@cleocode/skills 2026.9.20 → 2026.9.22

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 entry via `cleo manifest append <json>` (writes to pipeline_manifest table per ADR-027/T1093) | Required |
+| BASE-001 | MUST append ONE entry via `cleo manifest append --entry '<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 |

package/skills/{ct-memory/SKILL.md → ct-cleo/references/memory.md}

@@ -1,16 +1,6 @@
----
-name: ct-memory
-version: 1.0.0
-description: Brain memory protocol with progressive disclosure for anti-hallucination and context recall
-triggers:
-  - memory
-  - brain
-  - recall
-  - remember
-  - anti-hallucination
----
-
-# ct-memory -- Brain Memory Protocol
+<!-- Merged from the ct-memory skill into ct-cleo (T12649, D11157). -->
+
+# Memory (BRAIN) — progressive recall
 
 ## Purpose
 
@@ -20,8 +10,10 @@ Ensures LLM agents never start conversations with amnesia. Provides structured m
 
 Use CLI (`cleo`) for all memory operations.
 
-1. The memory bridge (.cleo/memory-bridge.md) is already loaded via CLEO-INJECTION.md @-reference
-2. If the bridge content feels stale (>2 hours old), refresh:
+1. `cleo briefing` (or `cleo memory digest`) gives the live project memory summary.
+   The file bridge (`.cleo/memory-bridge.md`) is a legacy opt-in
+   (`brain.memoryBridge.mode = "file"`); do not assume it was loaded.
+2. For the task at hand, search:
    - `cleo memory find "session task decision" --limit 10`
 3. Check for anti-patterns to avoid:
    - `cleo memory find "mistake error avoid warning" --limit 5`
@@ -62,14 +54,14 @@ Before stating facts about the codebase or project:
 
 ### Cross-Project Knowledge (via NEXUS)
 
-- `cleo nexus search "pattern" --scope global`
-- Search across all CLEO-managed projects
+- `cleo nexus search "pattern"` (add `--project <id>` to narrow to one project)
+- Search the symbol graph across CLEO-managed projects
 
 ## Token Budget Guidelines
 
 | Operation | ~Tokens | When |
 |-----------|---------|------|
-| memory-bridge.md (auto-loaded) | 200-400 | Always (free) |
+| `cleo memory digest` | 200-400 | Session start |
 | `cleo memory find` | 50/hit | Discovery |
 | `cleo memory fetch` | 500/entry | Details |
 | `cleo memory timeline` | 200-500 | Context |

package/skills/ct-cleo/references/orchestrator-constraints.md

@@ -18,11 +18,11 @@
 ### CLI Spawn Operations
 
 ```bash
-cleo orchestrator start --epic T001
-cleo orchestrator analyze T001
-cleo orchestrator ready --epic T001
-cleo orchestrator next --epic T001
-cleo orchestrator spawn T002
+cleo orchestrate start T001
+cleo orchestrate analyze T001
+cleo orchestrate ready T001
+cleo orchestrate next T001
+cleo orchestrate spawn T002
 ```
 
 ### Spawn Workflow

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

@@ -38,9 +38,14 @@ ct start T006                  # Start next task
 ```bash
 ct complete <id>               # Complete current
 ct archive                     # Clean up done tasks
-ct session end --note "Progress"
+ct session end --note "Progress"   # this terminal's session; elsewhere: --session <id>
 ```
 
+Sessions are terminal-bound: from a terminal that did not start/resume the
+session, `session end` fails with `E_SESSION_UNBOUND` rather than ending the
+newest session. Bind (`cleo session resume <id>`, `CLEO_SESSION_ID=<id>`) or pass
+`--session <id>`. Scripts and CI must export `CLEO_SESSION_ID`.
+
 ## Research & Manifest Operations
 
 ### Output Requirements
@@ -92,8 +97,7 @@ Orchestrators resolve ALL tokens before spawning subagents. Subagents CANNOT res
 | `{{EPIC_ID}}` | Parent epic identifier |
 | `{{DATE}}` | Current date (ISO) |
 | `{{TOPIC_SLUG}}` | URL-safe topic name |
-| `{{OUTPUT_DIR}}` | Output directory |
-| `{{MANIFEST_PATH}}` | Manifest file path |
+| `{{OUTPUT_DIR}}` | Legacy output directory — record output with `cleo docs add` instead |
 | `{{TASK_TITLE}}` | Task title |
 | `{{TASK_DESCRIPTION}}` | Task description |
 
@@ -113,8 +117,8 @@ Skills are **context injections, NOT agents**. The orchestrator selects and inje
 ### Discovery
 
 ```bash
-cleo skill list
-cleo skill show ct-orchestrator
+cleo skills list
+cleo skills info ct-orchestrator
 ```
 
 ### Key Skills
@@ -140,12 +144,16 @@ cleo skill show ct-orchestrator
 
 ## Release Workflow
 
-**CRITICAL**: `release ship` only commits version metadata. All code changes MUST be committed BEFORE running `release ship`.
+Releases are PR-gated (ADR-065). Commit and merge all code through PRs first; the
+release verbs are `plan` → `open` → `reconcile`. The legacy `create`/`ship`
+verbs were removed (T9540, T10103).
 
 ```bash
-git add <files> && git commit -m "feat(T####): description"
-cleo release create v1.0.0
-cleo release ship v1.0.0 --bump-version --create-tag --push
+cleo release plan v2026.MM.N --epic T####     # or --tasks T1,T2
+cleo release open v2026.MM.N                  # dispatches release-prepare
+cleo release pr-status v2026.MM.N             # poll the release PR + CI
+git tag -a v2026.MM.N -m "Release v2026.MM.N" && git push origin v2026.MM.N
+cleo release reconcile v2026.MM.N             # backfill provenance
 ```
 
 ## Project Context

package/skills/{ct-stickynote/SKILL.md → ct-cleo/references/sticky-notes.md}

@@ -1,19 +1,6 @@
----
-name: ct-stickynote
-description: Quick ephemeral sticky notes for project-wide capture before formal classification
-version: 1.0.0
-category: productivity
-tier: 0
-protocol: null
-tags: [sticky, notes, capture, quick, ephemeral]
-triggers: [note, sticky, jot, capture]
-compatibility: [claude-code, gemini-cli, codex-cli, opencode]
-dependencies: []
-sharedResources: []
-license: MIT
----
-
-# Sticky Notes Skill
+<!-- Merged from the ct-stickynote skill into ct-cleo (T12649, D11157). -->
+
+# Sticky notes — capture before you classify
 
 Quick capture ephemeral notes that fill the gap between session notes and formal tasks.
 
@@ -32,15 +19,10 @@ Use sticky notes for:
 | `sticky.add` | Create sticky | `cleo sticky add "Refactor auth middleware" --tag bug --color red` |
 | `sticky.list` | List active | `cleo sticky list --tag bug` |
 | `sticky.show` | Show details | `cleo sticky show SN-001` |
-| `sticky.convert` | Promote to task/memory | `cleo sticky convert SN-001 --to-task` |
+| `sticky.convert` | Promote to task/memory | `cleo sticky convert SN-001 --to-task --title "..."` or `--to-memory --type learning` |
 | `sticky.archive` | Archive | `cleo sticky archive SN-001` |
 
-## Installation
-
-```bash
-cleo skill install library:ct-stickynote
-```
-
-## Auto-Archive
 
-Stickies auto-archive after 30 days if not converted.
+Also: `cleo sticky jot "..."` (alias of add), `cleo sticky ls`, and
+`cleo sticky purge <id>` (permanent). Sticky notes are a core CLEO feature, so
+this guide ships inside ct-cleo rather than as a separate skill.

package/skills/ct-codebase-mapper/SKILL.md

@@ -1,9 +1,7 @@
 ---
 name: ct-codebase-mapper
-version: 1.0.0
-description: Codebase analysis and mapping for autonomous agent understanding. Builds structured maps of project stack, architecture, conventions, testing, integrations, and concerns.
-category: recommended
-tier: 1
+version: 2.0.1
+description: Orient in an unfamiliar or large codebase with CLEO's code-intelligence graph (cleo nexus) and project map (cleo map). Use before planning or editing unfamiliar code, for brownfield onboarding, to find what a change would break, or to map a project's structure, communities and execution flows. Triggers on "map the codebase", "understand this project", "what calls X", "what would break", "brownfield analysis", "project structure".
 protocol: null
 dependencies: []
 compatibility:
@@ -17,66 +15,96 @@ triggers:
   - understand project
   - brownfield analysis
   - project structure
+  - blast radius
+metadata:
+  version: 2.0.1
+  tier: on-demand
+  install: harness
+  covers:
+    - packages/cleo/src/cli/commands/nexus.ts
+    - packages/cleo/src/cli/commands/map.ts
+  lastReviewed: 2026-09-28
+  stability: stable
 ---
 
 # Codebase Mapper
 
-Structured codebase analysis for autonomous agent understanding.
+Two instruments, used together:
 
-## Quick Start
+- **`cleo nexus`** is the symbol graph: callers, callees, blast radius,
+  communities and execution flows, parsed from source. Use it for any question
+  about how code connects.
+- **`cleo map`** is the project survey: stack, architecture, structure,
+  conventions, testing, integrations and concerns. Use it for the one-page
+  overview, and `--store` to keep the findings in BRAIN.
 
-| Goal | Command | Cost |
-|------|---------|------|
-| Quick analysis | `query admin map` | ~500 tokens |
-| Deep analysis + store | `mutate admin map` | ~800 tokens |
-| Focus on one area | `query admin map {focus: "concerns"}` | ~300 tokens |
-| CLI | `cleo map` / `cleo map --store` | — |
-
-## Progressive Disclosure
-
-### Tier 0: Quick Analysis
+## 1. Check the index before trusting it
 
 ```bash
-cleo map
+cleo nexus status
 ```
 
-Returns structured `CodebaseMapResult` with stack, architecture, structure, conventions, testing, integrations, and concerns.
+Read `nodeCount`, `lastIndexedAt` and `staleFileCount` against `fileCount`.
+Queries auto-refresh up to 25 stale files; beyond that they warn
+`W_NEXUS_INDEX_STALE`. Refresh with `cleo nexus analyze` (incremental; `--full`
+rebuilds). An empty or stale index gives confident-looking but incomplete
+answers — say which you relied on.
 
-### Tier 1: Store to Brain
+## 2. Survey the project
 
 ```bash
-cleo map --store
+cleo map                      # full survey
+cleo map --focus concerns     # one area: stack | architecture | structure |
+                              #   conventions | testing | integrations | concerns
+cleo map --store              # same survey, findings stored to BRAIN
+                              #   (tagged source: 'codebase-map')
 ```
 
-Same analysis, but stores patterns, learnings, and observations to brain.db. Tagged with `source: 'codebase-map'` for filtering.
+## 3. Find the structure
+
+```bash
+cleo nexus clusters               # detected communities (modules that change together)
+cleo nexus flows                  # detected execution flows (entry point → callees)
+cleo nexus search-code "<text>"   # locate a symbol by name, file pattern or keyword
+```
 
-### Tier 2: Focused Analysis
+## 4. Before editing a symbol
 
 ```bash
-cleo map --focus concerns
+cleo nexus impact <symbol>        # blast radius: direct, indirect, transitive callers
+cleo nexus context <symbol>       # callers, callees, community, flows
+cleo nexus full-context <symbol>  # plus BRAIN memories, tasks and conduit threads
 ```
 
-Focus areas: `stack`, `architecture`, `structure`, `conventions`, `testing`, `integrations`, `concerns`.
+`HIGH`/`CRITICAL` impact means review the affected callers before editing.
+`UNKNOWN` means the assessment is incomplete, and `NONE` means nothing was
+detected in the assessed graph — static analysis cannot prove every runtime
+caller, so an empty footprint alone never establishes that a change is safe.
+When a symbol name is ambiguous, pass the qualified candidate the command
+returns and confirm against the source.
 
-## When to Use
+## When to use
 
-- **New project onboarding**: Run `cleo map --store` to build brain.db context
-- **Brownfield init**: `cleo init --map-codebase` runs analysis during initialization
-- **Before epic planning**: Understand project structure before decomposing work
-- **Tech debt assessment**: `query admin map {focus: "concerns"}` for TODOs and large files
+| Situation | Start with |
+|-----------|------------|
+| New or brownfield project | `cleo nexus status`, then `cleo map --store` |
+| Planning an epic in unfamiliar code | `cleo map --focus architecture`, `cleo nexus clusters` |
+| About to change a function or type | `cleo nexus impact <symbol>` |
+| "Who calls this / what does this call?" | `cleo nexus context <symbol>` |
+| Tech-debt review | `cleo map --focus concerns` |
 
-## Output Structure
+## `cleo map` output
 
 ```typescript
 {
-  projectContext: ProjectContext,  // From detectProjectType()
-  stack: StackAnalysis,           // Languages, frameworks, deps
-  architecture: ArchAnalysis,     // Layers, entry points, patterns
-  structure: StructureAnalysis,   // Directory tree with annotations
-  conventions: ConventionAnalysis,// Naming, linting, formatting
-  testing: TestingAnalysis,       // Framework, patterns, coverage
-  integrations: IntegrationAnalysis, // APIs, DBs, CI/CD
-  concerns: ConcernAnalysis,      // TODOs, large files, complexity
+  projectContext: ProjectContext,     // From detectProjectType()
+  stack: StackAnalysis,               // Languages, frameworks, deps
+  architecture: ArchAnalysis,         // Layers, entry points, patterns
+  structure: StructureAnalysis,       // Directory tree with annotations
+  conventions: ConventionAnalysis,    // Naming, linting, formatting
+  testing: TestingAnalysis,           // Framework, patterns, coverage
+  integrations: IntegrationAnalysis,  // APIs, DBs, CI/CD
+  concerns: ConcernAnalysis,          // TODOs, large files, complexity
   analyzedAt: string
 }
 ```

package/skills/ct-consensus-voter/SKILL.md

@@ -2,10 +2,19 @@
 name: ct-consensus-voter
 description: "Runs structured multi-agent voting for decision tasks with confidence scores, conflict detection, and HITL escalation when the threshold is not met. Use when two or more agents must vote on options: architecture choices, tool selection, policy decisions, when a task carries agent_type:analysis, or on phrases like 'reach consensus', 'vote on options', 'resolve the debate', 'pick the best approach'. Produces a voting matrix JSON, enforces the 0.5 threshold, flags ties within 0.1 confidence as contested and escalates to human tiebreak."
 protocol: consensus
-loomStage: consensus
 adrRefs:
   - ADR-015
   - ADR-023
+metadata:
+  version: 1.0.2
+  tier: on-demand
+  install: harness
+  covers:
+    - packages/core/src/validation/protocols/cant/consensus.cant
+    - packages/core/src/validation/protocols/protocols-markdown/consensus.md
+  loomStage: consensus
+  lastReviewed: 2026-09-28
+  stability: stable
 ---
 
 # Consensus Voter
@@ -129,10 +138,9 @@ On escalation:
 Validate the matrix through `cleo check protocol`:
 
 ```bash
-cleo check protocol \
-  --protocolType consensus \
-  --votingMatrixFile ./.cleo/rcasd/T4797/consensus/T4797-consensus.json \
-  --taskId T4797
+cleo check protocol consensus \
+  --voting-matrix-file ./.cleo/rcasd/T4797/consensus/T4797-consensus.json \
+  --task-id T4797
 ```
 
 Exit code 0 = matrix is valid and verdict is `PROVEN` or `REFUTED`. Exit code 65 = `HANDOFF_REQUIRED` (contested or insufficient evidence). Exit code 61 = `E_PROTOCOL_CONSENSUS` (matrix shape is invalid).
@@ -160,7 +168,7 @@ This skill typically hands off to ct-adr-recorder on a `PROVEN` verdict so the d
 5. Critical-severity conflicts always escalate, regardless of top-option confidence.
 6. Manifest entry MUST set `agent_type: "analysis"` and include the verdict.
 7. On PROVEN, hand off to ct-adr-recorder; on CONTESTED or INSUFFICIENT_EVIDENCE, hand off to HITL.
-8. Always validate via `cleo check protocol --protocolType consensus`.
+8. Always validate via `cleo check protocol consensus`.
 
 ## See also / References
 

package/skills/ct-contribution/SKILL.md

@@ -6,12 +6,8 @@ description: >-
   "consensus workflow", "multi-agent decision", "create contribution",
   "contribution start", "contribution submit", "detect conflicts",
   "weighted consensus", "decision tracking", "conflict resolution".
-version: 1.0.0
-tier: 3
-core: false
-category: meta
+version: 1.0.2
 protocol: contribution
-loomStage: contribution
 adrRefs:
   - ADR-015
   - ADR-053
@@ -24,6 +20,16 @@ compatibility:
   - windsurf
   - gemini-cli
 license: MIT
+metadata:
+  version: 1.0.2
+  tier: on-demand
+  install: harness
+  covers:
+    - packages/core/src/validation/protocols/cant/contribution.cant
+    - packages/core/src/validation/protocols/protocols-markdown/contribution.md
+  loomStage: contribution
+  lastReviewed: 2026-09-28
+  stability: stable
 ---
 
 # Contribution Protocol Skill

package/skills/ct-council/SKILL.md

@@ -1,6 +1,11 @@
 ---
 name: ct-council
 description: Convene "The Council" — a 5-advisor, shuffled gate-based peer-review, chairman-synthesis workflow for reviewing a plan, decision, architecture, or piece of work inside the current project. Use when the user says "convene the council" (or "counsel"), "get the council on this", "council review", "run the five advisors", "stress-test this", "get multiple perspectives", or asks for a rigorous multi-angle challenge of a proposal (Contrarian, First Principles, Expansionist, Outsider, Executor → shuffled peer review with pass/fail gates → convergence detector → Chairman verdict). Operates on the current codebase — each advisor grounds their analysis in actual files/commits before opining. Output is validated by scripts/validate.py.
+metadata:
+  version: 1.0.0
+  tier: on-demand
+  install: harness
+  stability: stable
 ---
 
 # The Council

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

@@ -1,10 +1,7 @@
 ---
 name: ct-dev-workflow
 description: Development workflow orchestration for task-driven development with atomic commits, conventional commit messages, and systematic release processes. Enforces task traceability, branch discipline, smart test scope selection, and GitHub Actions integration. Use when committing code, creating releases, managing branches, or following contribution protocols. Triggers on commit operations, release preparation, or workflow compliance needs.
-version: 3.1.0
-tier: 2
-core: false
-category: specialist
+version: 3.1.3
 protocol: contribution
 dependencies: []
 sharedResources:
@@ -17,8 +14,12 @@ compatibility:
   - gemini-cli
 license: MIT
 metadata:
-  version: 3.1.0
-  lastReviewed: 2026-09-18
+  version: 3.1.3
+  tier: core
+  install: harness
+  covers:
+    - .github/workflows/release-prepare.yml
+  lastReviewed: 2026-09-28
   stability: stable
 ---
 
@@ -337,8 +338,8 @@ cleo session end --note "Completed X, Y, Z"
 
 ### Output Requirements
 
-1. MUST write workflow summary to: `{{OUTPUT_DIR}}/{{DATE}}_{{TOPIC_SLUG}}.md`
-2. MUST append ONE line to: `{{MANIFEST_PATH}}`
+1. MUST record workflow summary with `cleo docs add {{TASK_ID}} --content - --type note --slug {{TOPIC_SLUG}}` (never a raw file under `.cleo/agent-outputs/`)
+2. MUST record ONE manifest entry: `cleo manifest append --entry '<entry JSON>'` (the flat manifest file is retired, ADR-027)
 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

@@ -1,19 +1,9 @@
 ---
 name: ct-documentor
-description: Documentation coordinator with CLEO style guide compliance. Routes every canonical-doc write (spec, adr, research, handoff, note, llm-readme) through the docs SSoT via `cleo docs add` / `cleo docs publish` / `cleo docs fetch` — never raw filesystem writes. Coordinates ct-docs-lookup, ct-docs-write, ct-docs-review, ct-spec-writer, and ct-adr-recorder. Use when creating or updating documentation files, consolidating scattered documentation, or validating documentation against style standards. Triggers on documentation tasks, doc update requests, or style guide compliance checks.
-version: 3.16.0
-tier: 3
-core: false
-category: specialist
+description: Documentation coordinator with CLEO style guide compliance. Routes every canonical-doc write (spec, adr, research, handoff, note, llm-readme) through the docs SSoT via `cleo docs add` / `cleo docs publish` / `cleo docs fetch` — never raw filesystem writes. Carries the CLEO writing and review guides as references and coordinates ct-spec-writer and ct-adr-recorder. Use when creating or updating documentation files, consolidating scattered documentation, or validating documentation against style standards. Triggers on documentation tasks, doc update requests, or style guide compliance checks.
+version: 3.17.3
 protocol: null
-metadata:
-  version: 3.16.0
-  lastReviewed: 2026-09-19
-  stability: stable
 dependencies:
-  - ct-docs-lookup
-  - ct-docs-write
-  - ct-docs-review
   - ct-spec-writer
   - ct-adr-recorder
 sharedResources:
@@ -25,6 +15,15 @@ compatibility:
   - windsurf
   - gemini-cli
 license: MIT
+metadata:
+  version: 3.17.3
+  tier: core
+  install: harness
+  covers:
+    - packages/cleo/src/cli/commands/docs.ts
+    - packages/contracts/src/docs-taxonomy.ts
+  lastReviewed: 2026-09-28
+  stability: stable
 ---
 
 # Documentation Specialist Context Injection
@@ -91,9 +90,9 @@ Context injection for documentation tasks spawned via cleo-subagent. Orchestrate
 
 | Skill | Purpose | Invoke When |
 |-------|---------|-------------|
-| `ct-docs-lookup` | Query existing docs, find references via `cleo docs fetch`/`list` | Discovery phase, checking what exists |
-| `ct-docs-write` | Create/edit docs via `cleo docs add` with CLEO style | Writing or updating content |
-| `ct-docs-review` | Check compliance with style guide, read through `cleo docs fetch` | Quality validation before completion |
+| `cleo docs find` / `list` / `fetch` (and the Context7 MCP for library APIs) | Query existing docs and current external docs | Discovery phase, checking what exists |
+| `references/writing.md` (was ct-docs-write) | Create/edit docs via `cleo docs add` with CLEO style | Writing or updating content |
+| `references/reviewing.md` (was ct-docs-review) | Check compliance with style guide, read through `cleo docs fetch`; PR mode | Quality validation before completion |
 | `ct-spec-writer` | Author specs (REQ-XXX requirements) via `cleo docs add --type spec` | Formal specification work |
 | `ct-adr-recorder` | Author ADRs via `cleo docs add --type adr --slug adr-NNN-...` | Architecture decisions promoted from consensus |
 
@@ -114,8 +113,8 @@ and every owner writes through `cleo docs add` — not raw filesystem writes.
 | `adr` (architecture decisions) | `ct-adr-recorder` | `cleo docs add <ownerId> <path> --type adr --slug adr-<NNN>-<rest>` (TODO T10360 · E3.2 pending: `--title` + auto-`adr-NNN` allocation) |
 | `research` (multi-source investigation) | `ct-research-agent` | `cleo docs add <ownerId> <path> --type research --slug research-<topic>` |
 | `handoff` (session/agent transition) | `ct-documentor` (this skill) | `cleo docs add <ownerId> <path> --type handoff --slug handoff-<context>` |
-| `note` (conversational prose) | `ct-docs-write` | `cleo docs add <ownerId> <path> --type note --slug <kebab-topic>` |
-| `llm-readme` (agent-facing) | `ct-docs-write` | `cleo docs add <ownerId> <path> --type llm-readme --slug <kebab-topic>` |
+| `note` (conversational prose) | `ct-documentor` (`references/writing.md`) | `cleo docs add <ownerId> <path> --type note --slug <kebab-topic>` |
+| `llm-readme` (agent-facing) | `ct-documentor` (`references/writing.md`) | `cleo docs add <ownerId> <path> --type llm-readme --slug <kebab-topic>` |
 
 Hard rule: EVERY canonical-type write goes through the SSoT. The coordinator
 rejects any subagent return that wrote raw markdown into `.cleo/adrs/`,
@@ -158,6 +157,7 @@ Before adding a new doc, ALWAYS ask: is this **a new doc**, **a change to an exi
 ### Examples
 
 - **"Fix a typo in ADR-076 saga-first-class"** - `cleo docs update adr-076-saga-first-class --file /tmp/fixed.md --message "fix typo in §2"` (canonical - T10161). NOT a new doc. NOT a supersession. Just patch in place; T10161 squashes patches within a 5-minute window so consecutive typo fixes don't bloat the audit log.
+- **"Accept a spec that review signed off"** - `cleo docs update <slug> --status accepted` (T12654). `--status` alone changes only the lifecycle status (draft, proposed, accepted, superseded, archived, deprecated); the stored bytes are kept, so there is no need to re-supply `--file` or `--content`. Any content edit without `--status` resets the doc to `draft`.
 
 - **"Replace the entire saga-orchestration model with v2" (ADVANCED)** - `cleo docs add T9999 v2.md --type adr --slug adr-080-saga-orchestration-v2` followed by `cleo docs supersede adr-073-above-epic-naming adr-080-saga-orchestration-v2 --reason "v2 canonicalizes the SG- prefix + 4-tier hierarchy"`. Both rows survive in the attachments table; readers see `lifecycle_status=superseded` on v1 and `supersedes=adr-073` on v2.
 
@@ -204,7 +204,7 @@ This closes the silent-absorption footgun where citty's underlying
 
 ```bash
 # Typo → E_UNKNOWN_FLAG with suggestion
-$ cleo docs add T123 file.md --titel "X"
+$ cleo docs add T123 file.md --titel "X"   # cleo-cmd: negative-example
 {
   "success": false,
   "error": {
@@ -398,8 +398,10 @@ Per-line opt-out (use sparingly): append
 the writer-uniqueness lint. Where T10369 prevents *new* raw `.md`
 writers from landing in `packages/core/src/**`, this sweep walks every
 `*.md` file *already* added under `.cleo/canon.yml`'s `rawMdPaths`
-directories since the T9791 docs-import cutoff (commit `251814e86`)
-and classifies each one against the docs SSoT:
+directories since the T9791 docs-import cutoff — the commit that
+imported the legacy corpus and committed its manifests under
+`.cleo/audit/imports/`, which is how the sweep locates it — and
+classifies each one against the docs SSoT:
 
 | Remediation | Meaning | Fix |
 |---|---|---|
@@ -574,9 +576,10 @@ not yet under test.
 
 **Anti-pattern**: do NOT write a `cleo memory observe` manually after a
 `cleo docs add` — the auto-emit already happened, and the duplicate
-observation pollutes the FTS index. Use `cleo memory backfill-docs` (AC4
-of T9976) only to repair attachments that pre-date the auto-emit feature
-or were written outside the SSoT.
+observation pollutes the FTS index. No CLI command back-fills that
+observation for attachments that pre-date the auto-emit feature: the
+`memory backfill-docs` verb planned in T9976 AC4 never shipped. Leave such
+attachments as they are rather than hand-writing a duplicate observation.
 
 #### System-managed exemptions (T10368)
 
@@ -693,7 +696,7 @@ the docs graph — never grep the filesystem for the file you just wrote.
 cleo docs list --type spec --project       # canonical: every spec in this project
 cleo docs list --task T1234                # canonical: everything attached to a task
 cleo docs versions --for T1234             # ADVANCED: list every SHA version
-cleo docs sync --from docs/legacy.md --for T1234 --type note --slug legacy-doc  # ADVANCED: back-fill on-disk file into SSoT
+cleo docs sync --from docs/legacy.md --for T1234  # ADVANCED: back-fill on-disk file into SSoT (no --type/--slug; classify with docs add)
 ```
 
 ---
@@ -770,7 +773,7 @@ Grep: pattern="{TOPIC_KEYWORDS}" path="docs/"
 Grep: pattern="{RELATED_TERMS}" path="docs/" output_mode="files_with_matches"
 ```
 
-**Invoke `/ct-docs-lookup`** for deeper documentation research.
+**Use the Context7 MCP** (`resolve-library-id` → `query-docs`) for current library and framework docs.
 
 ### Phase 2: Assess
 
@@ -783,7 +786,7 @@ Grep: pattern="{RELATED_TERMS}" path="docs/" output_mode="files_with_matches"
 
 ### Phase 3: Write/Update
 
-**Invoke `/ct-docs-write`** for content creation.
+**Load `references/writing.md`** for content creation.
 
 **For EXISTING files:**
 1. Read the current content
@@ -808,7 +811,7 @@ Grep: pattern="{RELATED_TERMS}" path="docs/" output_mode="files_with_matches"
 
 ### Phase 4: Review
 
-**Invoke `/ct-docs-review`** for quality validation.
+**Load `references/reviewing.md`** for quality validation.
 
 Checklist:
 - [ ] No formal language ("utilize", "offerings", "cannot")
@@ -868,14 +871,14 @@ cleo research link {TASK_ID} {RESEARCH_ID}
 
 ### Output Requirements
 
-1. MUST write documentation output to: `{{OUTPUT_DIR}}/`
-2. MUST append ONE line to: `{{MANIFEST_PATH}}`
+1. MUST record documentation output with `cleo docs add {{TASK_ID}} --content - --type <kind> --slug {{TOPIC_SLUG}}` (never a raw file under `.cleo/agent-outputs/`)
+2. MUST record ONE manifest entry: `cleo manifest append --entry '<entry JSON>'` (the flat manifest file is retired, ADR-027)
 3. MUST return ONLY: "Documentation complete. Manifest appended to pipeline_manifest."
 4. MUST NOT return documentation content in response
 
 ### Output File Format
 
-Write to `{{OUTPUT_DIR}}/`:
+Record it with `cleo docs add {{TASK_ID}} --content - --type <kind> --slug {{TOPIC_SLUG}}`, using this body:
 
 ```markdown
 # Documentation Update: {TITLE}
@@ -904,12 +907,12 @@ Write to `{{OUTPUT_DIR}}/`:
 - [ ] Changes don't duplicate existing content
 - [ ] Cross-references updated
 - [ ] Examples tested
-- [ ] Style guide compliance verified via ct-docs-review
+- [ ] Style guide compliance verified via `references/reviewing.md`
 ```
 
 ### Manifest Entry
 
-Append ONE line to `{{MANIFEST_PATH}}`:
+Record it with `cleo manifest append --entry '<entry JSON>'` (the flat manifest file is retired, ADR-027):
 
 ```json
 {"id":"docs-{TOPIC}-{DATE}","file":"{DATE}_docs-{TOPIC}.md","title":"Documentation Update: {TITLE}","date":"{DATE}","status":"complete","agent_type":"documentation","topics":["documentation","{topic}"],"key_findings":["Updated {file} with {change}","Consolidated {topic} docs into {canonical-location}","Avoided duplication by updating existing {file}"],"actionable":false,"needs_followup":[],"linked_tasks":["{TASK_ID}"]}
@@ -923,10 +926,10 @@ Append ONE line to `{{MANIFEST_PATH}}`:
 - [ ] Core principle followed (maintain, don't duplicate)
 - [ ] Coordinator pattern followed: every doc-type routed to its owning skill
 - [ ] Every canonical-type write went through `cleo docs add --type X --slug Y`
-- [ ] `/ct-docs-write` invoked for `note`/`llm-readme` content
+- [ ] `references/writing.md` followed for `note`/`llm-readme` content
 - [ ] `/ct-spec-writer` invoked when writing specs (REQ-XXX requirements)
 - [ ] `/ct-adr-recorder` invoked when promoting consensus → ADR
-- [ ] `/ct-docs-review` invoked for quality validation
+- [ ] `references/reviewing.md` applied for quality validation
 - [ ] Anti-duplication checklist verified
 - [ ] Output file written with "Files NOT Created" section
 - [ ] Manifest entry appended