wizz-method 1.19.0 → 2.1.0

package/src/bmm-skills/4-implementation/wizz-code-review/customize.toml

@@ -51,18 +51,13 @@ on_complete = ""
 id = "blind-hunter"
 name = "Blind Hunter"
 instruction = """
-Launch a context-free subagent with this prompt:
+Launch a context-free `wizz-exec-review` subagent with this prompt — pinned to the platform's Forte tier (`opus` in Claude Code), never inheriting the session model. Tell the user the tier and count of this dispatch.
 
-Conduct a review of CONTENT.
-Look for what's missing, not only what's wrong.
-Find at least ten issues to fix or improve.
-Output a Markdown list of findings only — no severity, priority, or ranking.
-If the content is empty, stop and say so.
-If you have zero findings, re-check and keep thinking; do not stop with an empty list.
+Read `{skill-root}/review-prompts/blind-hunter.md` completely and follow it as your review instructions.
 
-CONTENT: the unified diff at `{diff_file}`. Read that file — it is the content under review.
+Review content: the unified diff at `{diff_file}`. Read that file — it is the content under review.
 
-Do not invoke any skill, and do not spawn subagents of your own — you are the reviewer. Return your findings as text in your final message; do not route them through any findings-reporting tool the host may offer.
+Do not invoke any skill, and do not spawn subagents of your own — you are the reviewer. If the instruction file is unreadable, report that exact failure and stop. Return your findings as text in your final message; do not route them through any findings-reporting tool the host may offer.
 
 """
 
@@ -70,7 +65,7 @@ Do not invoke any skill, and do not spawn subagents of your own — you are the
 id = "edge-case-hunter"
 name = "Edge Case Hunter"
 instruction = """
-Launch a context-free subagent with this prompt:
+Launch a context-free `wizz-exec-review` subagent with this prompt — pinned to the platform's Forte tier (`opus` in Claude Code), never inheriting the session model. Tell the user the tier and count of this dispatch.
 
 Read `{skill-root}/review-prompts/edge-case-hunter.md` completely and follow it as your review instructions.
 
@@ -86,7 +81,7 @@ Do not invoke any skill, and do not spawn subagents of your own — you are the
 id = "verification-gap"
 name = "Verification Gap Reviewer"
 instruction = """
-Launch a context-free subagent with this prompt:
+Launch a context-free `wizz-exec-review` subagent with this prompt — pinned to the platform's Forte tier (`opus` in Claude Code), never inheriting the session model. Tell the user the tier and count of this dispatch.
 
 Read `{skill-root}/review-prompts/verification-gap.md` completely and follow it as your review instructions.
 
@@ -101,7 +96,7 @@ id = "acceptance-auditor"
 name = "Acceptance Auditor"
 when = 'Only when {review_mode} = "full".'
 instruction = """
-Launch a subagent with this prompt:
+Launch a `wizz-exec-review` subagent with this prompt — pinned to the platform's Forte tier (`opus` in Claude Code), never inheriting the session model. Tell the user the tier and count of this dispatch.
 
 You are an Acceptance Auditor. Review the provided diff against `{spec_file}` and any loaded context docs. Check for: violations of acceptance criteria, deviations from spec intent, missing implementation of specified behavior, contradictions between spec constraints and actual code. Output findings as a Markdown list. Each finding: one-line title, which AC/constraint it violates, and evidence from the diff.
 

package/src/bmm-skills/4-implementation/wizz-code-review/review-prompts/blind-hunter.md

@@ -0,0 +1,20 @@
+# Blind Hunter Review
+
+**Goal:** Conduct a blind review of CONTENT — no project context, no spec, no triage. Hunt for what's missing, not only what's wrong.
+
+**Your method:**
+
+- Conduct a review of CONTENT.
+- Look for what's missing, not only what's wrong.
+- Find at least ten issues to fix or improve.
+- Output a Markdown list of findings only — no severity, priority, or ranking.
+- If the content is empty, stop and say so.
+- If you have zero findings, re-check and keep thinking; do not stop with an empty list.
+
+## OUTPUT FORMAT
+
+A Markdown list of findings only. One bullet per issue, description only — no severity, priority, or ranking.
+
+## CONTENT SOURCE
+
+"Review content:" in the message that launched you gives the content itself or a path to read it from. Read the file when it is a path; either way that is the content under review, and this instruction file never is. If no content is supplied, or it is empty or unreadable, stop and say so — never report a clean review for content you could not read.

package/src/bmm-skills/4-implementation/wizz-code-review/steps/step-02-review.md

@@ -7,7 +7,7 @@ failed_layers: '' # set at runtime: comma-separated list of layers that failed o
 ## RULES
 
 - YOU MUST ALWAYS SPEAK OUTPUT in your Agent communication style with the config `{communication_language}`
-- All review subagents must run at the same model capability as the current session.
+- Review subagents run pinned to the platform's Forte tier via `wizz-exec-review` (`opus` in Claude Code) — never at the same model capability as the current session. See `_shared/model-ladder.md`.
 - Run subagents synchronously: launch them together as blocking calls awaited in this turn — never backgrounded or detached, never ending the turn to await results.
 
 ## INSTRUCTIONS

package/src/bmm-skills/4-implementation/wizz-code-review/steps/step-04-present.md

@@ -129,6 +129,6 @@ Present the user with follow-up options:
 
 ## On Complete
 
-Run: `python3 {project-root}/_wizz/scripts/resolve_customization.py --skill {skill-root} --key workflow.on_complete`
+Run: read `workflow.on_complete` from the `{project-root}/_wizz/_resolved/wizz-code-review.json` snapshot loaded in step 1
 
 If the resolved `workflow.on_complete` is non-empty, follow it as the final terminal instruction before exiting.

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

@@ -14,19 +14,18 @@ description: 'Manage significant changes during sprint execution. Use when the u
 - Bare paths (e.g. `checklist.md`) resolve from the skill root.
 - `{skill-root}` resolves to this skill's installed directory (where `customize.toml` lives).
 - `{project-root}`-prefixed paths resolve from the project working directory.
-- `{skill-name}` resolves to the skill directory's basename.
 
 ## On Activation
 
 ### Step 1: Resolve the Workflow Block
 
-Run: `python3 {project-root}/_wizz/scripts/resolve_customization.py --skill {skill-root} --key workflow`
+Run: read `{project-root}/_wizz/_resolved/wizz-correct-course.json` (subtree `workflow`). If the file is missing, empty or not valid JSON, run `npx wizz-method resolve --skill wizz-correct-course` from the project root and read the snapshot again
 
 **If the script fails**, resolve the `workflow` block yourself by reading these three files in base → team → user order and applying the same structural merge rules as the resolver:
 
 1. `{skill-root}/customize.toml` — defaults
-2. `{project-root}/_wizz/custom/{skill-name}.toml` — team overrides
-3. `{project-root}/_wizz/custom/{skill-name}.user.toml` — personal overrides
+2. `{project-root}/_wizz/custom/wizz-correct-course.toml` — team overrides
+3. `{project-root}/_wizz/custom/wizz-correct-course.user.toml` — personal overrides
 
 Any missing file is skipped. Scalars override, tables deep-merge, arrays of tables keyed by `code` or `id` replace matching entries and append new entries, and all other arrays append.
 
@@ -295,7 +294,7 @@ Activation is complete. If `activation_steps_prepend` or `activation_steps_appen
 
 <action>Report workflow completion to user with personalized message: "Correct Course workflow complete, {user_name}!"</action>
 <action>Remind user of success criteria and next steps for Developer agent</action>
-<action>Run: `python3 {project-root}/_wizz/scripts/resolve_customization.py --skill {skill-root} --key workflow.on_complete` — if the resolved value is non-empty, follow it as the final terminal instruction before exiting.</action>
+<action>Run: read `{project-root}/_wizz/_resolved/wizz-correct-course.json` (subtree `workflow.on_complete`). If the file is missing, empty or not valid JSON, run `npx wizz-method resolve --skill wizz-correct-course` from the project root and read it again — if the resolved value is non-empty, follow it as the final terminal instruction before exiting.</action>
 </step>
 
 </workflow>

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

@@ -24,19 +24,18 @@ If you need an explicit user instruction to run them, ask once now for the whole
 - Bare paths (e.g. `discover-inputs.md`) resolve from the skill root.
 - `{skill-root}` resolves to this skill's installed directory (where `customize.toml` lives).
 - `{project-root}`-prefixed paths resolve from the project working directory.
-- `{skill-name}` resolves to the skill directory's basename.
 
 ## On Activation
 
 ### Step 1: Resolve the Workflow Block
 
-Run: `python3 {project-root}/_wizz/scripts/resolve_customization.py --skill {skill-root} --key workflow`
+Run: read `{project-root}/_wizz/_resolved/wizz-create-story.json` (subtree `workflow`). If the file is missing, empty or not valid JSON, run `npx wizz-method resolve --skill wizz-create-story` from the project root and read the snapshot again
 
 **If the script fails**, resolve the `workflow` block yourself by reading these three files in base → team → user order and applying the same structural merge rules as the resolver:
 
 1. `{skill-root}/customize.toml` — defaults
-2. `{project-root}/_wizz/custom/{skill-name}.toml` — team overrides
-3. `{project-root}/_wizz/custom/{skill-name}.user.toml` — personal overrides
+2. `{project-root}/_wizz/custom/wizz-create-story.toml` — team overrides
+3. `{project-root}/_wizz/custom/wizz-create-story.user.toml` — personal overrides
 
 Any missing file is skipped. Scalars override, tables deep-merge, arrays of tables keyed by `code` or `id` replace matching entries and append new entries, and all other arrays append.
 
@@ -426,7 +425,7 @@ Activation is complete. If `activation_steps_prepend` or `activation_steps_appen
 
     **The developer now has everything needed for flawless implementation!**
   </output>
-  <action>Run: `python3 {project-root}/_wizz/scripts/resolve_customization.py --skill {skill-root} --key workflow.on_complete` — if the resolved value is non-empty, follow it as the final terminal instruction before exiting.</action>
+  <action>Run: read `{project-root}/_wizz/_resolved/wizz-create-story.json` (subtree `workflow.on_complete`). If the file is missing, empty or not valid JSON, run `npx wizz-method resolve --skill wizz-create-story` from the project root and read it again — if the resolved value is non-empty, follow it as the final terminal instruction before exiting.</action>
 </step>
 
 </workflow>

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

@@ -22,19 +22,18 @@ description: 'Execute story implementation following a context filled story spec
 - Bare paths (e.g. `steps/step-01-init.md`) resolve from the skill root.
 - `{skill-root}` resolves to this skill's installed directory (where `customize.toml` lives).
 - `{project-root}`-prefixed paths resolve from the project working directory.
-- `{skill-name}` resolves to the skill directory's basename.
 
 ## On Activation
 
 ### Step 1: Resolve the Workflow Block
 
-Run: `python3 {project-root}/_wizz/scripts/resolve_customization.py --skill {skill-root} --key workflow`
+Run: read `{project-root}/_wizz/_resolved/wizz-dev-story.json` (subtree `workflow`). If the file is missing, empty or not valid JSON, run `npx wizz-method resolve --skill wizz-dev-story` from the project root and read the snapshot again
 
 **If the script fails**, resolve the `workflow` block yourself by reading these three files in base → team → user order and applying the same structural merge rules as the resolver:
 
 1. `{skill-root}/customize.toml` — defaults
-2. `{project-root}/_wizz/custom/{skill-name}.toml` — team overrides
-3. `{project-root}/_wizz/custom/{skill-name}.user.toml` — personal overrides
+2. `{project-root}/_wizz/custom/wizz-dev-story.toml` — team overrides
+3. `{project-root}/_wizz/custom/wizz-dev-story.user.toml` — personal overrides
 
 Any missing file is skipped. Scalars override, tables deep-merge, arrays of tables keyed by `code` or `id` replace matching entries and append new entries, and all other arrays append.
 
@@ -495,7 +494,7 @@ Activation is complete. If `activation_steps_prepend` or `activation_steps_appen
       <action>Suggest checking {sprint_status} to see project progress</action>
     </check>
     <action>Remain flexible - allow user to choose their own path or ask for other assistance</action>
-  <action>Run: `python3 {project-root}/_wizz/scripts/resolve_customization.py --skill {skill-root} --key workflow.on_complete` — if the resolved value is non-empty, follow it as the final terminal instruction before exiting.</action>
+  <action>Run: read `{project-root}/_wizz/_resolved/wizz-dev-story.json` (subtree `workflow.on_complete`). If the file is missing, empty or not valid JSON, run `npx wizz-method resolve --skill wizz-dev-story` from the project root and read it again — if the resolved value is non-empty, follow it as the final terminal instruction before exiting.</action>
   </step>
 
 </workflow>

package/src/bmm-skills/4-implementation/wizz-investigate/SKILL.md

@@ -52,7 +52,7 @@ After every outcome, present what was learned and pause for the user before cont
 
 ### Step 1: Resolve the workflow block
 
-Run: `python3 {project-root}/_wizz/scripts/resolve_customization.py --skill {skill-root} --key workflow`
+Run: read `{project-root}/_wizz/_resolved/wizz-investigate.json` (subtree `workflow`). If the file is missing, empty or not valid JSON, run `npx wizz-method resolve --skill wizz-investigate` from the project root and read the snapshot again
 
 If the script fails, stop and surface the error.
 

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

@@ -14,19 +14,18 @@ description: 'Generate end to end automated tests for existing features. Use whe
 - Bare paths (e.g. `checklist.md`) resolve from the skill root.
 - `{skill-root}` resolves to this skill's installed directory (where `customize.toml` lives).
 - `{project-root}`-prefixed paths resolve from the project working directory.
-- `{skill-name}` resolves to the skill directory's basename.
 
 ## On Activation
 
 ### Step 1: Resolve the Workflow Block
 
-Run: `python3 {project-root}/_wizz/scripts/resolve_customization.py --skill {skill-root} --key workflow`
+Run: read `{project-root}/_wizz/_resolved/wizz-qa-generate-e2e-tests.json` (subtree `workflow`). If the file is missing, empty or not valid JSON, run `npx wizz-method resolve --skill wizz-qa-generate-e2e-tests` from the project root and read the snapshot again
 
 **If the script fails**, resolve the `workflow` block yourself by reading these three files in base → team → user order and applying the same structural merge rules as the resolver:
 
 1. `{skill-root}/customize.toml` — defaults
-2. `{project-root}/_wizz/custom/{skill-name}.toml` — team overrides
-3. `{project-root}/_wizz/custom/{skill-name}.user.toml` — personal overrides
+2. `{project-root}/_wizz/custom/wizz-qa-generate-e2e-tests.toml` — team overrides
+3. `{project-root}/_wizz/custom/wizz-qa-generate-e2e-tests.user.toml` — personal overrides
 
 Any missing file is skipped. Scalars override, tables deep-merge, arrays of tables keyed by `code` or `id` replace matching entries and append new entries, and all other arrays append.
 
@@ -171,6 +170,6 @@ Save summary to: `{default_output_file}`
 
 ## On Complete
 
-Run: `python3 {project-root}/_wizz/scripts/resolve_customization.py --skill {skill-root} --key workflow.on_complete`
+Run: read `{project-root}/_wizz/_resolved/wizz-qa-generate-e2e-tests.json` (subtree `workflow.on_complete`). If the file is missing, empty or not valid JSON, run `npx wizz-method resolve --skill wizz-qa-generate-e2e-tests` from the project root and read it again
 
 If the resolved `workflow.on_complete` is non-empty, follow it as the final terminal instruction before exiting.

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

@@ -37,7 +37,7 @@ A specification should target a **single user-facing goal** within **900–1600
 
 You are the leaf: the maestro demotes here for pointed work (bug, tweak, single-goal feature). Re-check scope against the shared complexity signal (areas, steps, needs-planning?, artifact+memory?):
 
-**Dispatch rule:** IF 2+ areas → `wizz-maestro`, always. ELSE count the 3 remaining factors (multi-step, needs planning, produces a memorable artifact); 2+ factors → `wizz-maestro`.
+**Dispatch rule:** IF 2+ areas → `wizz-maestro`, always. ELSE count the 3 remaining factors (multi-step, needs planning, produces a memorable artifact); 2+ factors → `wizz-maestro`. The area clause decides on its own, without summing with anything else.
 
 - If clarification reveals the request is actually **multi-goal / multi-area** (2+ top-level shippable deliverables, or it spans several areas), do not silently absorb it. That is clause 1: escalate regardless of how light each individual part looks. Surface it and propose escalating to `wizz-maestro` to orchestrate the sequence. Proceed solo only if the user confirms a narrowed single goal.
 - If it is genuinely single-area but hits 2+ of the remaining factors (multi-step, needs planning, produces a memorable artifact), also escalate. Do not silently absorb heavy single-area work either.
@@ -52,19 +52,18 @@ If the request is a **new multi-step feature** and no story/PRD covers it (check
 - Bare paths (e.g. `step-01-clarify-and-route.md`) resolve from the skill root.
 - `{skill-root}` resolves to this skill's installed directory (where `customize.toml` lives).
 - `{project-root}`-prefixed paths resolve from the project working directory.
-- `{skill-name}` resolves to the skill directory's basename.
 
 ## On Activation
 
 ### Step 1: Resolve the Workflow Block
 
-Run: `python3 {project-root}/_wizz/scripts/resolve_customization.py --skill {skill-root} --key workflow`
+Run: read `{project-root}/_wizz/_resolved/wizz-quick-dev.json` (subtree `workflow`). If the file is missing, empty or not valid JSON, run `npx wizz-method resolve --skill wizz-quick-dev` from the project root and read the snapshot again
 
 **If the script fails**, resolve the `workflow` block yourself by reading these three files in base → team → user order and applying the same structural merge rules as the resolver:
 
 1. `{skill-root}/customize.toml` — defaults
-2. `{project-root}/_wizz/custom/{skill-name}.toml` — team overrides
-3. `{project-root}/_wizz/custom/{skill-name}.user.toml` — personal overrides
+2. `{project-root}/_wizz/custom/wizz-quick-dev.toml` — team overrides
+3. `{project-root}/_wizz/custom/wizz-quick-dev.user.toml` — personal overrides
 
 Any missing file is skipped. Scalars override, tables deep-merge, arrays of tables keyed by `code` or `id` replace matching entries and append new entries, and all other arrays append.
 

package/src/bmm-skills/4-implementation/wizz-quick-dev/customize.toml

@@ -49,18 +49,13 @@ on_complete = ""
 id = "blind-hunter"
 name = "Blind Hunter"
 instruction = """
-Launch a context-free subagent with this prompt:
+Launch a context-free `wizz-exec-review` subagent with this prompt — pinned to the platform's Forte tier (`opus` in Claude Code), never inheriting the session model. Tell the user the tier and count of this dispatch.
 
-Conduct a review of CONTENT.
-Look for what's missing, not only what's wrong.
-Find at least ten issues to fix or improve.
-Output a Markdown list of findings only — no severity, priority, or ranking.
-If the content is empty, stop and say so.
-If you have zero findings, re-check and keep thinking; do not stop with an empty list.
+Read `{skill-root}/review-prompts/blind-hunter.md` completely and follow it as your review instructions.
 
-CONTENT: the unified diff at `{diff_file}`. Read that file — it is the content under review.
+Review content: the unified diff at `{diff_file}`. Read that file — it is the content under review.
 
-Do not invoke any skill, and do not spawn subagents of your own — you are the reviewer. Return your findings as text in your final message; do not route them through any findings-reporting tool the host may offer.
+Do not invoke any skill, and do not spawn subagents of your own — you are the reviewer. If the instruction file is unreadable, report that exact failure and stop. Return your findings as text in your final message; do not route them through any findings-reporting tool the host may offer.
 
 """
 
@@ -68,7 +63,7 @@ Do not invoke any skill, and do not spawn subagents of your own — you are the
 id = "edge-case-hunter"
 name = "Edge Case Hunter"
 instruction = """
-Launch a context-free subagent with this prompt:
+Launch a context-free `wizz-exec-review` subagent with this prompt — pinned to the platform's Forte tier (`opus` in Claude Code), never inheriting the session model. Tell the user the tier and count of this dispatch.
 
 Read `{skill-root}/review-prompts/edge-case-hunter.md` completely and follow it as your review instructions.
 
@@ -84,7 +79,7 @@ Do not invoke any skill, and do not spawn subagents of your own — you are the
 id = "verification-gap"
 name = "Verification Gap Reviewer"
 instruction = """
-Launch a context-free subagent with this prompt:
+Launch a context-free `wizz-exec-review` subagent with this prompt — pinned to the platform's Forte tier (`opus` in Claude Code), never inheriting the session model. Tell the user the tier and count of this dispatch.
 
 Read `{skill-root}/review-prompts/verification-gap.md` completely and follow it as your review instructions.
 
@@ -94,24 +89,24 @@ Do not invoke any skill, and do not spawn subagents of your own — you are the
 
 """
 
-# Review layers for the one-shot route.
+# Review layers for the one-shot route. Consumed by step-oneshot.md, the same way
+# step-04-review.md consumes review_layers above.
+#
+# O prompt do Blind Hunter vive em review-prompts/blind-hunter.md (fonte única,
+# item 22 da auditoria de 2026-09-11), mesmo padrão de edge-case-hunter e
+# verification-gap. Uma cópia idêntica fica em wizz-code-review/review-prompts/
+# e um teste de paridade (test/test-blind-hunter-parity.js) trava as duas.
 
 [[workflow.oneshot_review_layers]]
 id = "blind-hunter"
 name = "Blind Hunter"
 instruction = """
-Launch a context-free subagent with this prompt:
+Launch a context-free `wizz-exec-review` subagent with this prompt — pinned to the platform's Forte tier (`opus` in Claude Code), never inheriting the session model. Tell the user the tier and count of this dispatch.
 
-Conduct a review of CONTENT.
-Look for what's missing, not only what's wrong.
-Find at least ten issues to fix or improve.
-Output a Markdown list of findings only — no severity, priority, or ranking.
-If the content is empty, stop and say so.
-If you have zero findings, re-check and keep thinking; do not stop with an empty list.
+Read `{skill-root}/review-prompts/blind-hunter.md` completely and follow it as your review instructions.
 
-CONTENT:
-The changed files in the current worktree. Inspect them directly before reviewing.
+Review content: the changed files in the current worktree. Inspect them directly before reviewing.
 
-Do not invoke any skill, and do not spawn subagents of your own — you are the reviewer. Return your findings as text in your final message; do not route them through any findings-reporting tool the host may offer.
+Do not invoke any skill, and do not spawn subagents of your own — you are the reviewer. If the instruction file is unreadable, report that exact failure and stop. Return your findings as text in your final message; do not route them through any findings-reporting tool the host may offer.
 
 """

package/src/bmm-skills/4-implementation/wizz-quick-dev/review-prompts/blind-hunter.md

@@ -0,0 +1,20 @@
+# Blind Hunter Review
+
+**Goal:** Conduct a blind review of CONTENT — no project context, no spec, no triage. Hunt for what's missing, not only what's wrong.
+
+**Your method:**
+
+- Conduct a review of CONTENT.
+- Look for what's missing, not only what's wrong.
+- Find at least ten issues to fix or improve.
+- Output a Markdown list of findings only — no severity, priority, or ranking.
+- If the content is empty, stop and say so.
+- If you have zero findings, re-check and keep thinking; do not stop with an empty list.
+
+## OUTPUT FORMAT
+
+A Markdown list of findings only. One bullet per issue, description only — no severity, priority, or ranking.
+
+## CONTENT SOURCE
+
+"Review content:" in the message that launched you gives the content itself or a path to read it from. Read the file when it is a path; either way that is the content under review, and this instruction file never is. If no content is supplied, or it is empty or unreadable, stop and say so — never report a clean review for content you could not read.

package/src/bmm-skills/4-implementation/wizz-quick-dev/step-04-review.md

@@ -10,7 +10,7 @@ claims_file: '' # set at runtime: path to the change's own narrative
 
 - YOU MUST ALWAYS SPEAK OUTPUT in your Agent communication style with the config `{communication_language}`. Write any file output in `{document_output_language}`.
 - Review subagents get NO conversation context.
-- All review subagents must run at the same model capability as the current session.
+- Review subagents run pinned to the platform's Forte tier via `wizz-exec-review` (`opus` in Claude Code) — never at the same model capability as the current session. See `_shared/model-ladder.md`.
 - Run subagents synchronously: launch them together, then wait for all results before continuing. Never backgrounded or detached, never ending the turn to await results.
 
 ## INSTRUCTIONS

package/src/bmm-skills/4-implementation/wizz-quick-dev/step-05-present.md

@@ -73,6 +73,6 @@ Workflow complete.
 
 ## On Complete
 
-Run: `python3 {project-root}/_wizz/scripts/resolve_customization.py --skill {skill-root} --key workflow.on_complete`
+Run: read `workflow.on_complete` from the `{project-root}/_wizz/_resolved/wizz-quick-dev.json` snapshot loaded in step 1
 
 If the resolved `workflow.on_complete` is non-empty, follow it as the final terminal instruction before exiting.

package/src/bmm-skills/4-implementation/wizz-quick-dev/step-oneshot.md

@@ -19,7 +19,18 @@ Implement the clarified intent directly.
 
 ### Review
 
-Invoke the `wizz-review-adversarial-general` skill in a subagent with the changed files. The subagent gets NO conversation context — to avoid anchoring bias. Launch at the same model capability as the current session. If no sub-agents are available, write the changed files to a review prompt file in `{implementation_artifacts}` and HALT. Ask the human to run the review in a separate session and paste back the findings.
+1. The review layers are `{workflow.oneshot_review_layers}`, resolved during activation. For each layer:
+   - `instruction` empty or missing → drop the layer silently (an override disabled it).
+   - `when` condition present and not satisfied by the current context → drop the layer and tell the user.
+   - otherwise → the layer is active.
+
+   If no layer is active, HALT and escalate to the human.
+
+2. Announce skipped layers first, then launch every active layer before handling any layer's result. Expand `{skill-root}` in each layer's `instruction` to this skill's absolute installed directory — the child's working directory is not yours, so never leave it unresolved in a child prompt. Reviewers get NO conversation context, to avoid anchoring bias: they inspect the changed files in the worktree themselves. When an instruction launches a reviewer subagent, launch that child with the prompt text after expansion; for any other customized instruction, execute it as written. Spawn every reviewer before reading any of their output.
+
+3. If a layer's instruction requires subagents and none are available, write that layer's child prompt under `{implementation_artifacts}`, with every file it points to replaced inline by that file's contents and every other line left exactly as written — that session shares no filesystem with this one, so its prompt has to stand alone. Then HALT. Ask the human to run it in a separate session and paste back the findings.
+
+4. If any layer fails, times out, or returns empty, note it and proceed with the remaining layers. Collect all findings.
 
 ### Classify
 
@@ -66,6 +77,6 @@ Workflow complete.
 
 ## On Complete
 
-Run: `python3 {project-root}/_wizz/scripts/resolve_customization.py --skill {skill-root} --key workflow.on_complete`
+Run: read `workflow.on_complete` from the `{project-root}/_wizz/_resolved/wizz-quick-dev.json` snapshot loaded in step 1
 
 If the resolved `workflow.on_complete` is non-empty, follow it as the final terminal instruction before exiting.

package/src/bmm-skills/4-implementation/wizz-retrospective/SKILL.md

@@ -13,7 +13,6 @@ Every finding you report carries a source reference (file, line, commit, or log)
 
 - Bare paths and `{skill-root}` (e.g. `references/aggregate-views.md`, `scripts/sprint_status.py`) resolve from this skill's installed directory.
 - `{project-root}` → the project working directory.
-- `{skill-name}` → the skill directory's basename.
 - **Scripts:** `git_evidence.py` is stdlib-only and runs under `python3`, the Wizz default. `sprint_status.py` needs `ruamel.yaml` to round-trip the YAML without destroying its comments, so it runs under `uv run --no-cache`, which provisions the dependency from the script's own header. Do not rewrite it to `python3`: without `ruamel.yaml` installed globally it fails with `ModuleNotFoundError`.
 
 ## Modes
@@ -26,7 +25,7 @@ For automation, `-H <epic>` — an explicit epic in headless mode — is the sta
 
 Run these in order before the retrospective begins:
 
-1. **Resolve the workflow block.** Run `python3 {project-root}/_wizz/scripts/resolve_customization.py --skill {skill-root} --key workflow`. If it fails, resolve `{workflow.*}` yourself by reading `{skill-root}/customize.toml`, then `{project-root}/_wizz/custom/{skill-name}.toml`, then `.user.toml` in that order, merging base → team → user (scalars override, keyed arrays-of-tables merge by `code`/`id`, other arrays append).
+1. **Resolve the workflow block.** Read `{project-root}/_wizz/_resolved/wizz-retrospective.json` (subtree `workflow`). If the file is missing, empty or not valid JSON, run `npx wizz-method resolve --skill wizz-retrospective` from the project root and read the snapshot again. If it fails, resolve `{workflow.*}` yourself by reading `{skill-root}/customize.toml`, then `{project-root}/_wizz/custom/wizz-retrospective.toml`, then `.user.toml` in that order, merging base → team → user (scalars override, keyed arrays-of-tables merge by `code`/`id`, other arrays append).
 2. **Run prepend steps** — execute each entry in `{workflow.activation_steps_prepend}` in order.
 3. **Load persistent facts** — treat every `{workflow.persistent_facts}` entry as standing context. `file:` entries are paths/globs under `{project-root}` whose contents load as facts; all others are literal facts.
 4. **Load config** from `{project-root}/_wizz/bmm/config.yaml`: `project_name`, `user_name`, `communication_language`, `document_output_language`, `user_skill_level`, `planning_artifacts`, `implementation_artifacts`, and `date` (system datetime), plus `output_folder` from `{project-root}/_wizz/core/config.yaml`. Speak all output in `{communication_language}`; write all documents in `{document_output_language}`. Never state time estimates — AI has changed development speed, so hour/day/week predictions are noise.

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

@@ -9,7 +9,7 @@ You are a senior developer about to commit to this plan. Two moves, in order: fi
 
 ## On Activation
 
-1. Resolve customization: `python3 {project-root}/_wizz/scripts/resolve_customization.py --skill {skill-root} --key workflow`. On failure, read `{skill-root}/customize.toml` directly and use defaults.
+1. Resolve customization: Read `{project-root}/_wizz/_resolved/wizz-sprint-planning.json` (subtree `workflow`). If the file is missing, empty or not valid JSON, run `npx wizz-method resolve --skill wizz-sprint-planning` from the project root and read the snapshot again. On failure, read `{skill-root}/customize.toml` directly and use defaults.
 2. Execute each entry in `{workflow.activation_steps_prepend}` in order.
 3. Treat every entry in `{workflow.persistent_facts}` as foundational context for the rest of the run. Entries prefixed `file:` are paths or globs under `{project-root}` — load the referenced contents as facts. All other entries are facts verbatim.
 4. Load `{project-root}/_wizz/bmm/config.yaml` (and `config.user.yaml` if present). Resolve `{user_name}`, `{communication_language}`, `{document_output_language}`, `{project_name}`, `{planning_artifacts}`, `{implementation_artifacts}`, `{project_knowledge}` (skip gracefully if unset), `{date}`. Stay in `{communication_language}` for every turn, not just the greeting.

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

@@ -14,19 +14,18 @@ description: 'Summarize sprint status and surface risks. Use when the user says
 - Bare paths (e.g. `checklist.md`) resolve from the skill root.
 - `{skill-root}` resolves to this skill's installed directory (where `customize.toml` lives).
 - `{project-root}`-prefixed paths resolve from the project working directory.
-- `{skill-name}` resolves to the skill directory's basename.
 
 ## On Activation
 
 ### Step 1: Resolve the Workflow Block
 
-Run: `python3 {project-root}/_wizz/scripts/resolve_customization.py --skill {skill-root} --key workflow`
+Run: read `{project-root}/_wizz/_resolved/wizz-sprint-status.json` (subtree `workflow`). If the file is missing, empty or not valid JSON, run `npx wizz-method resolve --skill wizz-sprint-status` from the project root and read the snapshot again
 
 **If the script fails**, resolve the `workflow` block yourself by reading these three files in base → team → user order and applying the same structural merge rules as the resolver:
 
 1. `{skill-root}/customize.toml` — defaults
-2. `{project-root}/_wizz/custom/{skill-name}.toml` — team overrides
-3. `{project-root}/_wizz/custom/{skill-name}.user.toml` — personal overrides
+2. `{project-root}/_wizz/custom/wizz-sprint-status.toml` — team overrides
+3. `{project-root}/_wizz/custom/wizz-sprint-status.user.toml` — personal overrides
 
 Any missing file is skipped. Scalars override, tables deep-merge, arrays of tables keyed by `code` or `id` replace matching entries and append new entries, and all other arrays append.
 
@@ -232,7 +231,7 @@ If the command targets a story, set `story_key={{next_story_id}}` when prompted.
   </check>
 
   <check if="choice == 4">
-    <action>Run: `python3 {project-root}/_wizz/scripts/resolve_customization.py --skill {skill-root} --key workflow.on_complete` — if the resolved value is non-empty, follow it as the final terminal instruction before exiting.</action>
+    <action>Run: read `{project-root}/_wizz/_resolved/wizz-sprint-status.json` (subtree `workflow.on_complete`). If the file is missing, empty or not valid JSON, run `npx wizz-method resolve --skill wizz-sprint-status` from the project root and read it again — if the resolved value is non-empty, follow it as the final terminal instruction before exiting.</action>
     <action>Exit workflow</action>
   </check>
 </step>
@@ -305,7 +304,7 @@ If the command targets a story, set `story_key={{next_story_id}}` when prompted.
 
 <template-output>is_valid = true</template-output>
 <template-output>message = "sprint-status.yaml valid: metadata complete, all statuses recognized"</template-output>
-<action>Run: `python3 {project-root}/_wizz/scripts/resolve_customization.py --skill {skill-root} --key workflow.on_complete` — if the resolved value is non-empty, follow it as the final terminal instruction before exiting.</action>
+<action>Run: read `{project-root}/_wizz/_resolved/wizz-sprint-status.json` (subtree `workflow.on_complete`). If the file is missing, empty or not valid JSON, run `npx wizz-method resolve --skill wizz-sprint-status` from the project root and read it again — if the resolved value is non-empty, follow it as the final terminal instruction before exiting.</action>
 </step>
 
 </workflow>

package/src/core-skills/_shared/handoff-protocol.md

@@ -30,6 +30,14 @@ o entrypoint da skill e apenas as referências necessárias (progressive disclos
   acima de Opus (Fable); em sessão Opus quem recebe pula para `review`
   (detalhe completo em `_shared/model-ladder.md`, no módulo wizz).
   Campo opcional: sem ele o handoff funciona normal.
+- max_calls (opcional): teto de chamadas de ferramenta (tool calls) que o
+  executor pode gastar neste brief, como inteiro. Quem recebe despacha o
+  `wizz-exec-<hint>` com esse teto declarado no brief. Ao atingir o teto,
+  o executor PARA, entrega o parcial com pendências explícitas e não
+  escala sozinho: quem delega decide o próximo passo (reemitir com teto
+  maior, escalar 1 degrau, ou absorver o resto). Regra instrucional, igual
+  à anti-loop: nada programático conta as chamadas. Sem `max_calls` o
+  handoff funciona normal.
 - precisa planejar (opcional): veredito sim/não do fator de planejamento
   do sinal de complexidade, avaliado por quem delega. Evita que quem
   recebe re-derive o sinal para aplicar o Gate de Planejamento
@@ -47,6 +55,7 @@ o entrypoint da skill e apenas as referências necessárias (progressive disclos
     decisões já tomadas na cadeia: escopo é só mobile-first.
     seção relevante da skill: page-cro/references/checkout-flow.md
     model_hint: sonnet
+    max_calls: 40
 
 ## Regra anti-loop
 

package/src/core-skills/wizz-advanced-elicitation/SKILL.md

@@ -14,7 +14,7 @@ You are Wizz's shared refinement checkpoint: other skills invoke you at natural
 
 ## On Activation
 
-1. Resolve customization: `python3 {project-root}/_wizz/scripts/resolve_customization.py --skill {skill-root} --key workflow`. On failure, read `{skill-root}/customize.toml` directly and use defaults.
+1. Resolve customization: Read `{project-root}/_wizz/_resolved/wizz-advanced-elicitation.json` (subtree `workflow`). If the file is missing, empty or not valid JSON, run `npx wizz-method resolve --skill wizz-advanced-elicitation` from the project root and read the snapshot again. On failure, read `{skill-root}/customize.toml` directly and use defaults.
 2. Hold every `{workflow.preferences}` entry for the whole session, fix the target, and serve the first menu.
 
 ## Serving the Catalog
@@ -61,4 +61,4 @@ Use the method's description as its intent and its output_pattern as a flexible
 
 Never change the work unless the user accepts the proposal. If they reject it, drop the proposal entirely. Any other reply is instruction to follow.
 
-When a method casts personas (round tables, panels, debates), reuse party members already in the session if party mode is active; otherwise resolve installed agents on demand via `python3 {project-root}/_wizz/scripts/resolve_config.py --project-root {project-root} --key agents` (a four-layer merge of `_wizz/config.toml`, `config.user.toml`, and the two `_wizz/custom/` overrides; each entry keyed by agent code carries name, title, icon, description). If neither yields a fit, invent named viewpoints suited to the content.
+When a method casts personas (round tables, panels, debates), reuse party members already in the session if party mode is active; otherwise resolve installed agents on demand by reading the `agents` key of `{project-root}/_wizz/_resolved/_config.json` (the same four-layer merge, resolved at install time, of `_wizz/config.toml`, `config.user.toml`, and the two `_wizz/custom/` overrides; each entry keyed by agent code carries name, title, icon, description). If neither yields a fit, invent named viewpoints suited to the content.

package/src/core-skills/wizz-brainstorming/SKILL.md

@@ -18,7 +18,7 @@ The session runs in one of three stances, chosen by the user — set explicitly
 
 ## On Activation
 
-1. Resolve customization: `python3 {project-root}/_wizz/scripts/resolve_customization.py --skill {skill-root} --key workflow`. On failure, use a subagent to read `{skill-root}/customize.toml` directly with defaults.
+1. Resolve customization: Read `{project-root}/_wizz/_resolved/wizz-brainstorming.json` (subtree `workflow`). If the file is missing, empty or not valid JSON, run `npx wizz-method resolve --skill wizz-brainstorming` from the project root and read the snapshot again. On failure, use a subagent to read `{skill-root}/customize.toml` directly with defaults.
 2. Run each `{workflow.activation_steps_prepend}` entry. Treat each `{workflow.persistent_facts}` entry as foundational context (`file:`-prefixed entries are paths/globs under `{project-root}` — load their contents; others are facts verbatim).
 3. Load `{project-root}/_wizz/core/config.yaml` (and `config.user.yaml` if present); resolve `{user_name}`, `{communication_language}`, `{document_output_language}`, `{output_folder}`, `{project_name}`, `{date}`. Missing → neutral defaults; never block.
 4. **If launched headless** (a machine signal, not a human asking for output — `references/headless.md` lists them): load `references/headless.md` and follow it for the whole run. It is the *only* context where you generate ideas yourself; never load it otherwise.
@@ -34,13 +34,13 @@ These fight your defaults, in every mode; hold them deliberately. The stance you
 - **Keep shifting the creative domain** — every 5–10 turns (or ~10 ideas when you're generating), usually by moving to the next technique.
 - **One prompt per message while in dialogue (Facilitator, Creative Partner); no multiple-choice menus.** Don't stack questions into a wall or hand a menu that invites lazy picking — both pull the user out of generating. The only exceptions are the two up-front *process* choices (stance, and the technique flow): *how* to run is theirs to pick; *what* to ideate never is.
 
-**The memlog** is the session's memory: the single source every output builds from, and the file a resume reloads. Whatever isn't in it is gone. Log every idea, decision, question, and bit of user direction — anything you'd regret losing if the window closed — one line each, the gist in the user's meaning, in time order; never edit or reorder. Skip your prompts and small talk. All writes go through the shared `{project-root}/_wizz/scripts/memlog.py` (atomic; don't read it back mid-session — resume is the one exception):
+**The memlog** is the session's memory: the single source every output builds from, and the file a resume reloads. Whatever isn't in it is gone. Log every idea, decision, question, and bit of user direction — anything you'd regret losing if the window closed — one line each, the gist in the user's meaning, in time order; never edit or reorder. Skip your prompts and small talk. All writes go through the shared `{project-root}/_wizz/scripts/memlog.js` (atomic; don't read it back mid-session — resume is the one exception):
 
-- `memlog.py init --workspace {doc_workspace} --field topic="<topic>" --field goal="<goal>" --field mode="<facilitator|partner|autonomous>"` — create it once topic, goal, and stance are known.
-- `memlog.py append --workspace {doc_workspace} --type <kind> --text "<one-line gist>"` — log one entry. `--type` ∈ `idea`/`insight`/`question`/`decision`/`direction`/`technique` (a switch: `--text "started <name>"`); omit for a plain note. Add `--by user`/`--by coach` to mark authorship — **required in Creative Partner mode** (renders `(idea by user)`); skip it otherwise.
-- `memlog.py set --workspace {doc_workspace} --key status --value complete` — flip status at wrap-up.
+- `memlog.js init --workspace {doc_workspace} --field topic="<topic>" --field goal="<goal>" --field mode="<facilitator|partner|autonomous>"` — create it once topic, goal, and stance are known.
+- `memlog.js append --workspace {doc_workspace} --type <kind> --text "<one-line gist>"` — log one entry. `--type` ∈ `idea`/`insight`/`question`/`decision`/`direction`/`technique` (a switch: `--text "started <name>"`); omit for a plain note. Add `--by user`/`--by coach` to mark authorship — **required in Creative Partner mode** (renders `(idea by user)`); skip it otherwise.
+- `memlog.js set --workspace {doc_workspace} --key status --value complete` — flip status at wrap-up.
 
-(Each is `python3 {project-root}/_wizz/scripts/memlog.py …`.)
+(Each is `node {project-root}/_wizz/scripts/memlog.js …`.)
 
 ## Run a Session
 

package/src/core-skills/wizz-brainstorming/references/converge.md

@@ -17,7 +17,7 @@ Pick by what the decision needs:
 - **PMI (Plus / Minus / Interesting)** — when one strong candidate needs pressure-testing before commitment: list its pluses, minuses, and the merely-interesting, then judge.
 - **MoSCoW** — when scoping a build: sort into Must / Should / Could / Won't-this-time.
 
-Log the surviving directions and the reasoning with `python3 {project-root}/_wizz/scripts/memlog.py append --type decision --text "<one-line gist>"` (use `--by` in Creative Partner mode). Two or three convergence moves chained is fine (e.g. cluster → score the clusters); more than that is usually over-processing.
+Log the surviving directions and the reasoning with `node {project-root}/_wizz/scripts/memlog.js append --type decision --text "<one-line gist>"` (use `--by` in Creative Partner mode). Two or three convergence moves chained is fine (e.g. cluster → score the clusters); more than that is usually over-processing.
 
 ## Then finalize
 

package/src/core-skills/wizz-brainstorming/references/finalize.md

@@ -9,7 +9,7 @@ In Facilitator mode this is the one place your own creative contribution is welc
 1. **Hand them the mirror first.** Reflect a vivid sampling of *their* ideas back — deliberately include the odd, random, or buried ones from earlier, not just the recent obvious ones (in Creative Partner mode the `(... by user)` tags tell you which were theirs). Ask what they see now: conclusions, synergies, themes, the few that actually matter. Let them connect first; their own pattern-recognition is the point.
 2. **Then add the connections they would miss.** Lean in creatively — not new raw ideas, but the non-obvious links: this idea from technique one quietly solves that tension from technique four; these three are one idea wearing three hats; this wildcard is the real breakthrough.
 
-Record the insights and chosen directions with `memlog.py append --type insight`. **Then run `python3 {project-root}/_wizz/scripts/memlog.py set --workspace {doc_workspace} --key status --value complete`** — the session is done and must stop being offered for resume. Do this even if the user declines every artifact below.
+Record the insights and chosen directions with `memlog.js append --type insight`. **Then run `node {project-root}/_wizz/scripts/memlog.js set --workspace {doc_workspace} --key status --value complete`** — the session is done and must stop being offered for resume. Do this even if the user declines every artifact below.
 
 ## Artifacts