refactor: move builder output config from install prompts to per-skill customize.toml

AGENTS.md

@@ -102,7 +102,7 @@ your-module/
 ### Path Variables
 
 - `{project-root}/_bmad/bmb/` — Installation path (in repo, maps to `src/`)
-- `{bmad_builder_output_folder}` — User's custom content output
+- `{builder_output_folder}` — User's custom content output (per-skill, resolved from each builder skill's `customize.toml`)
 - Runtime variables: `{output_folder}`, `{project-root}` from Core config
 
 ## Development Notes

docs/explanation/module-configuration.md

@@ -127,7 +127,7 @@ module,skill,display-name,menu-code,description,action,args,phase,preceded-by,fo
 | **preceded-by**     | Capabilities that should complete before this one (this capability is preceded by them): format `skill-name:action`, comma-separated for multiple |
 | **followed-by**     | Capabilities that should run after this one (this capability is followed by them), same format as `preceded-by`                              |
 | **required**        | `true` if this is a blocking gate for phase progression, `false` otherwise                                                                   |
-| **output-location** | Config variable name (e.g., `output_folder`, `bmad_builder_reports`); `bmad-help` resolves from config to scan for completion artifacts     |
+| **output-location** | Config variable name (e.g., `output_folder`, `builder_output_folder`); `bmad-help` resolves from config to scan for completion artifacts. Leave blank when output is per-invocation (e.g., reports that land next to whatever's being analyzed) — completion detection is skipped for those rows. |
 | **outputs**         | File patterns `bmad-help` looks for in the output location to detect completion (e.g., "quality report", "agent skill")                      |
 
 ### How bmad-help Uses These Entries

docs/how-to/run-evals-against-a-skill.md

@@ -76,7 +76,7 @@ The runner stages each eval's workspace, executes `claude -p` against the prompt
 
 When the run finishes, the runner emits two paths:
 
-- The run folder, at `~/bmad-evals/<run-id>/` (or your configured `bmad_builder_reports` location)
+- The run folder, at `~/bmad-evals/<run-id>/` (or `{builder_output_folder}/eval-runs/<run-id>/` if `bmad-eval-runner`'s `customize.toml` is resolvable)
 - An HTML report at `<run-folder>/report.html`
 
 Open the report for the summary view. Drop into the run folder for full transcripts, artifacts, and grading details for any eval you want to examine.

docs/reference/builder-commands.md

@@ -248,7 +248,7 @@ The optimizer runs three tiers of analysis.
 
 ### Report Synthesis
 
-After all scanners complete, the optimizer synthesizes results into a unified report saved to `{bmad_builder_reports}/{skill-name}/quality-scan/{timestamp}/`.
+After all scanners complete, the optimizer synthesizes results into a unified report saved to `{target-skill-path}/reports/quality-scan/{timestamp}/` — reports always land next to the skill being analyzed.
 
 In interactive mode, it presents a summary with severity counts and offers next steps:
 
@@ -299,7 +299,7 @@ The HTML report includes:
 | **What survived** | Content that earns its place: instructions the LLM wouldn't follow correctly without being told  |
 | **Verdict** | One-sentence summary of the conversion |
 
-Reports are saved to `{bmad_builder_reports}/convert-{skill-name}/`.
+Reports are saved to `{target-skill-path}/reports/convert/` — next to the skill being converted.
 
 ### When to Use Convert vs Build Process
 
@@ -331,7 +331,7 @@ A brainstorming session that helps you plan your module from scratch. The builde
 | --------------- | ----------------------------------------------- |
 | **Interaction** | Interactive only; no headless mode              |
 | **Input**       | An idea or rough description                    |
-| **Output**      | Plan document saved to `{bmad_builder_reports}` |
+| **Output**      | Plan document saved to `{output_folder}/module-plans/` |
 
 **What it covers:**
 

skills/bmad-agent-builder/SKILL.md

@@ -19,12 +19,12 @@ Act as an architect guide — walk users through conversational discovery to und
 
 1. Detect user's intent. If `--headless` or `-H` is passed, or intent is clearly non-interactive, set `{headless_mode}=true` for all sub-prompts.
 
-2. Load available config from `{project-root}/_bmad/config.yaml` and `{project-root}/_bmad/config.user.yaml` (root and bmb section). If neither exists, fall back to `{project-root}/_bmad/bmb/config.yaml` (legacy per-module format). If still missing, and the `bmad-builder-setup` skill is available, let the user know they can run it at any time to configure. Resolve and apply throughout the session (defaults in parens):
+2. Load core config from `{project-root}/_bmad/config.toml` (and `config.user.toml`) for shared identity values. Resolve this skill's `customize.toml` (merged with any `{project-root}/_bmad/custom/bmad-agent-builder.toml` and `.user.toml` overrides) for skill-local knobs. Apply throughout the session (defaults in parens):
    - `{user_name}` (default: null) — address the user by name
    - `{communication_language}` (default: user or system intent) — use for all communications
    - `{document_output_language}` (default: user or system intent) — use for generated document content
-   - `{bmad_builder_output_folder}` (default: `{project-root}/skills`) — save built agents here
-   - `{bmad_builder_reports}` (default: `{project-root}/skills/reports`) — save reports (quality, eval, planning) here
+   - `{builder_output_folder}` (default: `{project-root}/skills`) — save built agents here
+   - Quality / analysis reports always land next to the skill being analyzed: `<target-skill-path>/reports/<analysis-type>/<date>/`.
 
 3. Route by intent — see Quick Reference below.
 

skills/bmad-agent-builder/customize.toml

@@ -0,0 +1,12 @@
+# DO NOT EDIT -- overwritten on every update.
+#
+# Workflow customization surface for bmad-agent-builder.
+#
+# Override files (not edited here):
+#   {project-root}/_bmad/custom/bmad-agent-builder.toml         (team)
+#   {project-root}/_bmad/custom/bmad-agent-builder.user.toml    (personal)
+
+[workflow]
+
+# Where built agent skills land. Override in team/user TOML to redirect.
+builder_output_folder = "{project-root}/skills"

skills/bmad-agent-builder/references/build-process.md

@@ -208,7 +208,7 @@ Load `./references/sample-capability-prompt.md` as a quality reference for capab
 - `./references/skill-best-practices.md` — outcome-driven authoring, patterns, anti-patterns
 - `./references/quality-dimensions.md` — build quality checklist
 
-Build the agent using templates from `./assets/` and rules from `./references/template-substitution-rules.md`. Output to `{bmad_builder_output_folder}`.
+Build the agent using templates from `./assets/` and rules from `./references/template-substitution-rules.md`. Output to `{builder_output_folder}`.
 
 ### Emit `customize.toml` (always, every archetype)
 

skills/bmad-agent-builder/references/quality-analysis.md

@@ -64,7 +64,7 @@ Each scanner writes a free-form analysis document:
 
 ## Execution
 
-First create output directory: `{bmad_builder_reports}/{skill-name}/quality-analysis/{date-time-stamp}/`
+First create output directory: `{target-skill-path}/reports/quality-analysis/{date-time-stamp}/` — reports always land next to the skill being analyzed, never in a central bucket.
 
 ### Step 1: Run All Scripts (Parallel)
 

skills/bmad-agent-builder/references/standard-fields.md

@@ -194,5 +194,5 @@ Use `{project-root}/...` for any path relative to the project root:
 Use directly — they already contain `{project-root}` in their resolved values:
 
 - `{output_folder}/file.md`
-- Correct: `{bmad_builder_output_folder}/agent.md`
-- Wrong: `{project-root}/{bmad_builder_output_folder}/agent.md` (double-prefix)
+- Correct: `{builder_output_folder}/agent.md`
+- Wrong: `{project-root}/{builder_output_folder}/agent.md` (double-prefix)

skills/bmad-bmb-setup/assets/module-help.csv

@@ -1,10 +1,10 @@
 module,skill,display-name,menu-code,description,action,args,phase,preceded-by,followed-by,required,output-location,outputs
 BMad Builder,bmad-bmb-setup,Setup Builder Module,SB,"Install or update BMad Builder module config and help entries.",configure,"{-H: headless mode}|{inline values: skip prompts with provided values}",anytime,,,false,{project-root}/_bmad,config.yaml and config.user.yaml
-BMad Builder,bmad-agent-builder,Build an Agent,BA,"Create, edit, or rebuild an agent skill through conversational discovery.",build-process,"{-H: headless mode}|{description: initial agent concept}|{path: existing agent to edit or rebuild}",anytime,,bmad-agent-builder:quality-analysis,false,bmad_builder_output_folder,agent skill
-BMad Builder,bmad-agent-builder,Analyze an Agent,AA,"Run quality analysis on an existing agent — structure, cohesion, prompt craft, and enhancement opportunities.",quality-analysis,"{-H: headless mode}|{path: agent to analyze}",anytime,bmad-agent-builder:build-process,,false,bmad_builder_reports,quality report
-BMad Builder,bmad-workflow-builder,Build a Workflow,BW,"Create, edit, or rebuild a workflow or utility skill.",build-process,"{-H: headless mode}|{description: initial skill concept}|{path: existing skill to edit or rebuild}",anytime,,bmad-workflow-builder:quality-analysis,false,bmad_builder_output_folder,workflow skill
-BMad Builder,bmad-workflow-builder,Analyze a Workflow,AW,"Run quality analysis on an existing workflow/skill — structure, efficiency, and enhancement opportunities.",quality-analysis,"{-H: headless mode}|{path: skill to analyze}",anytime,bmad-workflow-builder:build-process,,false,bmad_builder_reports,quality report
-BMad Builder,bmad-workflow-builder,Convert a Skill,CW,"Convert any skill to BMad-compliant, outcome-driven equivalent with before/after HTML comparison report.",convert-process,"{--convert: path or URL to source skill}|{-H: headless mode}",anytime,,,false,bmad_builder_reports,converted skill + comparison report
-BMad Builder,bmad-module-builder,Ideate Module,IM,"Brainstorm and plan a BMad module — explore ideas, decide architecture, and produce a build plan.",ideate-module,"{description: initial module idea}",anytime,,bmad-module-builder:create-module,false,bmad_builder_reports,module plan
-BMad Builder,bmad-module-builder,Create Module,CM,"Scaffold module infrastructure into built skills, making them an installable BMad module.",create-module,"{-H: headless mode}|{path: skills folder or single SKILL.md}",anytime,bmad-module-builder:ideate-module,,false,bmad_builder_output_folder,setup skill
-BMad Builder,bmad-module-builder,Validate Module,VM,"Check that a module's structure is complete, accurate, and all capabilities are properly registered.",validate-module,"{-H: headless mode}|{path: module or skill to validate}",anytime,bmad-module-builder:create-module,,false,bmad_builder_reports,validation report
+BMad Builder,bmad-agent-builder,Build an Agent,BA,"Create, edit, or rebuild an agent skill through conversational discovery.",build-process,"{-H: headless mode}|{description: initial agent concept}|{path: existing agent to edit or rebuild}",anytime,,bmad-agent-builder:quality-analysis,false,builder_output_folder,agent skill
+BMad Builder,bmad-agent-builder,Analyze an Agent,AA,"Run quality analysis on an existing agent — structure, cohesion, prompt craft, and enhancement opportunities.",quality-analysis,"{-H: headless mode}|{path: agent to analyze}",anytime,bmad-agent-builder:build-process,,false,,quality report (lands next to analyzed skill)
+BMad Builder,bmad-workflow-builder,Build a Workflow,BW,"Create, edit, or rebuild a workflow or utility skill.",build-process,"{-H: headless mode}|{description: initial skill concept}|{path: existing skill to edit or rebuild}",anytime,,bmad-workflow-builder:quality-analysis,false,builder_output_folder,workflow skill
+BMad Builder,bmad-workflow-builder,Analyze a Workflow,AW,"Run quality analysis on an existing workflow/skill — structure, efficiency, and enhancement opportunities.",quality-analysis,"{-H: headless mode}|{path: skill to analyze}",anytime,bmad-workflow-builder:build-process,,false,,quality report (lands next to analyzed skill)
+BMad Builder,bmad-workflow-builder,Convert a Skill,CW,"Convert any skill to BMad-compliant, outcome-driven equivalent with before/after HTML comparison report.",convert-process,"{--convert: path or URL to source skill}|{-H: headless mode}",anytime,,,false,,converted skill + comparison report (next to source)
+BMad Builder,bmad-module-builder,Ideate Module,IM,"Brainstorm and plan a BMad module — explore ideas, decide architecture, and produce a build plan.",ideate-module,"{description: initial module idea}",anytime,,bmad-module-builder:create-module,false,output_folder,module plan
+BMad Builder,bmad-module-builder,Create Module,CM,"Scaffold module infrastructure into built skills, making them an installable BMad module.",create-module,"{-H: headless mode}|{path: skills folder or single SKILL.md}",anytime,bmad-module-builder:ideate-module,,false,builder_output_folder,setup skill
+BMad Builder,bmad-module-builder,Validate Module,VM,"Check that a module's structure is complete, accurate, and all capabilities are properly registered.",validate-module,"{-H: headless mode}|{path: module or skill to validate}",anytime,bmad-module-builder:create-module,,false,,validation report (lands next to analyzed module)

skills/bmad-bmb-setup/assets/module.yaml

@@ -5,16 +5,9 @@ module_version: 1.0.0
 default_selected: false
 module_greeting: >
   Enjoy making your dream creations with the BMad Builder Module!
-  Run this again at any time if you want to reconfigure a setting or have updated the module, (or optionally just update _bmad/config.yaml and config.user.yaml to change existing values)
 
-  For questions, suggestions and support - check us on Discord at https://discord.gg/gk8jAdXWmj
 
-bmad_builder_output_folder:
-  prompt: "Where should your custom output (agent, workflow, module config) be saved?"
-  default: "{project-root}/skills"
-  result: "{project-root}/{value}"
+  Each builder skill carries its own `customize.toml` with sane defaults (built artifacts land in `{project-root}/skills`). Override per-skill in `_bmad/custom/{skill-name}.toml` if you want a different home; reports and analyses always land next to whatever's being analyzed.
+
 
-bmad_builder_reports:
-  prompt: "Output for Evals, Test, Quality and Planning Reports?"
-  default: "{project-root}/skills/reports"
-  result: "{project-root}/{value}"
+  For questions, suggestions and support - check us on Discord at https://discord.gg/gk8jAdXWmj

skills/bmad-eval-runner/SKILL.md

@@ -23,13 +23,13 @@ You are an experienced eval engineer. The user wants signal, not theatre. Cite s
 - `--mode artifact|trigger|both` — which eval kind to run. Default: `both` if both files are found, else whichever exists.
 - `--isolation docker|local|auto` — sandbox strategy. Default: `auto` (Docker when available, otherwise local).
 - `--project-root <path>` — root of the project the skill belongs to. Default: walk up from skill path looking for `_bmad/` or `.git/`.
-- `--output-dir <path>` — where run folders are written. Default: `{bmad_builder_reports}/eval-runs/` if configured, else `~/bmad-evals/`.
+- `--output-dir <path>` — where run folders are written. Default: `{builder_output_folder}/eval-runs/` if `customize.toml` is resolvable, else `~/bmad-evals/`.
 - `--workers <n>` — parallel evals. Default: 4.
 - `--headless` / `-H` — non-interactive; emit final JSON only.
 
 ## On Activation
 
-1. Resolve config the same way `bmad-workflow-builder` does (`{project-root}/_bmad/config.yaml` then `config.user.yaml`, falling back to `bmb/config.yaml`). Resolve `{user_name}`, `{communication_language}`, `{bmad_builder_reports}`. Apply throughout the session.
+1. Resolve core config from `{project-root}/_bmad/config.toml` (and `config.user.toml`) for `{user_name}` and `{communication_language}`. Resolve this skill's `customize.toml` (merged with any `{project-root}/_bmad/custom/bmad-eval-runner.toml` and `.user.toml` overrides) for `{builder_output_folder}`. Apply throughout the session.
 
 2. If `--headless` was passed, set `{headless_mode}=true` and skip every confirmation below; pick the safest defaults and proceed.
 

skills/bmad-eval-runner/customize.toml

@@ -0,0 +1,14 @@
+# DO NOT EDIT -- overwritten on every update.
+#
+# Workflow customization surface for bmad-eval-runner.
+#
+# Override files (not edited here):
+#   {project-root}/_bmad/custom/bmad-eval-runner.toml         (team)
+#   {project-root}/_bmad/custom/bmad-eval-runner.user.toml    (personal)
+
+[workflow]
+
+# Fallback for --output-dir when no flag is passed and ~/bmad-evals/ is not
+# desired. Eval runs land under {builder_output_folder}/eval-runs/<run-id>/.
+# Override in team/user TOML to redirect, or pass --output-dir per invocation.
+builder_output_folder = "{project-root}/skills"

skills/bmad-module-builder/SKILL.md

@@ -17,7 +17,7 @@ This skill helps you bring BMad modules to life — from the first spark of an i
 
 ## On Activation
 
-Load available config from `{project-root}/_bmad/config.yaml` and `{project-root}/_bmad/config.user.yaml` (root level and `bmb` section). If neither exists, fall back to `{project-root}/_bmad/bmb/config.yaml` (legacy per-module format). If still missing, let the user know `bmad-builder-setup` can configure the module at any time. Use sensible defaults for anything not configured.
+Load core config from `{project-root}/_bmad/config.toml` (and `config.user.toml`) for shared identity values. Resolve this skill's `customize.toml` (merged with any `{project-root}/_bmad/custom/bmad-module-builder.toml` and `.user.toml` overrides) for skill-local knobs — most importantly `{builder_output_folder}` (default `{project-root}/skills`), where created modules land. Ideate plan documents land under `{output_folder}/module-plans/`. Validation reports land next to the module being validated. Use sensible defaults for anything not configured.
 
 Detect user's intent:
 

skills/bmad-module-builder/customize.toml

@@ -0,0 +1,14 @@
+# DO NOT EDIT -- overwritten on every update.
+#
+# Workflow customization surface for bmad-module-builder.
+#
+# Override files (not edited here):
+#   {project-root}/_bmad/custom/bmad-module-builder.toml         (team)
+#   {project-root}/_bmad/custom/bmad-module-builder.user.toml    (personal)
+
+[workflow]
+
+# Where created modules and their scaffolded skills land. Override in
+# team/user TOML to redirect. Ideate plan documents land under
+# {output_folder}/module-plans/ (the core BMad planning area), not here.
+builder_output_folder = "{project-root}/skills"

skills/bmad-module-builder/references/create-module.md

@@ -167,15 +167,18 @@ Iterate until the user confirms everything is correct.
 
 #### Multi-skill modules (setup skill approach)
 
-Write the confirmed module.yaml and module-help.csv content to temporary files at `{bmad_builder_reports}/{module-code}-temp-module.yaml` and `{bmad_builder_reports}/{module-code}-temp-help.csv`. Run the scaffold script:
+Write the confirmed module.yaml and module-help.csv content to a freshly-created temp directory (e.g. via `mktemp -d`) — these are ephemeral scaffolding inputs, not user-visible artifacts. Bind the path to `{tmp-dir}` and run the scaffold script:
 
 ```bash
+TMP_DIR=$(mktemp -d)
+# Write {tmp-dir}/{module-code}-temp-module.yaml and {tmp-dir}/{module-code}-temp-help.csv ...
 python3 ./scripts/scaffold-setup-skill.py \
   --target-dir "{skills-folder}" \
   --module-code "{code}" \
   --module-name "{name}" \
-  --module-yaml "{bmad_builder_reports}/{module-code}-temp-module.yaml" \
-  --module-csv "{bmad_builder_reports}/{module-code}-temp-help.csv"
+  --module-yaml "$TMP_DIR/{module-code}-temp-module.yaml" \
+  --module-csv "$TMP_DIR/{module-code}-temp-help.csv"
+rm -rf "$TMP_DIR"
 ```
 
 This creates `{code}-setup/` in the user's skills folder containing: