chore: unify and centralize agent configuration in .agent/

1 files changed, 62 insertions, 0 deletions

diff --git a/.agent/config.md b/.agent/config.md
new file mode 100644
index 0000000..45ead3b
--- /dev/null
+++ b/.agent/config.md
@@ -0,0 +1,62 @@
+# Agent Configuration & Master Rulebook (.agent/config.md)
+
+This is the primary source of truth for all AI agents working on **Doot**. These instructions take absolute precedence over general defaults.
+
+## 1. Project Directory Structure (.agent/)
+
+| File | Purpose |
+|------|---------|
+| `config.md` | **Main Entry Point** — Rules, workflows, and core mandates. |
+| `worklog.md` | **Session State** — Current focus, recently completed, and next steps. |
+| `design.md` | **Architecture** — High-level design, database schema, and components. |
+| `coding_standards.md` | **Technical Standards** — Go/HTMX idioms, testing, and security. |
+| `ux_philosophy.md` | **UX Principles** — Interaction models, palette, and mobile-first design. |
+| `narrative.md` | **Background** — Historical context and evolution of the project. |
+
+## 2. Core Mandates
+
+### ULTRA-STRICT ROOT SAFETY PROTOCOL
+1.  **Inquiry-Only Default:** Treat every message as research/analysis unless it is an explicit, imperative command (Directive).
+2.  **Zero Unsolicited Implementation:** Never modify files, directories, or processes based on assumptions.
+3.  **Interactive Strategy Checkpoint:** Research first, present a strategy, and **WAIT** for an explicit "GO" before any system-changing tool call.
+4.  **No Destructive Assumptions:** Always verify state (`ps`, `ls`, `git status`) before proposing actions.
+5.  **Root-Awareness:** Prioritize system integrity and user confirmation over proactiveness.
+
+### Task Management
+- **Worklog:** Update `.agent/worklog.md` at the start and end of every session.
+- **Claudomator:** Use `claudomator create "Name" --instructions "Goals"` for new tasks. Use `claudomator finish <id>` when done.
+
+### Living Documentation Mandate
+1.  **Continuous Capture:** Agents MUST proactively update the files in `.agent/` (Design, UX, Standards, Mission, Preferences) as new decisions, patterns, or user preferences are revealed.
+2.  **No Stale Instructions:** If a workflow or technical standard evolves, the agent is responsible for reflecting that change in the Master Rulebook immediately.
+3.  **Worklog Integrity:** The `.agent/worklog.md` must be updated at the start and end of EVERY session to ensure continuity.
+
+## 3. Workflows
+
+### Research -> Strategy -> Execution
+1.  **Research:** Map codebase, validate assumptions, reproduce bugs.
+2.  **Strategy:** Share a summary. Wait for approval if significant.
+3.  **Execution (Plan-Act-Validate):**
+    - **Plan:** Define implementation and testing.
+    - **Act:** Apply surgical, idiomatic changes.
+    - **Validate:** Run `go test ./...` and `npm run build`.
+
+## 4. Agent Context API (Snapshots)
+
+The project includes an internal API for agents to understand the current user's task and meal context.
+
+- **Request Access:** `POST /agent/auth/request` (returns `request_token`).
+- **Poll Status:** `GET /agent/auth/poll?token=<request_token>` (awaits browser approval).
+- **Get Context:** `GET /agent/context` (requires Bearer token).
+- **Snapshot Endpoint:** `GET /api/claude/snapshot` (legacy, see `internal/handlers/agent.go` for new unified flow).
+
+## 5. Essential Commands
+
+| Command | Action |
+|---------|--------|
+| `go run cmd/dashboard/main.go` | Start application |
+| `go test ./...` | Run all tests |
+| `./scripts/deploy` | Deploy to production |
+| `./scripts/logs` | View production logs |
+| `./scripts/bugs` | List open production bugs |
+| `./scripts/resolve-bug <id>` | Resolve a production bug |