chore(bmad): migrate 80_bmad/base from 6.0.4 to 6.9 + port customizations to TOML overrides

Migration des modules via l'installer officiel (Quick update, en place) :
- core/bmm 6.0.4 -> 6.9.0
- tea 1.5.3 -> 1.19.0
- cis 0.1.8 -> 0.2.1

Portage des customisations Lead_tech vers le nouveau mécanisme d'overrides
(_bmad/custom/<skill>.toml, couche "team" résolue par resolve_customization.py) :
- 6 agents directs (analyst, architect, dev, pm, tech-writer, ux-designer)
- module tea
- workflows: dev-story, create-story, code-review, quick-dev, qa-generate-e2e-tests
- agents disparus en 6.9 reportés vers leurs workflows hôtes
  (QA -> code-review, SM -> create-story, quick-flow-solo-dev -> quick-dev)
- règle de capitalisation 95_a_capitaliser factorisée dans
  _bmad/custom/leadtech-capitalisation.md (référencée via persistent_facts)

Nettoyage du legacy 6.0.4 :
- suppression des 17 *.customize.yaml (non lus par 6.9)
- suppression des .bak générés par l'installer (contenu porté en .toml)
- suppression de 17 skills orphelins dans .agents/skills (anciens noms, .agents/.claude réalignés 66=66)
- suppression des coquilles de workflows disparus

Tous les overrides validés par le resolver officiel (12/12 JSON valide,
base préservée + ajouts Lead_tech). Le cœur (couche customize.toml) n'est plus modifié,
donc les updates 6.x futurs ne pourront plus écraser ces customisations.

Note env: resolve_customization.py exige Python >=3.11 (uv installé, python3 -> 3.12.13).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

80_bmad/base/.agents/skills/bmad-review-edge-case-hunter/SKILL.md

@@ -1,10 +1,67 @@
 ---
 name: bmad-review-edge-case-hunter
-description: Execute review-edge-case-hunter
+description: 'Walk every branching path and boundary condition in content, report only unhandled edge cases. Orthogonal to adversarial review - method-driven not attitude-driven. Use when you need exhaustive edge-case analysis of code, specs, or diffs.'
 ---
 
-# review-edge-case-hunter
+# Edge Case Hunter Review
 
-Read the entire task file at: {project-root}/_bmad/core/tasks/review-edge-case-hunter.xml
+**Goal:** You are a pure path tracer. Never comment on whether code is good or bad; only list missing handling.
+When a diff is provided, scan only the diff hunks and list boundaries that are directly reachable from the changed lines and lack an explicit guard in the diff.
+When no diff is provided (full file or function), treat the entire provided content as the scope.
+Ignore the rest of the codebase unless the provided content explicitly references external functions.
 
-Follow all instructions in the task file exactly as written.
+**Inputs:**
+- **content** — Content to review: diff, full file, or function
+- **also_consider** (optional) — Areas to keep in mind during review alongside normal edge-case analysis
+
+**MANDATORY: Execute steps in the Execution section IN EXACT ORDER. DO NOT skip steps or change the sequence. When a halt condition triggers, follow its specific instruction exactly. Each action within a step is a REQUIRED action to complete that step.**
+
+**Your method is exhaustive path enumeration — mechanically walk every branch, not hunt by intuition. Report ONLY paths and conditions that lack handling — discard handled ones silently. Do NOT editorialize or add filler — findings only.**
+
+
+## EXECUTION
+
+### Step 1: Receive Content
+
+- Load the content to review strictly from provided input
+- If content is empty, or cannot be decoded as text, return `[{"location":"N/A","trigger_condition":"Input empty or undecodable","guard_snippet":"Provide valid content to review","potential_consequence":"Review skipped — no analysis performed"}]` and stop
+- Identify content type (diff, full file, or function) to determine scope rules
+
+### Step 2: Exhaustive Path Analysis
+
+**Walk every branching path and boundary condition within scope — report only unhandled ones.**
+
+- If `also_consider` input was provided, incorporate those areas into the analysis
+- Walk all branching paths: control flow (conditionals, loops, error handlers, early returns) and domain boundaries (where values, states, or conditions transition). Derive the relevant edge classes from the content itself — don't rely on a fixed checklist. Examples: missing else/default, unguarded inputs, off-by-one loops, arithmetic overflow, implicit type coercion, race conditions, timeout gaps
+- For each path: determine whether the content handles it
+- Collect only the unhandled paths as findings — discard handled ones silently
+
+### Step 3: Validate Completeness
+
+- Revisit every edge class from Step 2 — e.g., missing else/default, null/empty inputs, off-by-one loops, arithmetic overflow, implicit type coercion, race conditions, timeout gaps
+- Add any newly found unhandled paths to findings; discard confirmed-handled ones
+
+### Step 4: Present Findings
+
+Output findings as a JSON array following the Output Format specification exactly.
+
+
+## OUTPUT FORMAT
+
+Return ONLY a valid JSON array of objects. Each object must contain exactly these four fields and nothing else:
+
+```json
+[{
+  "location": "file:start-end (or file:line when single line, or file:hunk when exact line unavailable)",
+  "trigger_condition": "one-line description (max 15 words)",
+  "guard_snippet": "minimal code sketch that closes the gap (single-line escaped string, no raw newlines or unescaped quotes)",
+  "potential_consequence": "what could actually go wrong (max 15 words)"
+}]
+```
+
+No extra text, no explanations, no markdown wrapping. An empty array `[]` is valid when no unhandled paths are found.
+
+
+## HALT CONDITIONS
+
+- If content is empty or cannot be decoded as text, return `[{"location":"N/A","trigger_condition":"Input empty or undecodable","guard_snippet":"Provide valid content to review","potential_consequence":"Review skipped — no analysis performed"}]` and stop