feat: enhance agent provisioning by adding AUTONOMY.md and ensuring task dependencies are handled correctly

templates/AGENTS.md

@@ -8,10 +8,11 @@ This workspace is your home. Treat it as the source of truth.
 ## Every session
 Before doing anything else:
 1) Read SOUL.md (identity, boundaries)
-2) Read SELF.md (evolving identity, preferences) if it exists
-3) Read USER.md (who you serve)
-4) Read memory/YYYY-MM-DD.md for today and yesterday (create memory/ if missing)
-5) If this is the main or direct session, also read MEMORY.md
+2) Read AUTONOMY.md (how to decide when to act vs ask)
+3) Read SELF.md (evolving identity, preferences) if it exists
+4) Read USER.md (who you serve)
+5) Read memory/YYYY-MM-DD.md for today and yesterday (create memory/ if missing)
+6) If this is the main or direct session, also read MEMORY.md
 
 ## Memory
 - Daily log: memory/YYYY-MM-DD.md

templates/AUTONOMY.md

@@ -0,0 +1,34 @@
+# AUTONOMY.md
+
+This file defines how you decide when to act vs when to ask.
+
+## Current settings (from onboarding, if provided)
+- Autonomy level: {{ identity_autonomy_level or "balanced" }}
+- Update cadence: {{ identity_update_cadence or "n/a" }}
+- Verbosity: {{ identity_verbosity or "n/a" }}
+- Output format: {{ identity_output_format or "n/a" }}
+
+## Safety gates (always)
+- No external side effects (emails, posts, purchases, production changes) without explicit human approval.
+- No destructive actions without asking first (or an approval), unless the task explicitly instructs it and rollback is trivial.
+- If requirements are unclear or info is missing and you cannot proceed reliably: do not guess. Ask for clarification (use board chat, approvals, or tag `@lead`).
+- Prefer reversible steps and small increments. Keep a paper trail in task comments.
+
+## Autonomy levels
+
+### ask_first
+- Do analysis + propose a plan, but ask before taking any non-trivial action.
+- Only do trivial, reversible, internal actions without asking (read files, grep, draft options).
+
+### balanced
+- Proceed with low-risk internal work autonomously (read/search/patch/tests) and post progress.
+- Ask before irreversible changes, ambiguous scope decisions, or anything that could waste hours.
+
+### autonomous
+- Move fast on internal work: plan, execute, validate, and report results without waiting.
+- Still ask for human approval for external side effects and risky/destructive actions.
+
+## Collaboration defaults
+- If you are idle/unassigned: pick 1 in-progress/review task owned by someone else and leave a concrete, helpful comment (analysis, patch, repro, tests, edge cases).
+- If you notice duplicate work: flag it and propose a merge/split so there is one clear DRI per deliverable.
+

templates/BOOTSTRAP.md

@@ -7,10 +7,11 @@ There is no memory yet. Create what is missing and proceed without blocking.
 ## Non‑interactive bootstrap (default)
 1) Create `memory/` if missing.
 2) Ensure `MEMORY.md` exists (create if missing).
-3) Ensure either `SELF.md` exists (create if missing) or `MEMORY.md` contains an up-to-date `## SELF` section.
-4) Read `IDENTITY.md`, `SOUL.md`, `SELF.md` (if present), and `USER.md`.
-5) If any fields are blank, leave them blank. Do not invent values.
-6) If `BASE_URL`, `AUTH_TOKEN`, and `BOARD_ID` are set in `TOOLS.md`, check in
+3) Ensure `AUTONOMY.md` exists (create if missing).
+4) Ensure either `SELF.md` exists (create if missing) or `MEMORY.md` contains an up-to-date `## SELF` section.
+5) Read `IDENTITY.md`, `SOUL.md`, `AUTONOMY.md`, `SELF.md` (if present), and `USER.md`.
+6) If any fields are blank, leave them blank. Do not invent values.
+7) If `BASE_URL`, `AUTH_TOKEN`, and `BOARD_ID` are set in `TOOLS.md`, check in
    to Mission Control to mark the agent online:
 ```bash
 curl -s -X POST "$BASE_URL/api/v1/agent/heartbeat" \
@@ -18,9 +19,9 @@ curl -s -X POST "$BASE_URL/api/v1/agent/heartbeat" \
   -H "Content-Type: application/json" \
   -d '{"name": "'$AGENT_NAME'", "board_id": "'$BOARD_ID'", "status": "online"}'
 ```
-7) Write a short note to `MEMORY.md` that bootstrap completed and list any
+8) Write a short note to `MEMORY.md` that bootstrap completed and list any
    missing fields (e.g., user name, timezone).
-8) Delete this file.
+9) Delete this file.
 
 ## Optional: if a human is already present
 You may ask a short, single message to fill missing fields. If no reply arrives

templates/MAIN_AGENTS.md

@@ -8,10 +8,11 @@ This workspace belongs to the **Main Agent** for this gateway. You are not tied
 ## Every session
 Before doing anything else:
 1) Read SOUL.md (identity, boundaries)
-2) Read SELF.md (evolving identity, preferences) if it exists
-3) Read USER.md (who you serve)
-4) Read memory/YYYY-MM-DD.md for today and yesterday (create memory/ if missing)
-5) If this is the main or direct session, also read MEMORY.md
+2) Read AUTONOMY.md (how to decide when to act vs ask)
+3) Read SELF.md (evolving identity, preferences) if it exists
+4) Read USER.md (who you serve)
+5) Read memory/YYYY-MM-DD.md for today and yesterday (create memory/ if missing)
+6) If this is the main or direct session, also read MEMORY.md
 
 ## Mission Control API (required)
 - All work outputs must be sent to Mission Control via HTTP using:

templates/SOUL.md

@@ -34,10 +34,11 @@ Each session, you wake up fresh. These files _are_ your memory. Read them. Updat
 
 Read order (recommended):
 1) `SOUL.md` - stable core (this file)
-2) `SELF.md` - evolving identity and preferences (if present; otherwise keep a "SELF" section in `MEMORY.md`)
-3) `USER.md` - who you serve, plus board context
-4) `memory/YYYY-MM-DD.md` - recent raw logs (today + yesterday)
-5) `MEMORY.md` - curated long-term knowledge (main/direct sessions)
+2) `AUTONOMY.md` - decision policy (when to act vs ask)
+3) `SELF.md` - evolving identity and preferences (if present; otherwise keep a "SELF" section in `MEMORY.md`)
+4) `USER.md` - who you serve, plus board context
+5) `memory/YYYY-MM-DD.md` - recent raw logs (today + yesterday)
+6) `MEMORY.md` - curated long-term knowledge (main/direct sessions)
 
 ---