azclaude-copilot 0.5.8 → 0.5.9

package/.claude-plugin/marketplace.json

@@ -9,7 +9,7 @@
     {
       "name": "azclaude",
       "description": "AZCLAUDE is a complete AI coding environment for Claude Code. It installs 39 commands, 10 auto-invoked skills, 15 specialized agents, 4 hooks, and a persistent memory system — in one command.\n\nKey features:\n• Memory across sessions — goals.md + checkpoints injected automatically before every session\n• Self-improving loop — /reflect fixes stale CLAUDE.md rules, /reflexes learns from tool-use patterns, /evolve creates agents from git evidence\n• Autonomous copilot mode — /copilot runs a three-tier team (orchestrator → problem-architect → milestone-builder) across sessions until the product ships\n• Spec-driven workflow — /constitute writes project rules, /spec writes structured ACs, /analyze detects plan drift and ghost milestones, /blueprint traces every milestone to a spec\n• Security layer — 111-rule environment scan (/sentinel), pre-write secret blocking, pre-ship credential audit\n• Progressive levels 0–10 — start with CLAUDE.md, grow into multi-agent pipelines and self-evolving environments\n• Zero dependencies — no npm packages, no external APIs, no vector databases. Plain markdown files and Claude Code's native architecture.\n• Smart install — npx azclaude-copilot@latest auto-detects first install vs upgrade vs verify. Context-aware onboarding shows the right next command for your project state.\n\nExample use cases:\n• /setup — scan an existing project, detect stack + domain + scale, fill CLAUDE.md, generate project-specific skills and agents automatically\n• /copilot \"Build a compliance SaaS with trilingual support\" — walk away, come back to working code across multiple sessions\n• /sentinel — run a scored security audit (0–100, grade A–F) across hooks, permissions, MCP servers, agent configs, and secrets\n• /evolve — detect gaps in the environment, generate new skills and agents from git co-change evidence, report score delta (e.g. 42/100 → 68/100)\n• /constitute — write your project's constitution (non-negotiables, architectural commitments, definition of done) — gates all future AI actions\n• /analyze — cross-artifact consistency check: ghost milestones, spec vs. code drift, unplanned commits\n• /reflect — find stale, missing, or contradicting rules in CLAUDE.md and propose exact fixes\n• /debate \"REST vs GraphQL for this project\" — adversarial evidence-based decision with order-independent scoring, logged to decisions.md",
-      "version": "0.5.8",
+      "version": "0.5.9",
       "source": {
         "source": "github",
         "repo": "haytamAroui/AZ-CLAUDE-COPILOT",

package/.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "azclaude",
-  "version": "0.5.8",
+  "version": "0.5.9",
   "description": "AZCLAUDE is a complete AI coding environment for Claude Code. It installs 39 commands, 10 auto-invoked skills, 15 specialized agents, 4 hooks, and a persistent memory system — in one command.\n\nKey features:\n• Memory across sessions — goals.md + checkpoints injected automatically before every session\n• Self-improving loop — /reflect fixes stale CLAUDE.md rules, /reflexes learns from tool-use patterns, /evolve creates agents from git evidence\n• Autonomous copilot mode — /copilot runs a three-tier team (orchestrator → problem-architect → milestone-builder) across sessions until the product ships\n• Spec-driven workflow — /constitute writes project rules, /spec writes structured ACs, /analyze detects plan drift and ghost milestones, /blueprint traces every milestone to a spec\n• Security layer — 111-rule environment scan (/sentinel), pre-write secret blocking, pre-ship credential audit\n• Progressive levels 0–10 — start with CLAUDE.md, grow into multi-agent pipelines and self-evolving environments\n• Zero dependencies — no npm packages, no external APIs, no vector databases. Plain markdown files and Claude Code's native architecture.\n• Smart install — npx azclaude-copilot@latest auto-detects first install vs upgrade vs verify. Context-aware onboarding shows the right next command for your project state.\n\nExample use cases:\n• /setup — scan an existing project, detect stack + domain + scale, fill CLAUDE.md, generate project-specific skills and agents automatically\n• /copilot \"Build a compliance SaaS with trilingual support\" — walk away, come back to working code across multiple sessions\n• /sentinel — run a scored security audit (0–100, grade A–F) across hooks, permissions, MCP servers, agent configs, and secrets\n• /evolve — detect gaps in the environment, generate new skills and agents from git co-change evidence, report score delta (e.g. 42/100 → 68/100)\n• /constitute — write your project's constitution (non-negotiables, architectural commitments, definition of done) — gates all future AI actions\n• /analyze — cross-artifact consistency check: ghost milestones, spec vs. code drift, unplanned commits\n• /reflect — find stale, missing, or contradicting rules in CLAUDE.md and propose exact fixes\n• /debate \"REST vs GraphQL for this project\" — adversarial evidence-based decision with order-independent scoring, logged to decisions.md",
   "author": {
     "name": "haytamAroui",

package/README.md

@@ -624,11 +624,11 @@ AZCLAUDE is a lazy-loaded environment of 48 capability modules. It only loads wh
 
 ## Verified
 
-1805 tests. Every template, command, capability, agent, hook, and CLI feature verified.
+1810 tests. Every template, command, capability, agent, hook, and CLI feature verified.
 
 ```bash
 bash tests/test-features.sh
-# Results: 1805 passed, 0 failed, 1805 total
+# Results: 1810 passed, 0 failed, 1810 total
 ```
 
 ---

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "azclaude-copilot",
-  "version": "0.5.8",
+  "version": "0.5.9",
   "description": "AI coding environment — 39 commands, 10 skills, 15 agents, memory, reflexes, evolution. Install: npx azclaude-copilot@latest, then open Claude Code.",
   "bin": {
     "azclaude": "bin/cli.js",

package/templates/capabilities/shared/parallel-coordination.md

@@ -166,6 +166,72 @@ These rules are injected by orchestrator into every parallel milestone-builder p
 
 ---
 
+## Proven Patterns — 3-Layer Conflict Prevention
+
+These patterns come from a real production run: 16 agents, 360 tests, zero merge conflicts.
+
+### Layer 1: Wave 0 — Bottleneck Files First (Sequential)
+
+Identify files that multiple milestones need to modify (shared models, core config, base schemas).
+**Do NOT parallelize these.** Instead, create a Wave 0 that runs sequentially before any parallel agents:
+
+```
+Wave 0 (sequential, orchestrator or single agent):
+  models.py      → ALL new fields added at once
+  versioning.py  → version bump
+  shared_config  → all schema changes
+
+Result: every subsequent agent finds shared dependencies already in place.
+```
+
+**Rule: SHARED DEPENDENCY → Wave 0 (sequential, do it first)**
+
+### Layer 2: Directory-Level File Isolation
+
+Design each parallel wave so agents own completely disjoint files:
+
+```
+Wave 1 (3 agents, zero file overlap):
+  Agent A: annex_1_rules.py, rules.py, conformity_path.py, test_annex_1.py
+  Agent B: gpai_rules.py, test_gpai_copyright.py
+  Agent C: test_fria_trigger.py, test_national_law_router.py (NEW files only)
+```
+
+**Test-only agents are always safe in parallel** — they create new test files and read (never write) engine code.
+
+**Rule: TEST-ONLY agents → always safe in any wave**
+
+### Layer 3: Same File, Different Sections
+
+When two agents must touch the same file, allow it **only if edits are 100+ lines apart**:
+
+```
+┌───────┬────────────────────────────────┬────────────┐
+│ Agent │ Section in rules.py            │ Line range │
+├───────┼────────────────────────────────┼────────────┤
+│ M2A   │ After result construction      │ ~line 392  │
+│ M2C   │ STEP 13 deadline unpacking     │ ~line 273  │
+└───────┴────────────────────────────────┴────────────┘
+```
+
+Git merges these cleanly because they don't touch overlapping context (3-line hunk window).
+
+**Rule: SAME FILE, DIFFERENT SECTIONS (100+ lines apart) → allowed in parallel**
+**Rule: SAME FILE, SAME SECTION → serialize into different waves**
+
+### Decision Table
+
+| Conflict type | Resolution |
+|---------------|-----------|
+| Multiple milestones need same model/schema file | Wave 0: one agent fixes it sequentially before all others |
+| Agents write different files entirely | Safe for parallel — standard worktree isolation |
+| Agents write same file, edits 100+ lines apart | Allowed in parallel — git auto-merges cleanly |
+| Agents write same file, edits < 100 lines apart | Serialize into different waves |
+| Agent only creates new test files | Always safe in any wave — no write conflicts possible |
+| Agent changes a function's return type | Must also fix all callers in the same agent's scope |
+
+---
+
 ## Wave State File — Context Loss Protection
 
 During parallel execution, the orchestrator writes `.claude/parallel-wave-state.md` **before dispatching any agents**. This file survives context compaction and enables session resume.