bms-speckit-plugin 4.2.0 → 4.3.1

package/.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "bms-speckit",
-  "version": "4.2.0",
+  "version": "4.3.0",
   "description": "Chain-orchestrated development pipeline with per-step error handling. /bms-speckit runs brainstorm → constitution → specify → plan → tasks → analyze → implement → verify.",
   "author": {
     "name": "manoirx"

package/blueprints/bms-speckit-pipeline.yaml

@@ -9,14 +9,14 @@
 # to prevent loss and provide traceability per the project constitution.
 
 id: bms_speckit_development_pipeline
-version: 4.2.0
+version: 4.3.0
 name: BMS Speckit Automated Development Pipeline
 description: >
   Full engineering workflow from requirement to verified implementation.
-  Chains brainstorming, constitution, knowledge research, specification,
-  planning, task generation, analysis, implementation (TDD), and final
-  verification. Commits after every important step. Uses knowledge-mcp
-  to ground specifications in real HOSxP data dictionaries and system design.
+  Chains brainstorming, constitution, specification, planning, task generation,
+  analysis, implementation (TDD), and final verification.
+  Commits after every important step. Uses knowledge-mcp during brainstorm
+  and specify steps to ground specs in real HOSxP data.
 category: Development
 
 # ─── Chain Sequence ────────────────────────────────────────────────────────────
@@ -46,6 +46,10 @@ chain_sequence:
       system_context: >
         Write a detailed specification from the user's requirement.
         Explore edge cases, constraints, and design alternatives.
+        Use mcp__bms-knowledge-mcp__search_knowledge to search the hosxp
+        collection for relevant data dictionaries, table schemas, and
+        system architecture. Also search bms, moph, nhso collections
+        if relevant to the feature.
 
   - step_id: step_2_constitution
     skill_id: speckit.constitution
@@ -101,41 +105,7 @@ chain_sequence:
         Read CLAUDE.md and verify it complies with specs/constitution.md.
         Update CLAUDE.md if it conflicts with or is missing constitution rules.
 
-  - step_id: step_4_knowledge_research
-    skill_id: internal.knowledge_mcp_search
-    action: execute
-    phase: 1
-    description: Search knowledge base for HOSxP data dictionaries, system design, and regulatory context
-    timeout_seconds: 300
-    input:
-      query: "{{step_1_brainstorm.output}}"
-      collections:
-        - hosxp    # 49 sources — data dictionaries, ER diagrams, table schemas, module architecture
-        - bms      # 3 sources — BMS tools, organization, API info
-        - moph     # 3 sources — Ministry of Public Health regulations
-        - nhso     # 44 sources — NHSO reimbursement rules and announcements
-    output:
-      artifacts: [knowledge_context]
-    post_action:
-      commit: true
-      message: "feat(speckit): add knowledge research from HOSxP data dictionary"
-      push: true
-    error_handling:
-      on_failure: continue
-      max_retries: 2
-    opinionated_prompts:
-      system_context: >
-        Use the knowledge-mcp MCP server to search for relevant context.
-        Search the hosxp collection for: data dictionaries, table schemas,
-        ER diagrams, and system architecture related to the feature.
-        Search bms for API and tool context.
-        Search moph/nhso if the feature involves regulatory compliance or
-        reimbursement rules.
-        Compile findings into a knowledge context document that will
-        inform the specification step. Include exact table names, field
-        names, data types, and relationships discovered.
-
-  - step_id: step_5_specify
+  - step_id: step_4_specify
     skill_id: speckit.specify
     action: execute
     phase: 1
@@ -143,7 +113,6 @@ chain_sequence:
     timeout_seconds: 300
     input:
       requirement: "{{step_1_brainstorm.output}}"
-      knowledge_context: "{{step_4_knowledge_research.output}}"
     output:
       artifacts: [specs/*/spec.md]
     post_action:
@@ -157,18 +126,19 @@ chain_sequence:
       system_context: >
         Generate a complete, testable specification. Include acceptance criteria,
         data models, API contracts, and edge cases.
-        IMPORTANT: Use the knowledge context from step 4 to ground the spec
-        in real HOSxP table structures, field names, and data types.
-        Reference actual table names and columns from the data dictionary.
+        Use mcp__bms-knowledge-mcp__search_knowledge to search the hosxp
+        collection for exact table names, field names, data types, and
+        relationships needed by this feature. Reference actual HOSxP
+        data structures in the spec, not assumed ones.
 
-  - step_id: step_6_plan
+  - step_id: step_5_plan
     skill_id: speckit.plan
     action: execute
     phase: 1
     description: Generate implementation plan from specification
     timeout_seconds: 300
     input:
-      source: "{{step_5_specify.artifacts}}"
+      source: "{{step_4_specify.artifacts}}"
     output:
       artifacts: [specs/*/plan.md]
     post_action:
@@ -183,14 +153,14 @@ chain_sequence:
         Plan in ordered steps. Include file paths, component boundaries,
         test strategy, and rollback considerations.
 
-  - step_id: step_7_tasks
+  - step_id: step_6_tasks
     skill_id: speckit.tasks
     action: execute
     phase: 1
     description: Generate dependency-ordered task list
     timeout_seconds: 300
     input:
-      source: "{{step_6_plan.artifacts}}"
+      source: "{{step_5_plan.artifacts}}"
     output:
       artifacts: [specs/*/tasks.md]
     post_action:
@@ -205,14 +175,14 @@ chain_sequence:
         Tasks must be atomic, dependency-ordered, and each independently testable.
         Include clear acceptance criteria per task.
 
-  - step_id: step_8_analyze
+  - step_id: step_7_analyze
     skill_id: speckit.analyze
     action: execute
     phase: 1
     description: Cross-artifact consistency and quality check
     timeout_seconds: 300
     input:
-      source: "{{step_7_tasks.artifacts}}"
+      source: "{{step_6_tasks.artifacts}}"
     output:
       artifacts: [analysis_report]
     post_action:
@@ -229,7 +199,7 @@ chain_sequence:
 
   # ── Phase 2: Implementation (main context) ────────────────────────────────
 
-  - step_id: step_9_compact
+  - step_id: step_8_compact
     skill_id: internal.compact
     action: execute
     phase: 2
@@ -239,14 +209,14 @@ chain_sequence:
       on_failure: continue
       max_retries: 0
 
-  - step_id: step_10_implement
+  - step_id: step_9_implement
     skill_id: speckit.implement
     action: execute_loop
     phase: 2
     description: Execute all tasks with TDD workflow via ralph-loop
     timeout_seconds: 3600
     input:
-      tasks_path: "{{step_7_tasks.artifacts}}"
+      tasks_path: "{{step_6_tasks.artifacts}}"
       loop_engine: ralph-loop
       completion_promise: "FINISHED"
       max_iterations: 10
@@ -270,7 +240,7 @@ chain_sequence:
         apply improvements, re-run all tests, confirm zero regression.
         Only output FINISHED after everything is validated.
 
-  - step_id: step_11_verify
+  - step_id: step_10_verify
     skill_id: speckit.analyze
     action: execute
     phase: 2
@@ -288,7 +258,7 @@ chain_sequence:
         Final gate. Verify all tasks completed, tests passing,
         no regressions, code quality standards met.
 
-  - step_id: step_12_merge
+  - step_id: step_11_merge
     skill_id: internal.git_merge_to_main
     action: execute
     phase: 2
@@ -310,21 +280,21 @@ metadata:
   author: manoirx
   created_at: "2026-03-29"
   tags: [speckit, tdd, workflow, development, chain, engineering, hosxp, knowledge]
-  estimated_duration_seconds: 6500
+  estimated_duration_seconds: 6000
   commit_strategy: per_step
   knowledge_collections:
-    hosxp: "49 sources — data dictionaries, ER diagrams, table schemas, module architecture"
-    bms: "3 sources — BMS tools, organization, API info"
-    moph: "3 sources — Ministry of Public Health regulations"
-    nhso: "44 sources — NHSO reimbursement rules and announcements"
+    hosxp: "Data dictionaries, ER diagrams, table schemas, module architecture"
+    bms: "BMS tools, organization, API info"
+    moph: "Ministry of Public Health regulations"
+    nhso: "NHSO reimbursement rules and announcements"
   phases:
     phase_1:
       name: Specification & Planning
-      steps: [step_1 through step_8]
+      steps: [step_1 through step_7]
       execution: subagent
       reason: Preserve main context window for implementation
     phase_2:
       name: Implementation & Verification & Merge
-      steps: [step_9 through step_12]
+      steps: [step_8 through step_11]
       execution: main_context
       reason: Implementation needs full tool access and ralph-loop

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "bms-speckit-plugin",
-  "version": "4.2.0",
+  "version": "4.3.1",
   "description": "Chain-orchestrated development pipeline: /bms-speckit takes requirements and runs brainstorm → constitution → specify → plan → tasks → analyze → implement → verify with per-step error handling",
   "files": [
     ".claude-plugin/",

package/skills/bms-speckit-auto/SKILL.md

@@ -14,7 +14,7 @@ Chain blueprint: `blueprints/bms-speckit-pipeline.yaml`
 3. On step failure, check the **error policy** before proceeding:
    - `on_failure: stop` → halt the chain and report which step failed
    - `on_failure: continue` → log the failure and proceed to next step
-4. Pass `$ARGUMENTS` (the user's requirement) to step 1 (brainstorm). Step 5 (specify) receives the **output from step 1** enriched with **knowledge context from step 4**
+4. Pass `$ARGUMENTS` (the user's requirement) to step 1 (brainstorm). Step 4 (specify) receives the **output from step 1**
 5. **Commit and push after every important step** — each artifact-producing step must commit its output before proceeding to the next step
 6. Do NOT ask for confirmation between steps
 
@@ -33,6 +33,7 @@ You are running the BMS Speckit specification and planning chain. Execute each s
 - **Skill:** `superpowers.brainstorm`
 - **Input:** "$ARGUMENTS"
 - **Purpose:** Explore intent, requirements, design alternatives, and edge cases
+- **Knowledge lookup:** Use `mcp__bms-knowledge-mcp__search_knowledge` to search the `hosxp` collection for relevant data dictionaries, table schemas, and system architecture. Also search `bms`, `moph`, `nhso` collections if relevant.
 - **Output:** Detailed specification document
 - **Timeout:** 300s
 - **Post-action:** Commit all files and push. Message: `feat(speckit): brainstorm — explore requirements and design`
@@ -48,43 +49,32 @@ You are running the BMS Speckit specification and planning chain. Execute each s
 - **Timeout:** 120s
 - **Post-action:** Commit all files and push. Message: `feat(speckit): add constitution and sync CLAUDE.md`
 
-### Step 4 — Knowledge Research `[on_failure: CONTINUE]`
-- **Tool:** `mcp__knowledge-mcp__search_knowledge` (MCP tool, not a skill)
-- **Purpose:** Search HOSxP knowledge base for data dictionaries, table schemas, ER diagrams, system architecture, and regulatory context relevant to the feature
-- **Timeout:** 300s
-- **Searches to perform:**
-  1. Search collection `hosxp` for table schemas and data dictionary related to the brainstorm output (e.g. patient tables, OPD/IPD tables, lab, pharmacy, appointments — whatever is relevant to the feature)
-  2. Search collection `hosxp` for system architecture and module design related to the feature
-  3. Search collection `bms` for BMS API and tool context if relevant
-  4. Search collection `moph` or `nhso` if the feature involves regulatory compliance or reimbursement rules
-- **Output:** Compile all findings into a knowledge context summary with exact table names, field names, data types, and relationships. Save to `specs/*/knowledge-context.md`
-- **Post-action:** Commit all files and push. Message: `feat(speckit): add knowledge research from HOSxP data dictionary`
-
-### Step 5 — Specify `[on_failure: STOP]`
+### Step 4 — Specify `[on_failure: STOP]`
 - **Skill:** `speckit.specify`
-- **Input:** Use the detailed specification output from Step 1 (brainstorm) as the argument. **IMPORTANT:** Also incorporate the knowledge context from Step 4 — reference actual HOSxP table names, field names, and data types in the specification.
+- **Input:** Use the detailed specification output from Step 1 (brainstorm) as the argument
+- **Knowledge lookup:** Use `mcp__bms-knowledge-mcp__search_knowledge` to search the `hosxp` collection for exact table names, field names, data types, and relationships needed by this feature. Reference actual HOSxP data structures in the spec.
 - **Output:** `specs/*/spec.md`
 - **Timeout:** 300s
 - **Retry:** up to 2 attempts
 - **Post-action:** Commit all files and push. Message: `feat(speckit): add feature specification`
 
-### Step 6 — Plan `[on_failure: STOP]`
+### Step 5 — Plan `[on_failure: STOP]`
 - **Skill:** `speckit.plan`
-- **Input:** reads from step 5 artifacts
+- **Input:** reads from step 4 artifacts
 - **Output:** `specs/*/plan.md`
 - **Timeout:** 300s
 - **Retry:** up to 2 attempts
 - **Post-action:** Commit all files and push. Message: `feat(speckit): add implementation plan`
 
-### Step 7 — Tasks `[on_failure: STOP]`
+### Step 6 — Tasks `[on_failure: STOP]`
 - **Skill:** `speckit.tasks`
-- **Input:** reads from step 6 artifacts
+- **Input:** reads from step 5 artifacts
 - **Output:** `specs/*/tasks.md`
 - **Timeout:** 300s
 - **Retry:** up to 2 attempts
 - **Post-action:** Commit all files and push. Message: `feat(speckit): add task list`
 
-### Step 8 — Analyze `[on_failure: CONTINUE]`
+### Step 7 — Analyze `[on_failure: CONTINUE]`
 - **Skill:** `speckit.analyze`
 - **Purpose:** Cross-artifact consistency check (spec ↔ plan ↔ tasks). Non-destructive — report only.
 - **Timeout:** 300s
@@ -99,10 +89,10 @@ After all steps complete, return: the feature name, number of tasks created, and
 
 > **Execution context:** Runs in main context after subagent completes.
 
-### Step 9 — Compact `[on_failure: CONTINUE]`
+### Step 8 — Compact `[on_failure: CONTINUE]`
 - **Action:** Run `/compact` to free context window before implementation.
 
-### Step 10 — Implement (loop) `[on_failure: CONTINUE | max_retries: 3]`
+### Step 9 — Implement (loop) `[on_failure: CONTINUE | max_retries: 3]`
 - **Engine:** ralph-loop
 - **Input:** Use the **tasks.md path returned by the Phase 1 subagent** (e.g. `specs/my-feature/tasks.md`). Replace `{TASKS_PATH}` below with the actual path.
 - **Completion promise:** `FINISHED`
@@ -112,13 +102,13 @@ After all steps complete, return: the feature name, number of tasks created, and
 
 `/ralph-loop:ralph-loop "systematically execute speckit.implement via the Skill tool to complete every task defined in {TASKS_PATH} with strict adherence to specification requirements, enforce TDD workflow including writing and passing unit, integration, and end-to-end tests before marking any task complete, ensure code quality through linting, static analysis, and consistent architecture with reusable components and centralized business logic, maintain atomic commits after each successful task with clear traceability, avoid requesting confirmation and proceed autonomously, once all tasks are implemented invoke speckit.analyze via the Skill tool to perform a full validation pass, automatically apply all recommended improvements or corrections, re-run all tests to confirm stability and zero regression, and only output <promise>FINISHED</promise> after every task is fully completed, validated, and aligned with production-grade quality standards" --completion-promise "FINISHED" --max-iterations 10`
 
-### Step 11 — Verify `[on_failure: STOP]`
+### Step 10 — Verify `[on_failure: STOP]`
 - **Skill:** `speckit.analyze`
 - **Purpose:** Final validation — confirm all tasks completed, tests passing, no regressions, code quality standards met.
 - **Timeout:** 300s
 - **Post-action:** Commit all files and push. Message: `chore(speckit): final verification pass complete`
 
-### Step 12 — Merge to Main `[on_failure: STOP]`
+### Step 11 — Merge to Main `[on_failure: STOP]`
 - **Action:** Switch to main branch, merge the feature branch (fast-forward if possible), push main to remote, then clean up the feature branch.
 - **Timeout:** 120s
 
@@ -127,23 +117,15 @@ After all steps complete, return: the feature name, number of tasks created, and
 ## Chain Summary
 
 ```
-Phase 1 (subagent)                              Phase 2 (main context)
-──────────────────────────────────              ──────────────────────────────
-Step 1:  brainstorm ──────STOP── commit         Step 9:  compact
-Step 2:  constitution ────STOP─┐                Step 10: implement (ralph-loop)
-Step 3:  CLAUDE.md sync ──────┘ commit                   commit per task
-Step 4:  knowledge research ─── commit          Step 11: verify ── commit
-Step 5:  specify ─────────STOP── commit         Step 12: merge to main + push
-Step 6:  plan ────────────STOP── commit
-Step 7:  tasks ───────────STOP── commit
-Step 8:  analyze ────────────── commit
+Phase 1 (subagent)                          Phase 2 (main context)
+──────────────────────────────              ──────────────────────────────
+Step 1: brainstorm ──STOP── commit          Step 8:  compact
+        + knowledge search (hosxp)          Step 9:  implement (ralph-loop)
+Step 2: constitution ─STOP─┐                         commit per task
+Step 3: CLAUDE.md sync ───┘ commit          Step 10: verify ── commit
+Step 4: specify ──────STOP── commit         Step 11: merge to main + push
+        + knowledge search (hosxp)
+Step 5: plan ─────────STOP── commit
+Step 6: tasks ────────STOP── commit
+Step 7: analyze ──────────── commit
 ```
-
-### Knowledge Collections Available
-
-| Collection | Sources | Content |
-|---|---|---|
-| `hosxp` | 49 | Data dictionaries, ER diagrams, table schemas, module architecture |
-| `bms` | 3 | BMS tools, organization, API info |
-| `moph` | 3 | Ministry of Public Health regulations |
-| `nhso` | 44 | NHSO reimbursement rules and announcements |