs/specs/{{SPEC_NAME}}.md`
 2. MUST append ONE line to: `{{MANIFEST_PATH}}`
-3. MUST return ONLY: "Specification complete. See MANIFEST.jsonl for summary."
+3. MUST return ONLY: "Specification complete. Manifest appended to pipeline_manifest."
 4. MUST NOT return specification content in response
 
 ### Manifest Entry Format

package/skills/ct-task-executor/SKILL.md

@@ -110,7 +110,7 @@ Context injection for implementation tasks spawned via cleo-subagent. Provides d
 
 1. MUST write findings to: `{{OUTPUT_DIR}}/{{DATE}}_{{TOPIC_SLUG}}.md`
 2. MUST append ONE line to: `{{MANIFEST_PATH}}`
-3. MUST return ONLY: "Implementation complete. See MANIFEST.jsonl for summary."
+3. MUST return ONLY: "Implementation complete. Manifest appended to pipeline_manifest."
 4. MUST NOT return implementation details in response
 
 ---
@@ -162,7 +162,7 @@ Write to `{{OUTPUT_DIR}}/{{DATE}}_{{TOPIC_SLUG}}.md`:
 
 ## Manifest Entry Format
 
-Append ONE line (no pretty-printing) to `{{MANIFEST_PATH}}`:
+Append ONE entry via `cleo manifest append <json>` (writes to pipeline_manifest table per ADR-027):
 
 ```json
 {"id":"{{TOPIC_SLUG}}-{{DATE}}","file":"{{DATE}}_{{TOPIC_SLUG}}.md","title":"{{TASK_NAME}}","date":"{{DATE}}","status":"complete","agent_type":"implementation","topics":{{TOPICS_JSON}},"key_findings":["Completed: deliverable 1","Completed: deliverable 2","All acceptance criteria passed"],"actionable":false,"needs_followup":[],"linked_tasks":["{{EPIC_ID}}","{{TASK_ID}}"]}
@@ -205,7 +205,7 @@ If all deliverables cannot be produced:
 3. Set manifest `"status": "partial"`
 4. Add blocking items to `needs_followup`
 5. Complete task (partial work is progress)
-6. Return: "Implementation partial. See MANIFEST.jsonl for details."
+6. Return: "Implementation partial. Manifest appended to pipeline_manifest."
 
 ### Blocked Execution
 
@@ -215,7 +215,7 @@ If work cannot proceed (missing dependencies, access issues, unclear requirement
 2. Set manifest `"status": "blocked"`
 3. Add blocker details to `needs_followup`
 4. Do NOT complete task
-5. Return: "Implementation blocked. See MANIFEST.jsonl for blocker details."
+5. Return: "Implementation blocked. Manifest appended to pipeline_manifest."
 
 ### Acceptance Criteria Failure
 

package/skills/ct-validator/SKILL.md

@@ -125,7 +125,7 @@ Context injection for compliance validation tasks spawned via cleo-subagent. Pro
 
 1. MUST write validation report to: `{{OUTPUT_DIR}}/{{DATE}}_{{TOPIC_SLUG}}.md`
 2. MUST append ONE line to: `{{MANIFEST_PATH}}`
-3. MUST return ONLY: "Validation complete. See MANIFEST.jsonl for summary."
+3. MUST return ONLY: "Validation complete. Manifest appended to pipeline_manifest."
 4. MUST NOT return validation content in response
 
 ### Manifest Entry Format