Merge 4a0c59ff8b into e36f219c81

* refactor(catalog): rename after/before columns to preceded-by/followed-by

The bare prepositions `after` and `before` had no subject anchor, leaving
the dependency direction ambiguous: "X has Y in its `after` column" reads
plausibly as either "Y comes after X" or "X comes after Y". An LLM
catalog consumer just got the direction wrong because of this.

`preceded-by` / `followed-by` are passive-voice participles whose grammar
locks the subject (the skill in this row) and forces a single reading:
"X is preceded by Y" can only mean Y comes first.

Rename applied to:
- module-help.csv headers (bmm-skills, core-skills)
- bmad-help SKILL.md schema doc + descriptions
- installer.js mergeModuleHelpCatalogs header string
- plugin-resolver.js _buildSynthesizedHelpCsv header string
- bmad-manifest.json keys (bmad-product-brief, bmad-prfaq)
- distillate-format-reference.md example manifest

The separate `required` column continues to carry hard-gate semantics;
the renamed columns are pure soft sequencing hints, as already documented
in bmad-help.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* style(installer): wrap long header strings per prettier

* feat(installer): warn on non-canonical module-help.csv headers

mergeModuleHelpCatalogs now compares each per-module file's header
against the canonical schema and emits a one-shot prompts.log.warn per
module on drift, naming both the expected and actual header. Data
continues to load positionally so external modules built against the
old after/before schema still install cleanly — the warning is the
maintainer signal to rename their columns.

Centralize the canonical header in modules/module-help-schema.js so the
merger and the synthesizer (PluginResolver._buildSynthesizedHelpCsv)
read the same source of truth; future column renames are one edit.

Verified by installing all four bmad-org external modules
(bmb, cis, gds, tea) — every one ships the legacy after/before header
today and now fires an advisory warning while still merging cleanly
into _bmad/_config/bmad-help.csv with the canonical column names.

---------

Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

src/bmm-skills/1-analysis/bmad-agent-analyst/SKILL.md

@@ -46,7 +46,7 @@ Treat every entry in `{agent.persistent_facts}` as foundational context you carr
 
 ### Step 5: Load Config
 
-Load config from `{project-root}/_bmad/bmm/config.yaml` and resolve:
+Load config by running `python3 {project-root}/_bmad/scripts/resolve_config.py --project-root {project-root}` (requires Python 3.11+). If the command fails, read the merge logic in `{project-root}/_bmad/scripts/resolve_config.py` and apply it yourself to resolve the config variables. Resolve:
 - Use `{user_name}` for greeting
 - Use `{communication_language}` for all communications
 - Use `{document_output_language}` for output documents

src/bmm-skills/1-analysis/bmad-agent-tech-writer/SKILL.md

@@ -46,7 +46,7 @@ Treat every entry in `{agent.persistent_facts}` as foundational context you carr
 
 ### Step 5: Load Config
 
-Load config from `{project-root}/_bmad/bmm/config.yaml` and resolve:
+Load config by running `python3 {project-root}/_bmad/scripts/resolve_config.py --project-root {project-root}` (requires Python 3.11+). If the command fails, read the merge logic in `{project-root}/_bmad/scripts/resolve_config.py` and apply it yourself to resolve the config variables. Resolve:
 - Use `{user_name}` for greeting
 - Use `{communication_language}` for all communications
 - Use `{document_output_language}` for output documents

src/bmm-skills/1-analysis/bmad-document-project/SKILL.md

@@ -40,7 +40,7 @@ Treat every entry in `{workflow.persistent_facts}` as foundational context you c
 
 ### Step 4: Load Config
 
-Load config from `{project-root}/_bmad/bmm/config.yaml` and resolve:
+Load config by running `python3 {project-root}/_bmad/scripts/resolve_config.py --project-root {project-root}` (requires Python 3.11+). If the command fails, read the merge logic in `{project-root}/_bmad/scripts/resolve_config.py` and apply it yourself to resolve the config variables. Resolve:
 - Use `{user_name}` for greeting
 - Use `{communication_language}` for all communications
 - Use `{document_output_language}` for output documents

src/bmm-skills/1-analysis/bmad-document-project/workflows/deep-dive-workflow.md

@@ -11,7 +11,7 @@
 
 ### Configuration Loading
 
-Load config from `{project-root}/_bmad/bmm/config.yaml` and resolve:
+Load config by running `python3 {project-root}/_bmad/scripts/resolve_config.py --project-root {project-root}` (requires Python 3.11+). If the command fails, read the merge logic in `{project-root}/_bmad/scripts/resolve_config.py` and apply it yourself to resolve the config variables. Resolve:
 
 - `project_knowledge`
 - `user_name`

src/bmm-skills/1-analysis/bmad-document-project/workflows/full-scan-workflow.md

@@ -10,7 +10,7 @@
 
 ### Configuration Loading
 
-Load config from `{project-root}/_bmad/bmm/config.yaml` and resolve:
+Load config by running `python3 {project-root}/_bmad/scripts/resolve_config.py --project-root {project-root}` (requires Python 3.11+). If the command fails, read the merge logic in `{project-root}/_bmad/scripts/resolve_config.py` and apply it yourself to resolve the config variables. Resolve:
 
 - `project_knowledge`
 - `user_name`

src/bmm-skills/1-analysis/bmad-prfaq/SKILL.md

@@ -50,7 +50,7 @@ Treat every entry in `{workflow.persistent_facts}` as foundational context you c
 
 ### Step 4: Load Config
 
-Load config from `{project-root}/_bmad/bmm/config.yaml` and resolve:
+Load config by running `python3 {project-root}/_bmad/scripts/resolve_config.py --project-root {project-root}` (requires Python 3.11+). If the command fails, read the merge logic in `{project-root}/_bmad/scripts/resolve_config.py` and apply it yourself to resolve the config variables. Resolve:
 - Use `{user_name}` for greeting
 - Use `{communication_language}` for all communications
 - Use `{document_output_language}` for output documents

src/bmm-skills/1-analysis/bmad-prfaq/bmad-manifest.json

@@ -7,8 +7,8 @@
       "description": "Produces battle-tested PRFAQ document and optional LLM distillate for PRD input.",
       "supports-headless": true,
       "phase-name": "1-analysis",
-      "after": ["brainstorming", "perform-research"],
+      "preceded-by": ["brainstorming", "perform-research"],
-      "before": ["create-prd"],
+      "followed-by": ["create-prd"],
       "is-required": false,
       "output-location": "{planning_artifacts}"
     }

src/bmm-skills/1-analysis/bmad-product-brief/SKILL.md

@@ -59,7 +59,7 @@ Treat every entry in `{workflow.persistent_facts}` as foundational context you c
 
 ### Step 4: Load Config
 
-Load config from `{project-root}/_bmad/bmm/config.yaml` and resolve:
+Load config by running `python3 {project-root}/_bmad/scripts/resolve_config.py --project-root {project-root}` (requires Python 3.11+). If the command fails, read the merge logic in `{project-root}/_bmad/scripts/resolve_config.py` and apply it yourself to resolve the config variables. Resolve:
 - Use `{user_name}` for greeting
 - Use `{communication_language}` for all communications
 - Use `{document_output_language}` for output documents

src/bmm-skills/1-analysis/bmad-product-brief/bmad-manifest.json

@@ -8,8 +8,8 @@
       "description": "Produces executive product brief and optional LLM distillate for PRD input.",
       "supports-headless": true,
       "phase-name": "1-analysis",
-      "after": ["brainstorming", "perform-research"],
+      "preceded-by": ["brainstorming", "perform-research"],
-      "before": ["create-prd"],
+      "followed-by": ["create-prd"],
       "is-required": true,
       "output-location": "{planning_artifacts}"
     }

src/bmm-skills/1-analysis/research/bmad-domain-research/SKILL.md

@@ -44,7 +44,7 @@ Treat every entry in `{workflow.persistent_facts}` as foundational context you c
 
 ### Step 4: Load Config
 
-Load config from `{project-root}/_bmad/bmm/config.yaml` and resolve:
+Load config by running `python3 {project-root}/_bmad/scripts/resolve_config.py --project-root {project-root}` (requires Python 3.11+). If the command fails, read the merge logic in `{project-root}/_bmad/scripts/resolve_config.py` and apply it yourself to resolve the config variables. Resolve:
 - Use `{user_name}` for greeting
 - Use `{communication_language}` for all communications
 - Use `{document_output_language}` for output documents

src/bmm-skills/1-analysis/research/bmad-market-research/SKILL.md

@@ -44,7 +44,7 @@ Treat every entry in `{workflow.persistent_facts}` as foundational context you c
 
 ### Step 4: Load Config
 
-Load config from `{project-root}/_bmad/bmm/config.yaml` and resolve:
+Load config by running `python3 {project-root}/_bmad/scripts/resolve_config.py --project-root {project-root}` (requires Python 3.11+). If the command fails, read the merge logic in `{project-root}/_bmad/scripts/resolve_config.py` and apply it yourself to resolve the config variables. Resolve:
 - Use `{user_name}` for greeting
 - Use `{communication_language}` for all communications
 - Use `{document_output_language}` for output documents

src/bmm-skills/1-analysis/research/bmad-technical-research/SKILL.md

@@ -44,7 +44,7 @@ Treat every entry in `{workflow.persistent_facts}` as foundational context you c
 
 ### Step 4: Load Config
 
-Load config from `{project-root}/_bmad/bmm/config.yaml` and resolve:
+Load config by running `python3 {project-root}/_bmad/scripts/resolve_config.py --project-root {project-root}` (requires Python 3.11+). If the command fails, read the merge logic in `{project-root}/_bmad/scripts/resolve_config.py` and apply it yourself to resolve the config variables. Resolve:
 - Use `{user_name}` for greeting
 - Use `{communication_language}` for all communications
 - Use `{document_output_language}` for output documents

src/bmm-skills/2-plan-workflows/bmad-agent-pm/SKILL.md

@@ -46,7 +46,7 @@ Treat every entry in `{agent.persistent_facts}` as foundational context you carr
 
 ### Step 5: Load Config
 
-Load config from `{project-root}/_bmad/bmm/config.yaml` and resolve:
+Load config by running `python3 {project-root}/_bmad/scripts/resolve_config.py --project-root {project-root}` (requires Python 3.11+). If the command fails, read the merge logic in `{project-root}/_bmad/scripts/resolve_config.py` and apply it yourself to resolve the config variables. Resolve:
 - Use `{user_name}` for greeting
 - Use `{communication_language}` for all communications
 - Use `{document_output_language}` for output documents

src/bmm-skills/2-plan-workflows/bmad-agent-ux-designer/SKILL.md

@@ -46,7 +46,7 @@ Treat every entry in `{agent.persistent_facts}` as foundational context you carr
 
 ### Step 5: Load Config
 
-Load config from `{project-root}/_bmad/bmm/config.yaml` and resolve:
+Load config by running `python3 {project-root}/_bmad/scripts/resolve_config.py --project-root {project-root}` (requires Python 3.11+). If the command fails, read the merge logic in `{project-root}/_bmad/scripts/resolve_config.py` and apply it yourself to resolve the config variables. Resolve:
 - Use `{user_name}` for greeting
 - Use `{communication_language}` for all communications
 - Use `{document_output_language}` for output documents

src/bmm-skills/2-plan-workflows/bmad-create-prd/SKILL.md

@@ -73,7 +73,7 @@ Treat every entry in `{workflow.persistent_facts}` as foundational context you c
 
 ### Step 4: Load Config
 
-Load config from `{project-root}/_bmad/bmm/config.yaml` and resolve:
+Load config by running `python3 {project-root}/_bmad/scripts/resolve_config.py --project-root {project-root}` (requires Python 3.11+). If the command fails, read the merge logic in `{project-root}/_bmad/scripts/resolve_config.py` and apply it yourself to resolve the config variables. Resolve:
 - Use `{user_name}` for greeting
 - Use `{communication_language}` for all communications
 - Use `{document_output_language}` for output documents

src/bmm-skills/2-plan-workflows/bmad-create-ux-design/SKILL.md

@@ -47,7 +47,7 @@ Treat every entry in `{workflow.persistent_facts}` as foundational context you c
 
 ### Step 4: Load Config
 
-Load config from `{project-root}/_bmad/bmm/config.yaml` and resolve:
+Load config by running `python3 {project-root}/_bmad/scripts/resolve_config.py --project-root {project-root}` (requires Python 3.11+). If the command fails, read the merge logic in `{project-root}/_bmad/scripts/resolve_config.py` and apply it yourself to resolve the config variables. Resolve:
 - Use `{user_name}` for greeting
 - Use `{communication_language}` for all communications
 - Use `{document_output_language}` for output documents

src/bmm-skills/2-plan-workflows/bmad-edit-prd/SKILL.md

@@ -73,7 +73,7 @@ Treat every entry in `{workflow.persistent_facts}` as foundational context you c
 
 ### Step 4: Load Config
 
-Load config from `{project-root}/_bmad/bmm/config.yaml` and resolve:
+Load config by running `python3 {project-root}/_bmad/scripts/resolve_config.py --project-root {project-root}` (requires Python 3.11+). If the command fails, read the merge logic in `{project-root}/_bmad/scripts/resolve_config.py` and apply it yourself to resolve the config variables. Resolve:
 - Use `{user_name}` for greeting
 - Use `{communication_language}` for all communications
 - Use `{document_output_language}` for output documents

src/bmm-skills/2-plan-workflows/bmad-validate-prd/SKILL.md

@@ -73,7 +73,7 @@ Treat every entry in `{workflow.persistent_facts}` as foundational context you c
 
 ### Step 4: Load Config
 
-Load config from `{project-root}/_bmad/bmm/config.yaml` and resolve:
+Load config by running `python3 {project-root}/_bmad/scripts/resolve_config.py --project-root {project-root}` (requires Python 3.11+). If the command fails, read the merge logic in `{project-root}/_bmad/scripts/resolve_config.py` and apply it yourself to resolve the config variables. Resolve:
 - Use `{user_name}` for greeting
 - Use `{communication_language}` for all communications
 - Use `{document_output_language}` for output documents

src/bmm-skills/3-solutioning/bmad-agent-architect/SKILL.md

@@ -46,7 +46,7 @@ Treat every entry in `{agent.persistent_facts}` as foundational context you carr
 
 ### Step 5: Load Config
 
-Load config from `{project-root}/_bmad/bmm/config.yaml` and resolve:
+Load config by running `python3 {project-root}/_bmad/scripts/resolve_config.py --project-root {project-root}` (requires Python 3.11+). If the command fails, read the merge logic in `{project-root}/_bmad/scripts/resolve_config.py` and apply it yourself to resolve the config variables. Resolve:
 - Use `{user_name}` for greeting
 - Use `{communication_language}` for all communications
 - Use `{document_output_language}` for output documents

src/bmm-skills/3-solutioning/bmad-check-implementation-readiness/SKILL.md

@@ -69,7 +69,7 @@ Treat every entry in `{workflow.persistent_facts}` as foundational context you c
 
 ### Step 4: Load Config
 
-Load config from `{project-root}/_bmad/bmm/config.yaml` and resolve:
+Load config by running `python3 {project-root}/_bmad/scripts/resolve_config.py --project-root {project-root}` (requires Python 3.11+). If the command fails, read the merge logic in `{project-root}/_bmad/scripts/resolve_config.py` and apply it yourself to resolve the config variables. Resolve:
 - Use `{user_name}` for greeting
 - Use `{communication_language}` for all communications
 - Use `{document_output_language}` for output documents

src/bmm-skills/3-solutioning/bmad-create-architecture/SKILL.md

@@ -50,7 +50,7 @@ Treat every entry in `{workflow.persistent_facts}` as foundational context you c
 
 ### Step 4: Load Config
 
-Load config from `{project-root}/_bmad/bmm/config.yaml` and resolve:
+Load config by running `python3 {project-root}/_bmad/scripts/resolve_config.py --project-root {project-root}` (requires Python 3.11+). If the command fails, read the merge logic in `{project-root}/_bmad/scripts/resolve_config.py` and apply it yourself to resolve the config variables. Resolve:
 - Use `{user_name}` for greeting
 - Use `{communication_language}` for all communications
 - Use `{document_output_language}` for output documents

src/bmm-skills/3-solutioning/bmad-create-epics-and-stories/SKILL.md

@@ -71,7 +71,7 @@ Treat every entry in `{workflow.persistent_facts}` as foundational context you c
 
 ### Step 4: Load Config
 
-Load config from `{project-root}/_bmad/bmm/config.yaml` and resolve:
+Load config by running `python3 {project-root}/_bmad/scripts/resolve_config.py --project-root {project-root}` (requires Python 3.11+). If the command fails, read the merge logic in `{project-root}/_bmad/scripts/resolve_config.py` and apply it yourself to resolve the config variables. Resolve:
 - Use `{user_name}` for greeting
 - Use `{communication_language}` for all communications
 - Use `{document_output_language}` for output documents

src/bmm-skills/3-solutioning/bmad-generate-project-context/SKILL.md

@@ -50,7 +50,7 @@ Treat every entry in `{workflow.persistent_facts}` as foundational context you c
 
 ### Step 4: Load Config
 
-Load config from `{project-root}/_bmad/bmm/config.yaml` and resolve:
+Load config by running `python3 {project-root}/_bmad/scripts/resolve_config.py --project-root {project-root}` (requires Python 3.11+). If the command fails, read the merge logic in `{project-root}/_bmad/scripts/resolve_config.py` and apply it yourself to resolve the config variables. Resolve:
 - Use `{user_name}` for greeting
 - Use `{communication_language}` for all communications
 - Use `{document_output_language}` for output documents

src/bmm-skills/4-implementation/bmad-agent-dev/SKILL.md

@@ -46,7 +46,7 @@ Treat every entry in `{agent.persistent_facts}` as foundational context you carr
 
 ### Step 5: Load Config
 
-Load config from `{project-root}/_bmad/bmm/config.yaml` and resolve:
+Load config by running `python3 {project-root}/_bmad/scripts/resolve_config.py --project-root {project-root}` (requires Python 3.11+). If the command fails, read the merge logic in `{project-root}/_bmad/scripts/resolve_config.py` and apply it yourself to resolve the config variables. Resolve:
 - Use `{user_name}` for greeting
 - Use `{communication_language}` for all communications
 - Use `{document_output_language}` for output documents

src/bmm-skills/4-implementation/bmad-checkpoint-preview/SKILL.md

@@ -40,7 +40,7 @@ Treat every entry in `{workflow.persistent_facts}` as foundational context you c
 
 ### Step 4: Load Config
 
-Load config from `{project-root}/_bmad/bmm/config.yaml` and resolve:
+Load config by running `python3 {project-root}/_bmad/scripts/resolve_config.py --project-root {project-root}` (requires Python 3.11+). If the command fails, read the merge logic in `{project-root}/_bmad/scripts/resolve_config.py` and apply it yourself to resolve the config variables. Resolve:
 
 - `implementation_artifacts`
 - `planning_artifacts`
@@ -63,6 +63,18 @@ Activation is complete. Begin the workflow below.
 - **Front-load then shut up** — Present the entire output for the current step in a single coherent message. Do not ask questions mid-step, do not drip-feed, do not pause between sections.
 - **Language** — Speak in `{communication_language}`. Write any file output in `{document_output_language}`.
 
+<<<<<<< HEAD
+=======
+## INITIALIZATION
+
+Load config by running `python3 {project-root}/_bmad/scripts/resolve_config.py --project-root {project-root}` (requires Python 3.11+). If the command fails, read the merge logic in `{project-root}/_bmad/scripts/resolve_config.py` and apply it yourself to resolve the config variables. Resolve:
+
+- `implementation_artifacts`
+- `planning_artifacts`
+- `communication_language`
+- `document_output_language`
+
+>>>>>>> 3846e184 (fix(skills): use resolve_config.py instead of reading config.yaml directly)
 ## FIRST STEP
 
 Read fully and follow `./step-01-orientation.md` to begin.

src/bmm-skills/4-implementation/bmad-code-review/SKILL.md

@@ -40,7 +40,7 @@ Treat every entry in `{workflow.persistent_facts}` as foundational context you c
 
 ### Step 4: Load Config
 
-Load config from `{project-root}/_bmad/bmm/config.yaml` and resolve:
+Load config by running `python3 {project-root}/_bmad/scripts/resolve_config.py --project-root {project-root}` (requires Python 3.11+). If the command fails, read the merge logic in `{project-root}/_bmad/scripts/resolve_config.py` and apply it yourself to resolve the config variables. Resolve:
 
 - `project_name`, `planning_artifacts`, `implementation_artifacts`, `user_name`
 - `communication_language`, `document_output_language`, `user_skill_level`

src/bmm-skills/4-implementation/bmad-correct-course/SKILL.md

@@ -40,7 +40,7 @@ Treat every entry in `{workflow.persistent_facts}` as foundational context you c
 
 ### Step 4: Load Config
 
-Load config from `{project-root}/_bmad/bmm/config.yaml` and resolve:
+Load config by running `python3 {project-root}/_bmad/scripts/resolve_config.py --project-root {project-root}` (requires Python 3.11+). If the command fails, read the merge logic in `{project-root}/_bmad/scripts/resolve_config.py` and apply it yourself to resolve the config variables. Resolve:
 
 - `project_name`, `user_name`
 - `communication_language`, `document_output_language`

src/bmm-skills/4-implementation/bmad-create-story/SKILL.md

@@ -47,7 +47,7 @@ Treat every entry in `{workflow.persistent_facts}` as foundational context you c
 
 ### Step 4: Load Config
 
-Load config from `{project-root}/_bmad/bmm/config.yaml` and resolve:
+Load config by running `python3 {project-root}/_bmad/scripts/resolve_config.py --project-root {project-root}` (requires Python 3.11+). If the command fails, read the merge logic in `{project-root}/_bmad/scripts/resolve_config.py` and apply it yourself to resolve the config variables. Resolve:
 
 - `project_name`, `user_name`
 - `communication_language`, `document_output_language`

src/bmm-skills/4-implementation/bmad-dev-story/SKILL.md

@@ -47,7 +47,7 @@ Treat every entry in `{workflow.persistent_facts}` as foundational context you c
 
 ### Step 4: Load Config
 
-Load config from `{project-root}/_bmad/bmm/config.yaml` and resolve:
+Load config by running `python3 {project-root}/_bmad/scripts/resolve_config.py --project-root {project-root}` (requires Python 3.11+). If the command fails, read the merge logic in `{project-root}/_bmad/scripts/resolve_config.py` and apply it yourself to resolve the config variables. Resolve:
 
 - `project_name`, `user_name`
 - `communication_language`, `document_output_language`

src/bmm-skills/4-implementation/bmad-qa-generate-e2e-tests/SKILL.md

@@ -40,7 +40,7 @@ Treat every entry in `{workflow.persistent_facts}` as foundational context you c
 
 ### Step 4: Load Config
 
-Load config from `{project-root}/_bmad/bmm/config.yaml` and resolve:
+Load config by running `python3 {project-root}/_bmad/scripts/resolve_config.py --project-root {project-root}` (requires Python 3.11+). If the command fails, read the merge logic in `{project-root}/_bmad/scripts/resolve_config.py` and apply it yourself to resolve the config variables. Resolve:
 
 - `project_name`, `user_name`
 - `communication_language`, `document_output_language`

src/bmm-skills/4-implementation/bmad-quick-dev/SKILL.md

@@ -59,7 +59,7 @@ Treat every entry in `{workflow.persistent_facts}` as foundational context you c
 
 ### Step 4: Load Config
 
-Load config from `{project-root}/_bmad/bmm/config.yaml` and resolve:
+Load config by running `python3 {project-root}/_bmad/scripts/resolve_config.py --project-root {project-root}` (requires Python 3.11+). If the command fails, read the merge logic in `{project-root}/_bmad/scripts/resolve_config.py` and apply it yourself to resolve the config variables. Resolve:
 
 - `project_name`, `planning_artifacts`, `implementation_artifacts`, `user_name`
 - `communication_language`, `document_output_language`, `user_skill_level`

src/bmm-skills/4-implementation/bmad-retrospective/SKILL.md

@@ -56,7 +56,7 @@ Treat every entry in `{workflow.persistent_facts}` as foundational context you c
 
 ### Step 4: Load Config
 
-Load config from `{project-root}/_bmad/bmm/config.yaml` and resolve:
+Load config by running `python3 {project-root}/_bmad/scripts/resolve_config.py --project-root {project-root}` (requires Python 3.11+). If the command fails, read the merge logic in `{project-root}/_bmad/scripts/resolve_config.py` and apply it yourself to resolve the config variables. Resolve:
 
 - `project_name`, `user_name`
 - `communication_language`, `document_output_language`

src/bmm-skills/4-implementation/bmad-sprint-planning/SKILL.md

@@ -40,7 +40,7 @@ Treat every entry in `{workflow.persistent_facts}` as foundational context you c
 
 ### Step 4: Load Config
 
-Load config from `{project-root}/_bmad/bmm/config.yaml` and resolve:
+Load config by running `python3 {project-root}/_bmad/scripts/resolve_config.py --project-root {project-root}` (requires Python 3.11+). If the command fails, read the merge logic in `{project-root}/_bmad/scripts/resolve_config.py` and apply it yourself to resolve the config variables. Resolve:
 
 - `project_name`, `user_name`
 - `communication_language`, `document_output_language`

src/bmm-skills/4-implementation/bmad-sprint-status/SKILL.md

@@ -40,7 +40,7 @@ Treat every entry in `{workflow.persistent_facts}` as foundational context you c
 
 ### Step 4: Load Config
 
-Load config from `{project-root}/_bmad/bmm/config.yaml` and resolve:
+Load config by running `python3 {project-root}/_bmad/scripts/resolve_config.py --project-root {project-root}` (requires Python 3.11+). If the command fails, read the merge logic in `{project-root}/_bmad/scripts/resolve_config.py` and apply it yourself to resolve the config variables. Resolve:
 
 - `project_name`, `user_name`
 - `communication_language`, `document_output_language`

src/bmm-skills/module-help.csv

@@ -1,4 +1,4 @@
-module,skill,display-name,menu-code,description,action,args,phase,after,before,required,output-location,outputs
+module,skill,display-name,menu-code,description,action,args,phase,preceded-by,followed-by,required,output-location,outputs
 BMad Method,_meta,,,,,,,,,false,https://docs.bmad-method.org/llms.txt,
 BMad Method,bmad-document-project,Document Project,DP,Analyze an existing project to produce useful documentation.,,,anytime,,,false,project-knowledge,*
 BMad Method,bmad-generate-project-context,Generate Project Context,GPC,Scan existing codebase to generate a lean LLM-optimized project-context.md. Essential for brownfield projects.,,,anytime,,,false,output_folder,project context

src/core-skills/bmad-brainstorming/workflow.md

@@ -32,7 +32,7 @@ This uses **micro-file architecture** for disciplined execution:
 
 ### Configuration Loading
 
-Load config from `{project-root}/_bmad/core/config.yaml` and resolve:
+Load config by running `python3 {project-root}/_bmad/scripts/resolve_config.py --project-root {project-root}` (requires Python 3.11+). If the command fails, read the merge logic in `{project-root}/_bmad/scripts/resolve_config.py` and apply it yourself to resolve the config variables. Resolve:
 
 - `project_name`, `output_folder`, `user_name`
 - `communication_language`, `document_output_language`, `user_skill_level`

src/core-skills/bmad-distillator/resources/distillate-format-reference.md

@@ -139,7 +139,7 @@ parts: 1
 
 ## Solution Architecture
 - Plugins: skill bundles with Anthropic plugin standard as base format + bmad-manifest.json extending for BMAD-specific metadata (installer options, capabilities, help integration, phase ordering, dependencies)
-- Existing manifest example: `{"module-code":"bmm","replaces-skill":"bmad-create-product-brief","capabilities":[{"name":"create-brief","menu-code":"CB","supports-headless":true,"phase-name":"1-analysis","after":["brainstorming"],"before":["create-prd"],"is-required":true}]}`
+- Existing manifest example: `{"module-code":"bmm","replaces-skill":"bmad-create-product-brief","capabilities":[{"name":"create-brief","menu-code":"CB","supports-headless":true,"phase-name":"1-analysis","preceded-by":["brainstorming"],"followed-by":["create-prd"],"is-required":true}]}`
 - Vercel skills CLI handles platform translation; integration pattern (wrap/fork/call) is PRD decision
 - bmad-setup: global skill scanning installed bmad-manifest.json files, registering capabilities, configuring project settings; always included as base skill in every bundle (solves bootstrapping)
 - bmad-update: plugin update path without full reinstall; technical approach (diff/replace/preserve customizations) is PRD decision

src/core-skills/bmad-help/SKILL.md

@@ -23,7 +23,7 @@ When this skill completes, the user should:
 ## Data Sources
 
 - **Catalog**: `{project-root}/_bmad/_config/bmad-help.csv` — assembled manifest of all installed module skills
-- **Config**: `config.yaml` and `user-config.yaml` files in `{project-root}/_bmad/` and its subfolders — resolve `output-location` variables, provide `communication_language` and `project_knowledge`
+- **Config**: Run `python3 {project-root}/_bmad/scripts/resolve_config.py --project-root {project-root}` to get merged config. If that fails, read the merge logic in `{project-root}/_bmad/scripts/resolve_config.py` and apply it yourself — resolve `output-location` variables, provide `communication_language` and `project_knowledge`
 - **Artifacts**: Files matching `outputs` patterns at resolved `output-location` paths reveal which steps are possibly completed; their content may also provide grounding context for recommendations
 - **Project knowledge**: If `project_knowledge` resolves to an existing path, read it for grounding context. Never fabricate project-specific details.
 - **Module docs**: Rows with `_meta` in the `skill` column carry a URL or path in `output-location` pointing to the module's documentation (e.g., llms.txt). Fetch and use these to answer general questions about that module.
@@ -33,16 +33,16 @@ When this skill completes, the user should:
 The catalog uses this format:
 
 ```
-module,skill,display-name,menu-code,description,action,args,phase,after,before,required,output-location,outputs
+module,skill,display-name,menu-code,description,action,args,phase,preceded-by,followed-by,required,output-location,outputs
 ```
 
 **Phases** determine the high-level flow:
 - `anytime` — available regardless of workflow state
 - Numbered phases (`1-analysis`, `2-planning`, etc.) flow in order; naming varies by module
 
-**Dependencies** determine ordering within and across phases:
+**Sequencing** determines recommended ordering within and across phases (these are soft suggestions, not hard gates — see `required` for gating):
-- `after` — skills that should ideally complete before this one
+- `preceded-by` — skills that should ideally complete before this one
-- `before` — skills that should run after this one
+- `followed-by` — skills that should ideally run after this one
 - Format: `skill-name` for single-action skills, `skill-name:action` for multi-action skills
 
 **Required gates**:

src/core-skills/bmad-party-mode/SKILL.md

@@ -22,7 +22,7 @@ Party mode accepts optional arguments when invoked:
 
 1. **Parse arguments** — check for `--model` and `--solo` flags from the user's invocation.
 
-2. Load config from `{project-root}/_bmad/core/config.yaml` and resolve:
+2. Load config by running `python3 {project-root}/_bmad/scripts/resolve_config.py --project-root {project-root}` (requires Python 3.11+). If the command fails, read the merge logic in `{project-root}/_bmad/scripts/resolve_config.py` and apply it yourself to resolve the config variables. Resolve:
   - Use `{user_name}` for greeting
   - Use `{communication_language}` for all communications
 

src/core-skills/module-help.csv

@@ -1,4 +1,4 @@
-module,skill,display-name,menu-code,description,action,args,phase,after,before,required,output-location,outputs
+module,skill,display-name,menu-code,description,action,args,phase,preceded-by,followed-by,required,output-location,outputs
 Core,_meta,,,,,,,,,false,https://docs.bmad-method.org/llms.txt,
 Core,bmad-brainstorming,Brainstorming,BSP,Use early in ideation or when stuck generating ideas.,,,anytime,,,false,{output_folder}/brainstorming,brainstorming session
 Core,bmad-party-mode,Party Mode,PM,Orchestrate multi-agent discussions when you need multiple perspectives or want agents to collaborate.,,,anytime,,,false,,

src/scripts/resolve_config.py

@@ -1,12 +1,13 @@
 #!/usr/bin/env python3
 """
-Resolve BMad's central config using four-layer TOML merge.
+Resolve BMad's central config using five-layer TOML merge.
 
-Reads from four layers (highest priority last):
+Reads from five layers (highest priority last):
   1. {project-root}/_bmad/config.toml              (installer-owned team)
   2. {project-root}/_bmad/config.user.toml         (installer-owned user)
-  3. {project-root}/_bmad/custom/config.toml       (human-authored team, committed)
+  3. ~/.bmad/config/config.user.toml               (global user preferences)
-  4. {project-root}/_bmad/custom/config.user.toml  (human-authored user, gitignored)
+  4. {project-root}/_bmad/custom/config.toml       (human-authored team, committed)
+  5. {project-root}/_bmad/custom/config.user.toml  (human-authored user, gitignored)
 
 Outputs merged JSON to stdout. Errors go to stderr.
 
@@ -40,6 +41,7 @@ except ImportError:
 
 _MISSING = object()
 _KEYED_MERGE_FIELDS = ("code", "id")
+GLOBAL_DIR = Path.home() / ".bmad" / "config"
 
 
 def load_toml(file_path: Path, required: bool = False) -> dict:
@@ -136,7 +138,7 @@ def extract_key(data, dotted_key: str):
 
 def main():
     parser = argparse.ArgumentParser(
-        description="Resolve BMad central config using four-layer TOML merge.",
+        description="Resolve BMad central config using five-layer TOML merge.",
     )
     parser.add_argument(
         "--project-root", "-p", required=True,
@@ -153,10 +155,12 @@ def main():
 
     base_team = load_toml(bmad_dir / "config.toml", required=True)
     base_user = load_toml(bmad_dir / "config.user.toml")
+    global_user = load_toml(GLOBAL_DIR / "config.user.toml")
     custom_team = load_toml(bmad_dir / "custom" / "config.toml")
     custom_user = load_toml(bmad_dir / "custom" / "config.user.toml")
 
     merged = deep_merge(base_team, base_user)
+    merged = deep_merge(merged, global_user)
     merged = deep_merge(merged, custom_team)
     merged = deep_merge(merged, custom_user)
 

src/scripts/resolve_customization.py

@@ -1,11 +1,12 @@
 #!/usr/bin/env python3
 """
-Resolve customization for a BMad skill using three-layer TOML merge.
+Resolve customization for a BMad skill using four-layer TOML merge.
 
-Reads customization from three layers (highest priority first):
+Reads customization from four layers (highest priority first):
   1. {project-root}/_bmad/custom/{name}.user.toml  (personal, gitignored)
   2. {project-root}/_bmad/custom/{name}.toml        (team/org, committed)
-  3. {skill-root}/customize.toml                    (skill defaults)
+  3. ~/.bmad/config/{name}.user.toml                (global user preferences)
+  4. {skill-root}/customize.toml                    (skill defaults)
 
 Skill name is derived from the basename of the skill directory.
 
@@ -51,6 +52,7 @@ except ImportError:
 
 _MISSING = object()
 _KEYED_MERGE_FIELDS = ("code", "id")
+GLOBAL_DIR = Path.home() / ".bmad" / "config"
 
 
 def find_project_root(start: Path):
@@ -179,7 +181,7 @@ def extract_key(data, dotted_key: str):
 
 def main():
     parser = argparse.ArgumentParser(
-        description="Resolve customization for a BMad skill using three-layer TOML merge.",
+        description="Resolve customization for a BMad skill using four-layer TOML merge.",
         add_help=True,
     )
     parser.add_argument(
@@ -211,7 +213,10 @@ def main():
         team = load_toml(custom_dir / f"{skill_name}.toml")
         user = load_toml(custom_dir / f"{skill_name}.user.toml")
 
-    merged = deep_merge(defaults, team)
+    global_user = load_toml(GLOBAL_DIR / f"{skill_name}.user.toml")
+
+    merged = deep_merge(defaults, global_user)
+    merged = deep_merge(merged, team)
     merged = deep_merge(merged, user)
 
     if args.key:

test/test-config-resolution.js

@@ -0,0 +1,341 @@
+/**
+ * Config Resolution Tests
+ *
+ * Tests the Python config resolution scripts by invoking them as subprocesses
+ * with temporary TOML fixtures. Validates:
+ * - Global user layer is loaded and merged with correct priority
+ * - Project layers override global layers
+ * - Missing global dir doesn't break anything (backward compat)
+ * - resolve_customization.py global skill layer
+ *
+ * Usage: node test/test-config-resolution.js
+ */
+
+const path = require('node:path');
+const os = require('node:os');
+const fs = require('node:fs/promises');
+const { execSync } = require('node:child_process');
+
+const SCRIPTS_DIR = path.resolve(__dirname, '..', 'src', 'scripts');
+
+const colors = {
+  reset: '',
+  green: '',
+  red: '',
+  dim: '',
+};
+
+let passed = 0;
+let failed = 0;
+
+function assert(condition, testName, errorMessage = '') {
+  if (condition) {
+    console.log(`${colors.green}✓${colors.reset} ${testName}`);
+    passed++;
+  } else {
+    console.log(`${colors.red}✗${colors.reset} ${testName}`);
+    if (errorMessage) {
+      console.log(`  ${colors.dim}${errorMessage}${colors.reset}`);
+    }
+    failed++;
+  }
+}
+
+function writeToml(filePath, data) {
+  const lines = [];
+  for (const [key, val] of Object.entries(data)) {
+    if (typeof val === 'string') {
+      lines.push(`${key} = "${val}"`);
+    } else if (typeof val === 'number' || typeof val === 'boolean') {
+      lines.push(`${key} = ${val}`);
+    }
+  }
+  return fs.writeFile(filePath, lines.join('\n') + '\n');
+}
+
+async function withTempDir(fn) {
+  const dir = await fs.mkdtemp(path.join(os.tmpdir(), 'bmad-config-test-'));
+  try {
+    return await fn(dir);
+  } finally {
+    await fs.rm(dir, { recursive: true, force: true });
+  }
+}
+
+async function testResolveConfig() {
+  console.log('\n--- resolve_config.py ---\n');
+
+  // Test 1: global user overrides installer defaults
+  await withTempDir(async (tmpDir) => {
+    const globalDir = path.join(tmpDir, '.bmad', 'config');
+    await fs.mkdir(globalDir, { recursive: true });
+    await writeToml(path.join(globalDir, 'config.user.toml'), {
+      user_name: 'GlobalAlice',
+      communication_language: 'en',
+    });
+
+    const projectDir = path.join(tmpDir, 'project');
+    const bmadDir = path.join(projectDir, '_bmad');
+    await fs.mkdir(path.join(bmadDir, 'custom'), { recursive: true });
+    await writeToml(path.join(bmadDir, 'config.toml'), {
+      project_name: 'TestProject',
+      user_name: 'InstallerDefault',
+    });
+    await writeToml(path.join(bmadDir, 'config.user.toml'), {
+      user_name: 'InstallerUserDefault',
+    });
+
+    const origHome = process.env.HOME;
+    process.env.HOME = tmpDir;
+    try {
+      const result = JSON.parse(execSync(`python3 ${SCRIPTS_DIR}/resolve_config.py --project-root ${projectDir}`, { encoding: 'utf-8' }));
+
+      assert(
+        result.user_name === 'GlobalAlice',
+        'global user overrides installer defaults',
+        `Expected "GlobalAlice", got "${result.user_name}"`,
+      );
+      assert(
+        result.communication_language === 'en',
+        'global communication_language preserved when installer has no override',
+        `Expected "en", got "${result.communication_language}"`,
+      );
+      assert(
+        result.project_name === 'TestProject',
+        'installer team config values preserved',
+        `Expected "TestProject", got "${result.project_name}"`,
+      );
+    } finally {
+      process.env.HOME = origHome;
+    }
+  });
+
+  // Test 2: missing global dir — backward compat
+  await withTempDir(async (tmpDir) => {
+    const projectDir = path.join(tmpDir, 'project');
+    const bmadDir = path.join(projectDir, '_bmad');
+    await fs.mkdir(path.join(bmadDir, 'custom'), { recursive: true });
+    await writeToml(path.join(bmadDir, 'config.toml'), {
+      project_name: 'NoGlobalProject',
+    });
+
+    const origHome = process.env.HOME;
+    process.env.HOME = tmpDir;
+    try {
+      const result = JSON.parse(execSync(`python3 ${SCRIPTS_DIR}/resolve_config.py --project-root ${projectDir}`, { encoding: 'utf-8' }));
+
+      assert(
+        result.project_name === 'NoGlobalProject',
+        'works fine without global config dir',
+        `Expected "NoGlobalProject", got "${result.project_name}"`,
+      );
+    } finally {
+      process.env.HOME = origHome;
+    }
+  });
+
+  // Test 3: full priority chain — base_team < base_user < global < custom_team < custom_user
+  await withTempDir(async (tmpDir) => {
+    const globalDir = path.join(tmpDir, '.bmad', 'config');
+    await fs.mkdir(globalDir, { recursive: true });
+    await writeToml(path.join(globalDir, 'config.user.toml'), {
+      user_name: 'L2-Global',
+    });
+
+    const projectDir = path.join(tmpDir, 'project');
+    const bmadDir = path.join(projectDir, '_bmad');
+    await fs.mkdir(path.join(bmadDir, 'custom'), { recursive: true });
+    await writeToml(path.join(bmadDir, 'config.toml'), { user_name: 'L0-BaseTeam' });
+    await writeToml(path.join(bmadDir, 'config.user.toml'), { user_name: 'L1-BaseUser' });
+    await writeToml(path.join(bmadDir, 'custom', 'config.toml'), { user_name: 'L3-CustomTeam' });
+    await writeToml(path.join(bmadDir, 'custom', 'config.user.toml'), { user_name: 'L4-CustomUser' });
+
+    const origHome = process.env.HOME;
+    process.env.HOME = tmpDir;
+    try {
+      const result = JSON.parse(execSync(`python3 ${SCRIPTS_DIR}/resolve_config.py --project-root ${projectDir}`, { encoding: 'utf-8' }));
+
+      assert(
+        result.user_name === 'L4-CustomUser',
+        'highest priority layer (custom user) wins',
+        `Expected "L4-CustomUser", got "${result.user_name}"`,
+      );
+    } finally {
+      process.env.HOME = origHome;
+    }
+  });
+
+  // Test 4: --key flag works with global layer
+  await withTempDir(async (tmpDir) => {
+    const globalDir = path.join(tmpDir, '.bmad', 'config');
+    await fs.mkdir(globalDir, { recursive: true });
+    await writeToml(path.join(globalDir, 'config.user.toml'), {
+      user_name: 'KeyTestGlobal',
+      communication_language: 'fr',
+    });
+
+    const projectDir = path.join(tmpDir, 'project');
+    const bmadDir = path.join(projectDir, '_bmad');
+    await fs.mkdir(path.join(bmadDir, 'custom'), { recursive: true });
+    await writeToml(path.join(bmadDir, 'config.toml'), {
+      project_name: 'KeyTestProject',
+    });
+
+    const origHome = process.env.HOME;
+    process.env.HOME = tmpDir;
+    try {
+      const result = JSON.parse(
+        execSync(`python3 ${SCRIPTS_DIR}/resolve_config.py --project-root ${projectDir} --key user_name --key communication_language`, {
+          encoding: 'utf-8',
+        }),
+      );
+
+      assert(
+        Object.keys(result).length === 2,
+        '--key returns only requested keys',
+        `Expected 2 keys, got ${Object.keys(result).length}: ${JSON.stringify(Object.keys(result))}`,
+      );
+      assert(
+        result.user_name === 'KeyTestGlobal',
+        '--key user_name returns global value',
+        `Expected "KeyTestGlobal", got "${result.user_name}"`,
+      );
+      assert(
+        result.communication_language === 'fr',
+        '--key communication_language returns global value',
+        `Expected "fr", got "${result.communication_language}"`,
+      );
+    } finally {
+      process.env.HOME = origHome;
+    }
+  });
+}
+
+async function testResolveCustomization() {
+  console.log('\n--- resolve_customization.py ---\n');
+
+  // Test 1: global skill user overrides skill defaults
+  await withTempDir(async (tmpDir) => {
+    const globalDir = path.join(tmpDir, '.bmad', 'config');
+    await fs.mkdir(globalDir, { recursive: true });
+    await writeToml(path.join(globalDir, 'test-skill.user.toml'), {
+      agent: 'global-agent-prompt',
+    });
+
+    const skillDir = path.join(tmpDir, 'skill', 'test-skill');
+    await fs.mkdir(skillDir, { recursive: true });
+    await writeToml(path.join(skillDir, 'customize.toml'), {
+      agent: 'default-agent-prompt',
+      version: '1.0.0',
+    });
+
+    const origHome = process.env.HOME;
+    process.env.HOME = tmpDir;
+    try {
+      const result = JSON.parse(execSync(`python3 ${SCRIPTS_DIR}/resolve_customization.py --skill ${skillDir}`, { encoding: 'utf-8' }));
+
+      assert(
+        result.agent === 'global-agent-prompt',
+        'global user overrides skill defaults',
+        `Expected "global-agent-prompt", got "${result.agent}"`,
+      );
+      assert(result.version === '1.0.0', 'skill default values preserved', `Expected "1.0.0", got "${result.version}"`);
+    } finally {
+      process.env.HOME = origHome;
+    }
+  });
+
+  // Test 2: global skill layer provides value not in defaults
+  await withTempDir(async (tmpDir) => {
+    const globalDir = path.join(tmpDir, '.bmad', 'config');
+    await fs.mkdir(globalDir, { recursive: true });
+    await writeToml(path.join(globalDir, 'test-skill.user.toml'), {
+      extra_global_key: 'from-global',
+    });
+
+    const skillDir = path.join(tmpDir, 'skill', 'test-skill');
+    await fs.mkdir(skillDir, { recursive: true });
+    await writeToml(path.join(skillDir, 'customize.toml'), {
+      version: '2.0.0',
+    });
+
+    const origHome = process.env.HOME;
+    process.env.HOME = tmpDir;
+    try {
+      const result = JSON.parse(execSync(`python3 ${SCRIPTS_DIR}/resolve_customization.py --skill ${skillDir}`, { encoding: 'utf-8' }));
+
+      assert(
+        result.extra_global_key === 'from-global',
+        'global key not in defaults is preserved',
+        `Expected "from-global", got "${result.extra_global_key}"`,
+      );
+      assert(result.version === '2.0.0', 'skill defaults still present', `Expected "2.0.0", got "${result.version}"`);
+    } finally {
+      process.env.HOME = origHome;
+    }
+  });
+
+  // Test 3: missing global dir — backward compat
+  await withTempDir(async (tmpDir) => {
+    const skillDir = path.join(tmpDir, 'skill', 'test-skill');
+    await fs.mkdir(skillDir, { recursive: true });
+    await writeToml(path.join(skillDir, 'customize.toml'), {
+      version: '3.0.0',
+    });
+
+    const origHome = process.env.HOME;
+    process.env.HOME = tmpDir;
+    try {
+      const result = JSON.parse(execSync(`python3 ${SCRIPTS_DIR}/resolve_customization.py --skill ${skillDir}`, { encoding: 'utf-8' }));
+
+      assert(result.version === '3.0.0', 'works without global config dir', `Expected "3.0.0", got "${result.version}"`);
+    } finally {
+      process.env.HOME = origHome;
+    }
+  });
+
+  // Test 4: full priority chain — defaults < global < team < user
+  await withTempDir(async (tmpDir) => {
+    const globalDir = path.join(tmpDir, '.bmad', 'config');
+    await fs.mkdir(globalDir, { recursive: true });
+    await writeToml(path.join(globalDir, 'test-skill.user.toml'), {
+      agent: 'L1-Global',
+    });
+
+    const skillDir = path.join(tmpDir, 'project', '_bmad', 'skills', 'test-skill');
+    await fs.mkdir(skillDir, { recursive: true });
+    await writeToml(path.join(skillDir, 'customize.toml'), { agent: 'L0-Defaults' });
+
+    const customDir = path.join(tmpDir, 'project', '_bmad', 'custom');
+    await fs.mkdir(customDir, { recursive: true });
+    await writeToml(path.join(customDir, 'test-skill.toml'), { agent: 'L2-Team' });
+    await writeToml(path.join(customDir, 'test-skill.user.toml'), { agent: 'L3-User' });
+
+    const origHome = process.env.HOME;
+    process.env.HOME = tmpDir;
+    try {
+      const result = JSON.parse(execSync(`python3 ${SCRIPTS_DIR}/resolve_customization.py --skill ${skillDir}`, { encoding: 'utf-8' }));
+
+      assert(result.agent === 'L3-User', 'highest priority layer (project user) wins', `Expected "L3-User", got "${result.agent}"`);
+    } finally {
+      process.env.HOME = origHome;
+    }
+  });
+}
+
+async function main() {
+  console.log('Config Resolution Tests\n');
+
+  try {
+    await testResolveConfig();
+    await testResolveCustomization();
+  } catch (error) {
+    console.error(`${colors.red}Fatal error: ${error.message}${colors.reset}`);
+    process.exit(1);
+  }
+
+  console.log(`\n${colors.green}${passed} passed${colors.reset}, ${colors.red}${failed} failed${colors.reset}`);
+  process.exit(failed > 0 ? 1 : 0);
+}
+
+main();

tools/installer/core/installer.js

@@ -12,6 +12,7 @@ const { BMAD_FOLDER_NAME } = require('../ide/shared/path-utils');
 const { InstallPaths } = require('./install-paths');
 const { ExternalModuleManager } = require('../modules/external-manager');
 const { resolveModuleVersion } = require('../modules/version-resolver');
+const { MODULE_HELP_CSV_HEADER } = require('../modules/module-help-schema');
 
 const { ExistingInstall } = require('./existing-install');
 const { warnPreNativeSkillsLegacy } = require('./legacy-warnings');
@@ -942,7 +943,7 @@ class Installer {
    */
   async mergeModuleHelpCatalogs(bmadDir, _agentEntries = []) {
     const allRows = [];
-    const headerRow = 'module,skill,display-name,menu-code,description,action,args,phase,after,before,required,output-location,outputs';
+    const headerRow = MODULE_HELP_CSV_HEADER;
     const COLUMN_COUNT = 13;
     const PHASE_INDEX = 7;
 
@@ -975,9 +976,19 @@ class Installer {
           const content = await fs.readFile(helpFilePath, 'utf8');
           const lines = content.split('\n').filter((line) => line.trim() && !line.startsWith('#'));
 
+          let headerWarned = false;
           for (const line of lines) {
-            // Skip header row
+            // Header row: warn on drift from canonical schema, then skip.
+            // Data rows are loaded positionally regardless, so the warning
+            // is advisory — the maintainer should rename their columns.
             if (line.startsWith('module,')) {
+              if (!headerWarned && line.trim() !== headerRow) {
+                await prompts.log.warn(
+                  `  ${moduleName}/module-help.csv header does not match canonical schema. ` +
+                    `Expected: ${headerRow} | Found: ${line.trim()} | Data loaded positionally.`,
+                );
+                headerWarned = true;
+              }
               continue;
             }
 

tools/installer/modules/module-help-schema.js

@@ -0,0 +1,13 @@
+/**
+ * Canonical schema for per-module `module-help.csv` files.
+ *
+ * Both the merger (`Installer.mergeModuleHelpCatalogs`) and the synthesizer
+ * (`PluginResolver._buildSynthesizedHelpCsv`) emit this exact header. The
+ * merger compares each per-module file's header against this string and
+ * warns on drift, so any rename here must be matched in external module
+ * authors' CSVs (or accepted as a positional fall-through with a warning).
+ */
+const MODULE_HELP_CSV_HEADER =
+  'module,skill,display-name,menu-code,description,action,args,phase,preceded-by,followed-by,required,output-location,outputs';
+
+module.exports = { MODULE_HELP_CSV_HEADER };

tools/installer/modules/plugin-resolver.js

@@ -1,6 +1,7 @@
 const fs = require('../fs-native');
 const path = require('node:path');
 const yaml = require('yaml');
+const { MODULE_HELP_CSV_HEADER } = require('./module-help-schema');
 
 /**
  * Resolves how to install a plugin from marketplace.json by analyzing
@@ -338,8 +339,7 @@ class PluginResolver {
    * @returns {string} CSV content
    */
   _buildSynthesizedHelpCsv(moduleName, skillInfos) {
-    const header = 'module,skill,display-name,menu-code,description,action,args,phase,after,before,required,output-location,outputs';
+    const rows = [MODULE_HELP_CSV_HEADER];
-    const rows = [header];
 
     for (const info of skillInfos) {
       const displayName = this._formatDisplayName(info.name || info.dirName);