refactor(planning): rename architect skill to plan

.claude-plugin/marketplace.json

@@ -191,7 +191,7 @@
       "name": "planning",
       "source": "./plugins/planning",
       "category": "design",
-      "tags": ["planning", "wayfind", "decision-map", "brainstorm", "prd", "interview", "domain-modeling", "ubiquitous-language", "glossary", "design", "design-handoff", "devils-advocate", "architect", "stress-test", "skill"]
+      "tags": ["planning", "wayfind", "decision-map", "brainstorm", "prd", "interview", "domain-modeling", "ubiquitous-language", "glossary", "design", "design-handoff", "devils-advocate", "plan", "stress-test", "skill"]
     },
     {
       "name": "naming",

docs/conventions/topic-docs/examples/worked-slice.md

@@ -8,10 +8,10 @@ Topic: adding token-refresh to an auth module. Derived slug:
 
 ```text
 docs/topics/auth-token-refresh/     <- contract slice, committed on branch
-  PLAN.md                           interview writes Brief; architect appends Plan
+  PLAN.md                           interview writes Brief; plan appends Plan
   PRD.md                            prd (status: locked)
   design/
-    design-threads.md               all RESOLVED -> architect's gate passes
+    design-threads.md               all RESOLVED -> plan's gate passes
     design-resolution.md
   verification/
     20260714T161500Z-outcomes.md    distilled manifest, verified_at_sha-keyed

docs/topics/plugin-fleet-sync-skill/PLAN.md

@@ -64,7 +64,7 @@ One command that guarantees, on any machine and from any directory, that the plu
 
 - **Does `plugin update -s project` avoid writing the repo's committed `.claude/settings.json`?** — RESOLVED, see Open questions VERIFIED line 1: hash-verified no write. Decision 4 stands, no re-approval needed.
 - **Is `/reload-plugins --force` required after sync, or is plain `/reload-plugins` sufficient?** — RESOLVED, see Open questions VERIFIED line 2: no `--force` flag exists; report recommends bare `/reload-plugins`.
-- **`all`-marketplaces argument interaction with third-party marketplaces lacking renames maps / non-git sources** — RESOLVED by /architect: graceful degradation — `marketplace update` handles every source type; a marketplace without a `renames` map simply has no rename residue; failures per-marketplace are reported and do not abort the sweep.
+- **`all`-marketplaces argument interaction with third-party marketplaces lacking renames maps / non-git sources** — RESOLVED by /planning:plan: graceful degradation — `marketplace update` handles every source type; a marketplace without a `renames` map simply has no rename residue; failures per-marketplace are reported and do not abort the sweep.
 
 ## Plan
 

docs/topics/plugin-organization/PLAN.md

@@ -81,9 +81,9 @@ history; grouping lives in marketplace metadata.
 
 ### Deferred questions
 
-- Empirical check: typeahead prefix filtering on plugin-skill leaf names — `/architect`.
+- Empirical check: typeahead prefix filtering on plugin-skill leaf names — `/planning:plan`.
 - session-flow category label `workflow` — judgment call (no marketplace precedent); revisit if a stronger authoritative label emerges.
 
 ## Plan
 
-(unfilled — /architect)
+(unfilled — /planning:plan)

plugins/claude-ops/.claude-plugin/plugin.json

@@ -1,7 +1,7 @@
 {
   "$schema": "https://json.schemastore.org/claude-code-plugin-manifest.json",
   "name": "claude-ops",
-  "version": "0.10.0",
+  "version": "0.10.1",
   "description": "Claude Code operations toolkit. Five skills: observability (read locally captured telemetry — OTEL store, collector, hook-event JSONL, ccusage — with trend reports and store pruning), known-issues (search known Claude product GitHub bugs, check service health, maintain a persistent tracked-issue registry), changelog (ingest Claude Code changelog entries and integrate them into the current repo), plugins (bring a machine's plugin fleet current on demand — marketplace refresh, effective-scope updates including in-repo project/local installs, new-plugin install per policy, scope-divergence detection and explicit convergence), and a re-runnable setup action that settles where the known-issues registry lives. Plus a family of seven advisory *-audit telemetry-emitter hooks (API errors, config changes, instruction loads, permission denials, pre-compaction, skill usage, tool failures) that emit the shared hook-telemetry envelope, and a reference sink that maps envelopes into the hook-events.jsonl the observability skill reads.",
   "author": {
     "name": "Melodic Software",

plugins/claude-ops/CHANGELOG.md

@@ -3,6 +3,12 @@
 All notable changes to the `claude-ops` plugin are documented here. Format follows
 [Keep a Changelog](https://keepachangelog.com/en/1.1.0/); this plugin uses semantic versioning.
 
+## [0.10.1]
+
+### Changed
+
+- References to the renamed `/planning:plan` skill (was `/planning:architect`, planning 0.13.0 breaking rename) retargeted. Version bumped so existing installs receive the rewritten prompts.
+
 ## [0.10.0]
 
 ### Changed

plugins/claude-ops/skills/changelog/SKILL.md

@@ -49,7 +49,7 @@ Parse `$ARGUMENTS` to extract the action (first token) and remaining arguments.
 
 | Action | Description | Detail |
 |--------|-------------|--------|
-| `apply` | Full pipeline: ingest → explore → research → interview → architect → implement → verify → close issues | See "Action: apply" below |
+| `apply` | Full pipeline: ingest → explore → research → interview → plan → implement → verify → close issues | See "Action: apply" below |
 | `fetch` | Fetch + display changelog for version(s). Read-only | See "Action: fetch" below |
 | `diff` | Fetch + orient on repo impact. Read-only analysis table | See "Action: diff" below |
 | `status` | Show applied versions, open issues, pending work | See "Action: status" below |
@@ -69,7 +69,7 @@ If action is unknown, show action table.
 detects a new CC release in conversation, default to `fetch` or `diff` and offer `apply` — do not
 auto-start the pipeline.
 
-The full pipeline runs explore → research → interview → architect → implement → verify as the phases below. If the consumer project ships its own stage skills for these, prefer them at each phase.
+The full pipeline runs explore → research → interview → plan → implement → verify as the phases below. If the consumer project ships its own stage skills for these, prefer them at each phase.
 
 ### Phase 0 — Ingest
 
@@ -127,7 +127,7 @@ User picks scope: "all P1+P2", "just P1", or specific items by number.
 
 Lock brief: confirmed scope becomes implementation contract.
 
-### Phase 4 — Architect
+### Phase 4 — Plan
 
 Plan concrete edits with cross-cutting awareness:
 
@@ -140,7 +140,7 @@ Plan concrete edits with cross-cutting awareness:
 
 Execute plan:
 
-1. Edit files per architect plan
+1. Edit files per the approved plan
 2. Run the consumer repo's markdown linter on every touched `.md` file (e.g. `npx markdownlint-cli2`), when one is configured
 3. If hook scripts touched: run their tests with the consumer repo's test runner
 4. If settings.json touched: `jq empty .claude/settings.json`

plugins/claude-ops/skills/changelog/evals/evals.json

@@ -9,7 +9,7 @@
       "files": [],
       "expectations": [
         "The response presents changelog content and/or a repo-impact analysis without editing any file",
-        "The response does NOT run the apply pipeline (no interview/architect/implement phases executed) on a passive version mention",
+        "The response does NOT run the apply pipeline (no interview/plan/implement phases executed) on a passive version mention",
         "If integration is relevant, the response offers `apply` as an explicit opt-in step rather than starting it automatically"
       ]
     },

plugins/implementation/.claude-plugin/plugin.json

@@ -1,7 +1,7 @@
 {
   "$schema": "https://json.schemastore.org/claude-code-plugin-manifest.json",
   "name": "implementation",
-  "version": "0.6.1",
+  "version": "0.6.2",
   "description": "Disciplined implementation stage: execute approved plans inline (`/implementation:implement`) or via orchestrated worker subagents (`/implementation:implement-dispatch`) with incremental validation, TDD-by-default cadence, green-checkpoint commits, scope-fence drift detection, and divergence detection that routes back to planning. Build/test/lint, testing, and outcome verification live in the companion `toolchain`, `testing`, and `verification` plugins, invoked when installed.",
   "author": {
     "name": "Melodic Software",

plugins/implementation/CHANGELOG.md

@@ -3,6 +3,12 @@
 All notable changes to the `implementation` plugin are documented here. Format follows
 [Keep a Changelog](https://keepachangelog.com/en/1.1.0/); this plugin uses semantic versioning.
 
+## [0.6.2]
+
+### Changed
+
+- References to the renamed `/planning:plan` skill (was `/planning:architect`, planning 0.13.0 breaking rename) retargeted. Version bumped so existing installs receive the rewritten prompts.
+
 ## [0.6.1]
 
 ### Changed

plugins/implementation/skills/implement-dispatch/SKILL.md

@@ -34,7 +34,7 @@ Run the `/implementation:implement` "Step 1: Prerequisite Check" preflight first
 2. **Dispatch** the worker
 3. **Verify the return against direct evidence before accepting edits** — worker returns are synthesis, not ground truth; promote their claims to direct evidence (diff read, grep, file Read) before building on them
 4. **Build/test main-side** — invoke `/toolchain:check` from the main window when the `toolchain` plugin is installed, otherwise run the project's own build/test command main-side; never accept a worker's green claim as the build signal
-5. **Route worker divergence reports into `/implementation:implement` "Step 3: Divergence Detection"** — a worker STOPping per the divergence-escalation clause is a divergence signal, severity-assessed the same way; the orchestrator revises the brief or routes back to the planning skill (`/planning:architect review` when installed)
+5. **Route worker divergence reports into `/implementation:implement` "Step 3: Divergence Detection"** — a worker STOPping per the divergence-escalation clause is a divergence signal, severity-assessed the same way; the orchestrator revises the brief or routes back to the planning skill (`/planning:plan review` when installed)
 
 ## Divergence in non-interactive runs
 
@@ -62,7 +62,7 @@ Any criterion fails → clear + resume from the emitted prompt. **The phase-boun
 |-----------|--------|
 | Phase is inline-routed (main-window), interactive mode | Hand back to `/implementation:implement` classic cadence |
 | Phase is inline-routed or routing table absent, autonomous mode | Synthesize a worker row and dispatch — the orchestrator never does volume edits |
-| Worker divergence report | Severity-assess per `/implementation:implement` "Step 3: Divergence Detection"; Major → the planning skill (`/planning:architect review` when installed) |
+| Worker divergence report | Severity-assess per `/implementation:implement` "Step 3: Divergence Detection"; Major → the planning skill (`/planning:plan review` when installed) |
 | Every worker return | Verify against direct evidence, then `/toolchain:check` main-side (when the `toolchain` plugin is installed; else the project's own build) |
 | Phase sanity check passes | `/implementation:implement` "Step 4" ritual (its item-1 verifier gate applies in every mode; orchestrated runs dispatch it — see Phase boundaries) |
 | All phases complete | `/implementation:implement` "Step 5: Completion and Handoff" |

plugins/implementation/skills/implement/SKILL.md

@@ -52,7 +52,7 @@ If `$ARGUMENTS` specifies a mode (`feature`, `fix`, `refactor`, `config`), use t
 
 Before writing code, verify the knowledge base:
 
-- **Is there an approved plan?** If yes, use it as execution roadmap. If no plan exists and the task is non-trivial (3+ files, new project, cross-cutting change), suggest a planning pass first — `/planning:architect` when the planning plugin is installed, otherwise whatever plan skill the consuming setup provides (check what's actually available; never invent skill names). For trivial changes (single-file fix, small config edit), proceed without a formal plan
+- **Is there an approved plan?** If yes, use it as execution roadmap. If no plan exists and the task is non-trivial (3+ files, new project, cross-cutting change), suggest a planning pass first — `/planning:plan` when the planning plugin is installed, otherwise whatever plan skill the consuming setup provides (check what's actually available; never invent skill names). For trivial changes (single-file fix, small config edit), proceed without a formal plan
 - **Is the branch correct?** Check pre-computed branch. If on the default branch (`main`/`master`) and the project's workflow expects feature branches, stop and create one (`git checkout -b <type>/<description>`, or `/source-control:worktree` when that plugin is installed)
 - **Are there uncommitted changes?** If dirty working tree with unrelated changes, flag it — don't mix concerns in one commit
 
@@ -74,7 +74,7 @@ Core execution loop. Key discipline: **validate after each logical block, not ju
 
 - **Build fails** → fix immediately. Don't add more code on top of broken code
 - **Test fails unexpectedly** → investigate. An unexpected failure may signal a flawed approach, not just a bug
-- **Scope creep** → if implementation reveals the task is bigger than planned, stop and replan — route back to the planning skill (`/planning:architect review` when installed) rather than expanding scope silently
+- **Scope creep** → if implementation reveals the task is bigger than planned, stop and replan — route back to the planning skill (`/planning:plan review` when installed) rather than expanding scope silently
 - **Too-big-and-foggy (not just bigger)** → if implementation reveals the work is a sprawling set of still-undecided, not-yet-phrasable questions rather than a scoped change, stop building and name `/planning:wayfind` to the user — it charts the fog as a decision map upstream of the plan. Guide, never auto-switch
 
 ### Commit discipline
@@ -108,7 +108,7 @@ Most important discipline in execution. Plans are hypotheses — implementation
 3. **Assess severity:**
    - **Minor** (typo in plan, small API difference) → fix inline, note the deviation
    - **Moderate** (approach needs adjustment but direction is right) → adjust the plan, document what changed and why. Research alternatives before adjusting — don't settle for workarounds when a proper solution may exist
-   - **Major** (fundamental assumption was wrong) → run external research first to find alternative approaches (`/discovery:research` when the discovery plugin is installed, otherwise a disciplined multi-source lookup), THEN route back to the planning skill (`/planning:architect review` when installed) to re-plan. The user approved a plan that no longer works — they need to approve the new direction, informed by fresh research
+   - **Major** (fundamental assumption was wrong) → run external research first to find alternative approaches (`/discovery:research` when the discovery plugin is installed, otherwise a disciplined multi-source lookup), THEN route back to the planning skill (`/planning:plan review` when installed) to re-plan. The user approved a plan that no longer works — they need to approve the new direction, informed by fresh research
 4. **For major divergence:** switch to plan mode for safe exploration while redesigning the approach. Exit plan mode only after the revised plan is clear
 
 **Non-interactive fork (autonomous runs only):** see `/implementation:implement-dispatch` "Divergence in non-interactive runs" — Moderate divergence takes the conservative option + a deviations log instead of deadlocking; Major still STOPS. Interactive sessions keep the escalation ladder above unchanged.
@@ -190,7 +190,7 @@ When all planned work is done:
 | After each logical block | Invoke `/toolchain:check` via Skill tool (when the `toolchain` plugin is installed; else the project's own build) |
 | At every phase boundary | Run the Step 4 ritual (plan marks + handoff entry + status + commit + resume prompt) |
 | Worker-routed phase or autonomous orchestration | Invoke `/implementation:implement-dispatch` via Skill tool |
-| Divergence detected (major) | Route back to the planning skill (`/planning:architect review` when installed) |
+| Divergence detected (major) | Route back to the planning skill (`/planning:plan review` when installed) |
 | Technical question mid-implementation | `/discovery:research` (when installed), otherwise disciplined multi-source research |
 | HIGH/CRITICAL change at completion | Call the `advisor` tool — rubber-duck checkpoint before review |
 | All implementation complete, tests pass | `/verification:confirm` (when the `verification` plugin is installed; else self-verify against intent), then suggest the project's review/PR flow (`/review:quality-gate`, `/source-control:pull-request` when installed) |

plugins/implementation/skills/implement/evals/evals.json

@@ -30,7 +30,7 @@
       "id": 3,
       "name": "major-divergence-routes-back-to-planning",
       "prompt": "/implementation:implement — I approved a plan that assumed the vendor SDK exposes a streaming API, but partway through it's clear the SDK only supports batch calls, so the whole approach doesn't fit. Keep going and make it work.",
-      "expected_output": "Recognizes this as major divergence (a fundamental plan assumption was wrong), STOPS writing code rather than forcing workarounds, runs external research for alternative approaches first, then routes back to the planning skill (/planning:architect review when installed) so the user can approve the new direction — it does not silently push through with hacks.",
+      "expected_output": "Recognizes this as major divergence (a fundamental plan assumption was wrong), STOPS writing code rather than forcing workarounds, runs external research for alternative approaches first, then routes back to the planning skill (/planning:plan review when installed) so the user can approve the new direction — it does not silently push through with hacks.",
       "files": [],
       "expectations": [
         "Classifies the wrong SDK-capability assumption as major divergence, not a minor inline fixup",

plugins/knowledge/.claude-plugin/plugin.json

@@ -1,7 +1,7 @@
 {
   "$schema": "https://json.schemastore.org/claude-code-plugin-manifest.json",
   "name": "knowledge",
-  "version": "0.6.0",
+  "version": "0.6.1",
   "description": "Ingest external knowledge into durable, synthesized artifacts. Ships a book-distillation pipeline (PDF/EPUB into concept-organized, author-attributed skill reference files), a YouTube pipeline (watch, transcript, link harvest, and repo-applicability synthesis), and a course-digest pipeline (extract and synthesize online video courses — Dometrain, Teachable — into repo-applicable recommendations), plus a re-runnable setup action; a configurable library directory governs where synthesized artifacts land in the consuming repo.",
   "author": {
     "name": "Melodic Software",

plugins/knowledge/CHANGELOG.md

@@ -4,6 +4,12 @@ All notable changes to the `knowledge` plugin are recorded here. The `version` i
 `.claude-plugin/plugin.json` is the delivery vehicle — a consumer receives a change
 only after that version increases.
 
+## 0.6.1
+
+### Changed
+
+- References to the renamed `/planning:plan` skill (was `/planning:architect`, planning 0.13.0 breaking rename) retargeted. Version bumped so existing installs receive the rewritten prompts.
+
 ## 0.6.0
 
 ### Changed

plugins/knowledge/skills/youtube-digest/SKILL.md

@@ -266,7 +266,7 @@ node "${CLAUDE_PLUGIN_ROOT}/skills/youtube-digest/extraction/run.mjs" evals/chec
    - `recommendations/questions.md` — open questions for the user
    - Update `README.md` per `templates/readme-journey.md`
    - **Offer an HTML view** — optionally render a self-contained HTML dashboard of the prioritized recommendations menu (markdown stays the tracked record); follow your project's HTML-vs-markdown convention when one exists.
-   - **No auto-implement** — `/interview` → `/architect` → `/implement`
+   - **No auto-implement** — `/interview` → `/planning:plan` → `/implement`
 
 2. **Interview handoff** — write `recommendations/interview.md` with menu + *"Should we go further?"*; suggest `/interview` for POC/full-slice items.
 

plugins/knowledge/skills/youtube-digest/context/quality-gates.md

@@ -144,7 +144,7 @@ When `watch.json` / `selection.json` sets `highVolume: true`:
 | `recommendations/questions.md` | Yes |
 | `recommendations/interview.md` | Yes |
 | `README.md` updated | Yes — per `templates/readme-journey.md` |
-| Auto-implement | **No** — `/interview` → `/architect` → `/implement` |
+| Auto-implement | **No** — `/interview` → `/planning:plan` → `/implement` |
 
 ## Complete slice