@zik000/archai 0.2.3 → 0.2.4

package/README.md

@@ -45,7 +45,7 @@ And tell it what to build:
 After reviewing and approving the spec:
 
 ```
-> Use maestro-agent for: the prepared task in .claude/state/prepared-task.md
+> Use maestro-agent for: the prepared task in .task/inbox/Task-AUTH-001.md
 ```
 
 The agent system takes over — plans the work, waits for your approval, implements it, runs tests, and commits.
@@ -76,7 +76,7 @@ For vague or complex tasks, structure them first:
 > Use task-prep for: add user authentication with JWT
 ```
 
-The agent gathers project context, asks targeted clarifying questions, and produces a structured spec. After you approve, it saves to `.claude/state/prepared-task.md`.
+The agent gathers project context, asks targeted clarifying questions, and produces a structured spec. After you approve, it saves to `.task/inbox/` with a descriptive name like `Task-AUTH-001.md`.
 
 ### Step 1: Define Your Task
 
@@ -210,7 +210,7 @@ your-project/
 ├── .claude/
 │   ├── agents/          # Core + specialist agent definitions
 │   ├── plans/           # Approved implementation plans
-│   ├── state/           # Working state (gitignored, includes prepared-task.md)
+│   ├── state/           # Working state (gitignored)
 │   └── version.json     # Version tracking for smart updates
 ├── .knowledge/          # Persistent knowledge base (decisions, constraints, patterns, learnings)
 ├── .tasks/              # Task inbox, epics, review, done

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@zik000/archai",
-  "version": "0.2.3",
+  "version": "0.2.4",
   "description": "Multi-agent AI development workflow setup for any project",
   "keywords": [
     "claude",

package/templates/core-agents/maestro-agent.md

@@ -50,7 +50,7 @@ git branch --show-current
 
 ## Step 0: Create Task Anchor
 
-**Check for prepared task**: If `.claude/state/prepared-task.md` exists (created by `task-prep`), use it as the basis:
+**Check for prepared task**: If a task spec exists in `.task/inbox/` (created by `task-prep`), use the one specified by the user (or the most recent) as the basis:
 - Objective → Original Request
 - Acceptance Criteria → Acceptance Criteria
 - Dependencies + Business Context → Critical Constraints

package/templates/core-agents/task-prep.md

@@ -32,7 +32,7 @@ You are the FIRST agent in the pipeline. You sit BEFORE the execution loop. Your
 - Read `.knowledge/context/project-description.md`
 - Read `archai.config.md` (if exists)
 - Run `git status` and `git log --oneline -10`
-- Check `.claude/state/` for in-progress work
+- Check `.task/inbox/` for existing tasks/epics (to determine next index number)
 
 ### Step 2: Classify Input
 
@@ -89,13 +89,39 @@ For any business rules, scope decisions, or user preferences gathered during ref
 
 ### Step 6: Structure Output
 
-Write the standardized task spec to `.claude/state/prepared-task.md`:
+#### File Naming Convention
+
+Output goes to `.task/inbox/` using this naming scheme:
+
+```
+[Task|Epic]-{SLUG}-{INDEX}.md
+```
+
+- **Task or Epic**: Based on classification from Step 2
+- **SLUG**: 4-6 uppercase letters identifying the area (e.g., `AUTH`, `AGENT`, `ROUTE`, `DBMIG`, `UIPNL`)
+- **INDEX**: 3-digit zero-padded number, auto-incremented per slug
+
+**Index rules:**
+1. List existing files in `.task/inbox/` matching the same slug pattern (e.g., `Task-AUTH-*.md`)
+2. If none exist, start at `001`
+3. If matches exist, take the highest index and increment by 1
+
+**Examples:**
+- First auth task: `Task-AUTH-001.md`
+- Second auth task: `Task-AUTH-002.md`
+- An epic for refactoring agents: `Epic-AGENT-001.md`
+- A task for UI panels: `Task-UIPNL-001.md`
+
+Create the `.task/inbox/` directory if it doesn't exist.
+
+#### Spec Template
+
+Write the standardized task spec:
 
 ```markdown
 ## Task: [clear imperative title]
-**ID**: task-{YYYYMMDD}-{HHMMSS}
-**Type**: Task
-**Parent Epic**: (none, or epic ID if decomposed)
+**Type**: Task | Epic
+**Parent Epic**: (none, or epic filename if decomposed)
 
 ### Context
 [Auto-gathered project context from Step 3]
@@ -134,10 +160,10 @@ Show the structured spec to the user. Wait for:
 - **MODIFY** → Return to Step 4 for another refinement turn (within the 3-turn limit).
 - **REJECT** → Discard and start over.
 
-After approval, tell the user:
+After approval, tell the user (using the actual filename):
 ```
-Spec saved to .claude/state/prepared-task.md
-Next: Use maestro-agent for: the prepared task in .claude/state/prepared-task.md
+Spec saved to .task/inbox/{filename}.md
+Next: Use maestro-agent for: the prepared task in .task/inbox/{filename}.md
 ```
 
 ---
@@ -153,7 +179,7 @@ Next: Use maestro-agent for: the prepared task in .claude/state/prepared-task.md
 
 ## Output
 
-**Primary output**: `.claude/state/prepared-task.md`
+**Primary output**: `.task/inbox/[Task|Epic]-{SLUG}-{INDEX}.md`
 **Secondary output**: Knowledge signals appended to `.claude/state/knowledge_signals.md`
 
 ## Usage
@@ -161,7 +187,8 @@ Next: Use maestro-agent for: the prepared task in .claude/state/prepared-task.md
 ```
 # Prepare a task spec from a vague request
 Use task-prep for: add user authentication with JWT
+# → creates .task/inbox/Task-AUTH-001.md
 
 # After reviewing and approving the spec:
-Use maestro-agent for: the prepared task in .claude/state/prepared-task.md
+Use maestro-agent for: the prepared task in .task/inbox/Task-AUTH-001.md
 ```