wizz-method 2.13.0 → 2.15.0

package/src/core-skills/wizz-party-mode/scripts/tests/test_resolve_party.py

@@ -5,6 +5,7 @@
 """Unit tests for resolve_party.py — merge, alias, override, group resolution."""
 
 import sys
+import tempfile
 import unittest
 from pathlib import Path
 
@@ -142,5 +143,25 @@ class TestInstalledCodesIsDefaultRoom(unittest.TestCase):
         self.assertEqual(col["wizz-agent-analyst"]["name"], "Mary-Custom")
 
 
+class TestPassesProjectRootToResolver(unittest.TestCase):
+    """Sem snapshot, o wrapper chama resolve_customization.py; a raiz vai explícita (BMAD 6.12, #2802)."""
+
+    def _captured_command(self, tmp):
+        captured = []
+        original = rp._run_json
+        rp._run_json = lambda cmd: captured.append(cmd) or {"workflow": {}}
+        try:
+            rp.load_workflow(Path(tmp) / "project", Path(tmp) / "skill")
+        finally:
+            rp._run_json = original
+        return captured[0]
+
+    def test_passes_project_root_to_the_customization_resolver(self):
+        with tempfile.TemporaryDirectory() as tmp:
+            cmd = self._captured_command(tmp)
+            self.assertIn("--project-root", cmd)
+            self.assertEqual(cmd[cmd.index("--project-root") + 1], str(Path(tmp) / "project"))
+
+
 if __name__ == "__main__":
     unittest.main()

package/src/core-skills/wizz-spec/customize.toml

@@ -20,11 +20,10 @@ activation_steps_append = []
 # Persistent facts the workflow keeps in mind for the whole run.
 # Each entry is either a literal sentence, a skill prefixed with `skill:`,
 # or a `file:`-prefixed path/glob whose contents are loaded as facts.
-# Default points to a single top-level file; override in team/user TOML
-# to widen the scope (e.g. `_wizz/**/project-context.md`) if needed.
-persistent_facts = [
-  "file:{project-root}/project-context.md",
-]
+# Empty of project-context by default: repo-wide context belongs in CLAUDE.md/AGENTS.md
+# (the Wizz block imports project-context.md there once per session). Add
+# `file:{project-root}/**/project-context.md` here only to load it on every activation.
+persistent_facts = []
 
 # Executed when the workflow completes. Scalar or array of instructions.
 on_complete = ""

package/src/modules/wizz/_shared/model-ladder.md

@@ -4,7 +4,7 @@ The names `wizz-exec-mechanical`/`wizz-exec-standard`/`wizz-exec-strong`/`wizz-e
 
 ## The recommended session (the boss)
 
-The recommended session model is the Standard tier (Sonnet 5 / gpt-5.6-terra / claude-sonnet-5 / gemini-3.5-flash). The boss does common work itself — commands, questions, implementation with a spec — dispatches subagents for isolation or parallel work, arbitrates conflict between executor and reviewer, and takes architecture/product decisions WITH the user.
+The recommended session model is the Standard tier (Sonnet / gpt-5.6-terra / claude-sonnet-5-5 / gemini-3.5-flash). The boss does common work itself — commands, questions, implementation with a spec — dispatches subagents for isolation or parallel work, arbitrates conflict between executor and reviewer, and takes architecture/product decisions WITH the user.
 
 A session running above Standard (Opus, Fable, Mythos...) absorbs every tier at or below its own model: an Opus session does Strong work itself, and dispatches `wizz-exec-ultra` only after that attempt returns `ESCALAR` per the escalation signals below. A session on the Ultra model (Fable) absorbs Ultra too: it takes strong's `ESCALAR` itself and never dispatches `wizz-exec-ultra`. Review is the exception — it's NEVER absorbed: it always runs on `wizz-exec-review`, pinned to the Strong tier, so in a Fable session review moves off the boss and onto Opus.
 
@@ -15,10 +15,10 @@ How to know who the boss is in Claude Code: the system prompt states the session
 | Tier | Subagent | Use | Claude Code | Codex | OpenCode | Gemini CLI |
 |---|---|---|---|---|---|---|
 | Mechanical | `wizz-exec-mechanical` | scanning, rename, repetitive diff, 100% specified change | haiku (maxTurns 50, no effort field) | gpt-5.6-luna, effort low | anthropic/claude-haiku-4-5 | gemini-3.1-flash-lite (max_turns 50, no effort field) |
-| Standard | `wizz-exec-standard` | small/medium defined feature, bug with known cause, tests | sonnet, effort medium (maxTurns 80) | gpt-5.6-terra, effort medium | anthropic/claude-sonnet-5 | gemini-3.5-flash (max_turns 80) |
-| Strong | `wizz-exec-strong` | bug with unclear cause after one investigation cycle, refactor spanning modules, schema/auth/payment changes, local technical decision | opus, effort high (maxTurns 120) | gpt-5.6-sol, effort high | anthropic/claude-opus-5 | gemini-3.1-pro-preview (max_turns 120) |
+| Standard | `wizz-exec-standard` | small/medium defined feature, bug with known cause, tests | sonnet, effort medium (maxTurns 80) | gpt-5.6-terra, effort medium | anthropic/claude-sonnet-5-5 | gemini-3.5-flash (max_turns 80) |
+| Strong | `wizz-exec-strong` | bug with unclear cause after one investigation cycle, refactor spanning modules, schema/auth/payment changes, local technical decision | opus, effort high (maxTurns 120) | gpt-5.6-sol, effort high | anthropic/claude-opus-5-5 | gemini-3.1-pro-preview (max_turns 120) |
 | Ultra | `wizz-exec-ultra` | ultra-hard work the Strong tier returned `ESCALAR` on, plus its findings | fable, effort xhigh (maxTurns 150) | gpt-6-astra, effort xhigh | anthropic/claude-fable-5-1 | no ultra tier on this platform |
-| Review | `wizz-exec-review` | review of a diff produced by any tier; pinned to Strong, never inherits the session | opus, effort high (maxTurns 60) | gpt-5.6-sol, effort high | anthropic/claude-opus-5 | gemini-3.1-pro-preview (max_turns 60) |
+| Review | `wizz-exec-review` | review of a diff produced by any tier; pinned to Strong, never inherits the session | opus, effort high (maxTurns 60) | gpt-5.6-sol, effort high | anthropic/claude-opus-5-5 | gemini-3.1-pro-preview (max_turns 60) |
 
 OpenCode gets the model only: its per-agent effort field isn't documented, and it has no per-agent turn cap field either. Claude Code and Gemini CLI enforce turn caps natively (`maxTurns` / `max_turns`); Codex and OpenCode have no per-agent turn cap field, so briefs to them should always carry `max_calls`.
 

package/src/modules/wizz/agents/wizz-designer/SKILL.md

@@ -34,7 +34,7 @@ For every task, **go through the right door via the `Skill` tool** and bring the
 
 Always **show the visual/plan before the code**. Code building is `wizz-agent-dev`'s job; for a one-off tweak, point to `wizz-quick-dev`.
 
-**Research gate:** for a non-trivial component/effect, research runs against the project's research map (`design-state.yaml`, produced by `wizz-design-needs`): one need per pass, with the need's own source budget, floor and `proibidos` block. Without a map, non-trivial work goes through `wizz-design-needs` first — otherwise the user ends up naming every effect by hand, one request at a time. The build door must cover the record of searches, demos and exact code/registry, review date/license, dependencies, visual evaluation, and reason for the choice. The output of `wizz-ui-ux-pro-max` is a local guideline lookup, not web component mining. Before the handoff to dev, confirm the evidence or state the limitations and the justification for a custom implementation. Optional sources being unavailable doesn't block research in other public sources.
+**Research gate:** for a non-trivial component/effect, research runs against the project's research map (`design-state.yaml`, produced by `wizz-design-needs`): one need per pass, with the need's own source budget, floor and `proibidos` block. Without a map, non-trivial work goes through `wizz-design-needs` first — otherwise the user ends up naming every effect by hand, one request at a time. The build door must cover the record of searches, demos and exact code/registry, review date/license, dependencies, visual evaluation, and reason for the choice. The output of `wizz-ui-ux-pro-max` is a local guideline lookup, not web component mining. Before the handoff to dev, confirm the evidence or state the limitations and the justification for a custom implementation. Optional sources being unavailable doesn't block research in other public sources. A generic design skill from outside the registry (e.g. the frontend-design plugin) can add taste, never replace this gate. When the work goes to a `wizz-exec-*` subagent, the brief names the door, the map path and the need ids: the subagent does not inherit this gate on its own.
 
 ## Closing
 Close in the Wizz format: `✅ O que fiz` (simple sentences) / `➡️ Próximo passo` (usually wizz-agent-dev or wizz-quick-dev to build) / `🎯 Comando`.

package/src/modules/wizz/agents/wizz-maestro/SKILL.md

@@ -101,7 +101,7 @@ In short: **the menu chooses the agent, the registry chooses the skill(s) and th
 
 Inside the 1-area branch, three shortcuts **demote on their own**, before counting any factor: a **question with a single definable answer**, a **single delivery**, and the **diagnosis of one specific mechanism** all go to the area agent. "How do I improve / reduce X" is not that question — it has no single answer. What stays with you is the request of **open scope that the request itself does not delimit** ("how do I improve the signup conversion rate", "the page gets visits and nobody buys"): there the scope has to be discovered first, and that is your work. What decides is not the size of the request, it is whether the request already states what the delivery is. **Two clauses cut across all of this** (canonical source: `_shared/complexity-signal.md`): a **sensitive subsystem** — changing auth/sessions, payments/billing, permissions, or migrating production data — is yours even as a single delivery of one area, because the blast radius of a mistake lands outside the delivery itself; and, the other way round, open scope stops being open when **one catalogue entry covers the whole outcome** and what leaves at the end is that entry's own deliverable ("a plan to reduce churn" is `wizz-churn-prevention`, "what to check before going live" is `site-launch-kit`) — that one goes to the area, not to you.
 
-**Changing the product's code is `dev`, even when the subject is visual** — the delivery is a commit. Ask which artifact leaves at the end: a file in the repo → dev; a decision, a spec or a piece of art → the area that owns it.
+**Changing the product's code is `dev`, even when the subject is visual** — the delivery is a commit. Ask which artifact leaves at the end: a file in the repo → dev; a decision, a spec or a piece of art → the area that owns it. **Exception: new or rebuilt screens.** When the request asks to BUILD screens in code (a new app, page, dashboard or panel, or a whole screen rebuilt in the product), the visual decision has not been made yet, so `designer` comes first and the sequence is design → dev: the designer runs its research gate (`wizz-design-needs` → `wizz-ui-component-curator` / `wizz-premium-landing-ui-researcher`) before any screen is coded. A generic design skill from outside the registry (e.g. the frontend-design plugin) never stands in for that gate. A tweak to an existing screen (a price, a label, a spacing) stays dev, and redesigning a section with no build asked for (a hero, a card) stays designer.
 
 **What `rel` drags counts as an extra area when the related capability shapes the SAME deliverable.** Ask of each edge: would the thing being handed over be incomplete without this? A sales page without the offer and the conversion structure is half a page (same artifact → escalates); a text post does not become a video job because of a `before: [get-brolls]` edge (different artifact → does not). `pairs_with` alone never escalates.
 

package/src/modules/wizz/subagents/opencode/wizz-exec-review.md

@@ -1,9 +1,9 @@
 ---
 # Gerado por tools/generate-subagents.mjs a partir de src/modules/wizz/subagents/spec.yaml. Não edite este arquivo direto: edite o spec.yaml e rode `npm run generate:subagents`.
 description: >-
-  Wizz Method reviewer pinned to the Strong tier (anthropic/claude-opus-5), never to the session's model. Receives a diff or an executor's result and reviews correctness, security, regressions, and scope adherence. Doesn't implement: returns a verdict and a list of issues with file:line.
+  Wizz Method reviewer pinned to the Strong tier (anthropic/claude-opus-5-5), never to the session's model. Receives a diff or an executor's result and reviews correctness, security, regressions, and scope adherence. Doesn't implement: returns a verdict and a list of issues with file:line.
 mode: subagent
-model: anthropic/claude-opus-5
+model: anthropic/claude-opus-5-5
 permission:
   edit: deny
 ---

package/src/modules/wizz/subagents/opencode/wizz-exec-standard.md

@@ -1,9 +1,9 @@
 ---
 # Gerado por tools/generate-subagents.mjs a partir de src/modules/wizz/subagents/spec.yaml. Não edite este arquivo direto: edite o spec.yaml e rode `npm run generate:subagents`.
 description: >-
-  Standard Wizz Method executor for day-to-day implementation. Well-defined small/medium features, bug fixes with a known cause, multi-file edits, tests. Same tier as the recommended session model: dispatch it for isolation or parallel work (1 per file/module, up to 4 at once), not to escalate. Model on this platform: anthropic/claude-sonnet-5.
+  Standard Wizz Method executor for day-to-day implementation. Well-defined small/medium features, bug fixes with a known cause, multi-file edits, tests. Same tier as the recommended session model: dispatch it for isolation or parallel work (1 per file/module, up to 4 at once), not to escalate. Model on this platform: anthropic/claude-sonnet-5-5.
 mode: subagent
-model: anthropic/claude-sonnet-5
+model: anthropic/claude-sonnet-5-5
 ---
 
 You are an implementation executor for the Wizz Method. You receive a brief with a goal and context, and you implement it.

package/src/modules/wizz/subagents/opencode/wizz-exec-strong.md

@@ -1,9 +1,9 @@
 ---
 # Gerado por tools/generate-subagents.mjs a partir de src/modules/wizz/subagents/spec.yaml. Não edite este arquivo direto: edite o spec.yaml e rode `npm run generate:subagents`.
 description: >-
-  Strong Wizz Method executor for hard work. Bugs with no known cause after one investigation cycle, cross-module refactors, schema/auth/payment changes, local technical decisions. The session dispatches it when the work is too hard for the session's own tier. If the work turns out to be ultra hard, it returns ESCALAR with its findings; it never dispatches anything itself. Model on this platform: anthropic/claude-opus-5.
+  Strong Wizz Method executor for hard work. Bugs with no known cause after one investigation cycle, cross-module refactors, schema/auth/payment changes, local technical decisions. The session dispatches it when the work is too hard for the session's own tier. If the work turns out to be ultra hard, it returns ESCALAR with its findings; it never dispatches anything itself. Model on this platform: anthropic/claude-opus-5-5.
 mode: subagent
-model: anthropic/claude-opus-5
+model: anthropic/claude-opus-5-5
 ---
 
 You are a senior executor for the Wizz Method. You receive a brief with a goal and context for hard work, where the root cause or the path forward isn't clear yet.

package/src/modules/wizz/subagents/spec.yaml

@@ -165,10 +165,10 @@ models:
     review: gemini-3.1-pro-preview
   opencode:
     mechanical: anthropic/claude-haiku-4-5
-    standard: anthropic/claude-sonnet-5
-    strong: anthropic/claude-opus-5
+    standard: anthropic/claude-sonnet-5-5
+    strong: anthropic/claude-opus-5-5
     ultra: anthropic/claude-fable-5-1
-    review: anthropic/claude-opus-5
+    review: anthropic/claude-opus-5-5
   codex:
     mechanical: gpt-5.6-luna
     standard: gpt-5.6-terra

package/src/scripts/resolve_config.py

@@ -169,6 +169,14 @@ def main():
     else:
         output = merged
 
+    write_json_stdout(output)
+
+
+def write_json_stdout(output):
+    """Write JSON as UTF-8 so Windows cp1252 stdout can carry emoji icons."""
+    reconfigure = getattr(sys.stdout, "reconfigure", None)
+    if reconfigure is not None:
+        reconfigure(encoding="utf-8")
     sys.stdout.write(json.dumps(output, indent=2, ensure_ascii=False) + "\n")
 
 

package/src/scripts/resolve_customization.py

@@ -15,6 +15,7 @@ Requires Python 3.11+ (uses stdlib `tomllib`). No `uv`, no `pip install`,
 no virtualenv — plain `python3` is sufficient.
 
   python3 resolve_customization.py --skill /abs/path/to/skill-dir
+  python3 resolve_customization.py --skill ... --project-root /abs/project
   python3 resolve_customization.py --skill ... --key agent
   python3 resolve_customization.py --skill ... --key agent.menu
 
@@ -86,13 +87,22 @@ _SHARED_DIR_NAME = "_shared"
 
 
 def find_project_root(start: Path):
+    """Nearest ancestor holding `_wizz/`, falling back to the nearest holding `.git`.
+
+    `_wizz/` outranks `.git` at every depth: a submodule or nested repo carries
+    `.git` without being the Wizz project, so treating the two as equal stops the
+    walk short of the root that owns `_wizz/custom/` (BMAD 6.12, #2802).
+    """
+    git_root = None
     current = start.resolve()
     while True:
-        if (current / "_wizz").exists() or (current / ".git").exists():
+        if (current / "_wizz").is_dir():
             return current
+        if git_root is None and (current / ".git").exists():
+            git_root = current
         parent = current.parent
         if parent == current:
-            return None
+            return git_root
         current = parent
 
 
@@ -388,6 +398,11 @@ def main():
         "--skill", "-s", required=True,
         help="Absolute path to the skill directory (must contain customize.toml)",
     )
+    parser.add_argument(
+        "--project-root", "-p",
+        help="Absolute path to the project root (contains _wizz/). When omitted, "
+        "the root is inferred by walking up from the skill directory, then cwd.",
+    )
     parser.add_argument(
         "--key", "-k", action="append", default=[],
         help="Dotted field path to resolve (repeatable). Omit for full dump.",
@@ -403,7 +418,13 @@ def main():
     # for standalone skills invoked directly). Using cwd first is unsafe when
     # an ancestor of cwd happens to have a stray _wizz/ from another project.
     # Resolved BEFORE the base layer: the `_shared/` include fallback needs it.
-    project_root = find_project_root(skill_dir) or find_project_root(Path.cwd())
+    # An explicit --project-root wins and skips the inference entirely: a
+    # skill installed under ~ walks up to ~, and a stray ~/_wizz there would
+    # hide the real project's overrides without any error (BMAD 6.12, #2802).
+    if args.project_root:
+        project_root = Path(args.project_root).resolve()
+    else:
+        project_root = find_project_root(skill_dir) or find_project_root(Path.cwd())
 
     defaults = resolve_includes(
         load_toml(defaults_path, required=True), defaults_path.parent, project_root, skill_name

package/src/scripts/tests/test_resolve_config.py

@@ -0,0 +1,42 @@
+import json
+import os
+import subprocess
+import sys
+import tempfile
+import unittest
+from pathlib import Path
+
+
+SCRIPT = Path(__file__).resolve().parents[1] / "resolve_config.py"
+
+
+class ResolveConfigStdoutTests(unittest.TestCase):
+    def test_writes_emoji_json_when_stdout_encoding_is_cp1252(self):
+        with tempfile.TemporaryDirectory() as temp_dir:
+            root = Path(temp_dir)
+            (root / "_wizz").mkdir(parents=True)
+            (root / "_wizz" / "config.toml").write_text(
+                '[agents]\nname = "Analyst"\nicon = "📊"\n',
+                encoding="utf-8",
+            )
+
+            env = os.environ.copy()
+            env["PYTHONIOENCODING"] = "cp1252"
+            result = subprocess.run(
+                [sys.executable, str(SCRIPT), "--project-root", str(root)],
+                stdout=subprocess.PIPE,
+                stderr=subprocess.PIPE,
+                env=env,
+                check=False,
+            )
+
+            stderr = result.stderr.decode("utf-8", errors="replace")
+            self.assertEqual(result.returncode, 0, msg=stderr)
+
+            output = result.stdout.decode("utf-8")
+            self.assertIn("📊", output)
+            self.assertEqual(json.loads(output)["agents"]["icon"], "📊")
+
+
+if __name__ == "__main__":
+    unittest.main()

package/src/scripts/tests/test_resolve_customization.py

@@ -46,5 +46,50 @@ class ResolveCustomizationStdoutTests(unittest.TestCase):
             self.assertEqual(resolved["agent"]["icon"], "🧭")
 
 
+class ResolveCustomizationProjectRootTests(unittest.TestCase):
+    """--project-root explícito e `_wizz/` acima de `.git` (BMAD 6.12, #2802)."""
+
+    def _skill(self, parent: Path) -> Path:
+        skill_dir = parent / "demo-skill"
+        skill_dir.mkdir(parents=True)
+        (skill_dir / "customize.toml").write_text('[workflow]\nmode = "base"\n', encoding="utf-8")
+        return skill_dir
+
+    def _override(self, root: Path) -> None:
+        custom = root / "_wizz" / "custom"
+        custom.mkdir(parents=True)
+        (custom / "demo-skill.toml").write_text('[workflow]\nmode = "team"\n', encoding="utf-8")
+
+    def _run(self, *args, cwd=None):
+        result = subprocess.run(
+            [sys.executable, str(SCRIPT), *args, "--key", "workflow"],
+            capture_output=True, text=True, cwd=cwd, check=False,
+        )
+        self.assertEqual(result.returncode, 0, msg=result.stderr)
+        return json.loads(result.stdout)["workflow"]
+
+    def test_explicit_project_root_wins_over_inference(self):
+        with tempfile.TemporaryDirectory() as tmp:
+            project = Path(tmp) / "project"
+            self._override(project)
+            # Skill fora do projeto: a inferência nunca chegaria em project/.
+            skill_dir = self._skill(Path(tmp) / "elsewhere")
+            self.assertEqual(self._run("--skill", str(skill_dir), cwd=tmp)["mode"], "base")
+            self.assertEqual(
+                self._run("--skill", str(skill_dir), "--project-root", str(project), cwd=tmp)["mode"],
+                "team",
+            )
+
+    def test_wizz_folder_outranks_nested_git(self):
+        with tempfile.TemporaryDirectory() as tmp:
+            project = Path(tmp) / "project"
+            self._override(project)
+            # Submódulo/repo aninhado: tem .git mas não é o projeto Wizz.
+            nested = project / "vendor" / "sub"
+            (nested / ".git").mkdir(parents=True)
+            skill_dir = self._skill(nested / "skills")
+            self.assertEqual(self._run("--skill", str(skill_dir), cwd=tmp)["mode"], "team")
+
+
 if __name__ == "__main__":
     unittest.main()

package/src/skills-lib/_shared/complexity-signal.md

@@ -36,7 +36,7 @@ Written as bare labels, the 3 factors above were true of almost any request, and
 
 **And the counterpart has one exception: a single entry already delimits the scope.** If the whole outcome being asked for fits the `when:` of ONE catalogue entry, and what leaves at the end is that entry's own deliverable — a plan, a recommendation, an audit — then the scope is not open, the catalogue delimited it, and the request goes to that entry's area. "A plan to reduce churn" is `wizz-churn-prevention`; "I want ChatGPT and Perplexity to cite us" is `wizz-ai-seo`; "what to check before going live" is `site-launch-kit`. It stops being the exception the moment delivering the outcome means changing what other areas own: "improve the signup conversion rate" ends up in copy, UI and code, so it comes back to the maestro through the area clause. Ask which single entry would deliver it whole — if it takes two, the scope really is open. (Owner's decision, 2026-09-18.)
 
-**Changing the product's code is `dev`, even when the subject is visual.** "Adjust the secondary button's colour", "fix the mobile spacing": the delivery is a commit, so it is the dev area — `designer` decides what the look should be, it does not ship the change. Ask which artifact leaves at the end: a file in the repo → dev; a decision, a spec or a piece of art → the area that owns it.
+**Changing the product's code is `dev`, even when the subject is visual.** "Adjust the secondary button's colour", "fix the mobile spacing": the delivery is a commit, so it is the dev area — `designer` decides what the look should be, it does not ship the change. Ask which artifact leaves at the end: a file in the repo → dev; a decision, a spec or a piece of art → the area that owns it. **Exception: new or rebuilt screens.** When the request asks to BUILD screens in code (a new app, page, dashboard or panel, or a whole screen rebuilt in the product), the visual decision has not been made yet, so `designer` comes first and the sequence is design → dev (2 areas → maestro): the designer runs its research gate before any screen is coded. A tweak to an existing screen (a price, a label, a spacing) stays dev, and redesigning a section with no build asked for (a hero, a card) stays designer.
 
 **What `rel` drags counts as an extra area when the related capability shapes the SAME deliverable.** Writing the copy of a sales page without the offer and without the conversion structure delivers half a page: offer, copy and conversion are the same artifact, so that is 2 areas → maestro. What does NOT count is an adjacent capability that would produce a **different** artifact: a plain text post for LinkedIn does not need video capture just because the social content skill declares `before: [get-brolls]` — the b-roll would be another deliverable, not part of this one. `pairs_with` alone never escalates: it is neighbourhood, not dependency. The question to ask about each edge is "would the thing I am about to hand over be incomplete without this?", not "is this related?".
 

package/src/skills-lib/ctc-align/SKILL.md

@@ -20,7 +20,7 @@ exact text and only looks for where each word is: precision within tens of ms.
 
     mkdir -p tools/ctc-align && cd tools/ctc-align
     uv venv --python 3.12 .venv
-    uv pip install --python .venv/bin/python "git+https://github.com/MahmoudAshraf97/ctc-forced-aligner.git"
+    uv pip install --python .venv/bin/python "git+https://github.com/MahmoudAshraf97/ctc-forced-aligner.git@64293cc6d711e57666c4a8b098e9fd93b381fd88"
 
 Copy this skill's `scripts/align.py` to `tools/ctc-align/align.py`.
 Runs on CPU (Mac ARM ok, no CUDA needed). First use downloads the MMS model (~1GB).

package/src/skills-lib/wizz-agent-browser/SKILL.md

@@ -119,6 +119,9 @@ agent-browser open http://localhost:3000
 | `-i`               | Snapshot: interactive elements only |
 | `-c`               | Snapshot: compact output            |
 | `-d <n>`           | Snapshot: limit tree depth          |
+| `--delta`          | Snapshot: full state once, then only what changed (fewer tokens) |
+| `--if-changed`     | Screenshot: skip when the page did not change |
+| `--no-webmcp`      | Turn off WebMCP page tools (on by default since 0.36) |
 
 ## Debugging
 
@@ -137,3 +140,5 @@ agent-browser eval "document.title"                 # Run JS
 3. **Wait when needed** - Use `wait <ms>` or `wait <selector>` after actions that trigger loading
 4. **Sessions for auth** - Use named sessions to persist login state
 5. **Headed for debugging** - Use `--headed` when things aren't working as expected
+6. **Repeat checks cheaply** - `snapshot -i --delta` and `screenshot --if-changed` in a verify loop
+7. **WebMCP off on third-party sites** - Since 0.36 a page can announce its own tools into your context. Launch with `--no-webmcp` unless the site is the project's own app; never invoke a page tool the user did not ask for

package/src/skills-lib/wizz-design-needs/SKILL.md

@@ -25,7 +25,7 @@ Output: a `needs` block in `design-state.yaml`. Nothing else. This skill never o
 3. **Decompose.** Surfaces → sections → components → behaviours. Procedure in [decomposicao](references/decomposicao.md).
 4. **Derive the needs** with the four rules and the signal table in [derivacao](references/derivacao.md). This is where needs are both created and forbidden.
 5. **Run the gap analysis** ([gap-analysis](references/gap-analysis.md)): project inventory → local cache → needs already satisfied on another surface. What survives gets a query, a source budget and a floor. What does not survive is closed with `status: dropped` and a reason.
-6. **Write `design-state.yaml`** in the shape of [design-state](references/design-state.md), and hand off.
+6. **Write `design-state.yaml`** in the shape of [design-state](references/design-state.md), always at `{output_folder}/design-state.yaml`, and hand off. A brief that restricts writes to another folder (e.g. "only write in `_design/`") governs deliverables, not the map: the miners look for the map in `{output_folder}`.
 
 ## Output format