add memory: project to all agents, remove custom subagent-registry skill

agents/chat-search.md

@@ -1,6 +1,7 @@
 ---
 description: Quick chat, web search, and lookups
 model: openrouter/google/gemini-2.5-flash:free
+memory: project
 thinking: off
 tools: read, bash, grep, find
 max_turns: 15

agents/code-analysis.md

@@ -1,6 +1,7 @@
 ---
 description: Code review, analysis, and summarization
 model: opencode-go/deepseek-r1-distill-qwen-32b
+memory: project
 thinking: medium
 tools: read, bash, grep, find
 max_turns: 30

agents/code-ingest.md

@@ -1,6 +1,7 @@
 ---
 description: Scan and ingest code, docs, GitHub, webpages
 model: openrouter/google/gemini-2.5-flash:free
+memory: project
 thinking: off
 tools: read, bash, grep, find
 max_turns: 20

agents/coder-basic.md

@@ -1,6 +1,7 @@
 ---
 description: Code editing (React, PHP, Python, Arduino)
 model: openrouter/deepseek/deepseek-chat
+memory: project
 thinking: low
 tools: read, bash, write, grep, find
 max_turns: 30

agents/database.md

@@ -1,6 +1,7 @@
 ---
 description: Database design, SQL, and schema creation
 model: opencode-go/deepseek-r1-distill-qwen-32b
+memory: project
 thinking: low
 tools: read, bash, write, grep
 max_turns: 25

agents/devops-basic.md

@@ -1,6 +1,7 @@
 ---
 description: Docker, YAML, NixOS config editing
 model: openrouter/deepseek/deepseek-chat
+memory: project
 thinking: low
 tools: read, bash, write, grep, find
 skills: nixos-workflow, system-architect

agents/devops-pro.md

@@ -1,6 +1,7 @@
 ---
 description: Complex multi-service DevOps (deep reasoning)
 model: openrouter/deepseek/deepseek-v4-pro
+memory: project
 thinking: high
 tools: read, bash, write, grep, find, edit
 max_turns: 50

agents/document-writer.md

@@ -1,6 +1,7 @@
 ---
 description: Documents, letters, and planning notes
 model: opencode-go/deepseek-r1-distill-qwen-32b
+memory: project
 thinking: low
 tools: read, bash, write
 max_turns: 25

agents/file-ops.md

@@ -1,6 +1,7 @@
 ---
 description: Filesystem scanning, drive management
 model: opencode-go/qwen-coder-32b-instruct
+memory: project
 thinking: off
 tools: read, bash, grep, find, write
 max_turns: 20

agents/home-automation.md

@@ -1,6 +1,7 @@
 ---
 description: Bash, Python, MQTT, and Home Assistant
 model: opencode-go/deepseek-r1-distill-qwen-32b
+memory: project
 thinking: low
 tools: read, bash, write, grep
 max_turns: 30

agents/image-maker.md

@@ -1,6 +1,7 @@
 ---
 description: Image generation via OpenRouter chat completions API
 model: openrouter/openai/gpt-5-image-mini
+memory: project
 thinking: off
 tools: read, bash, write
 max_turns: 15

agents/iot-coder.md

@@ -1,6 +1,7 @@
 ---
 description: Arduino C++, ESP32, and IoT firmware
 model: opencode-go/qwen-coder-32b-instruct
+memory: project
 thinking: low
 tools: read, bash, write, grep, find
 max_turns: 30

agents/iot-hardware.md

@@ -1,6 +1,7 @@
 ---
 description: Hardware specs, boards, and ESP Home
 model: openrouter/moonshotai/kimi-k2.6
+memory: project
 thinking: off
 tools: read, bash, grep, find
 max_turns: 20

agents/obsidian.md

@@ -1,6 +1,7 @@
 ---
 description: Obsidian note-taking and vault management
 model: opencode-go/deepseek-r1-distill-qwen-14b
+memory: project
 thinking: low
 tools: read, bash, write, grep, find
 skills: obsidian-cli

agents/research.md

@@ -1,6 +1,7 @@
 ---
 description: Web search and documentation lookup
 model: openrouter/google/gemini-2.5-flash:free
+memory: project
 thinking: off
 tools: read, bash, grep, find
 max_turns: 15

agents/video-analyze.md

@@ -1,6 +1,7 @@
 ---
 description: Video and image analysis via vision models
 model: openrouter/qwen/qwen-2.5-vl
+memory: project
 thinking: off
 tools: read, bash, grep, find
 max_turns: 20

agents/vscode-setup.md

@@ -1,6 +1,7 @@
 ---
 description: VS Code, AI dev tools, and IDE setup
 model: openrouter/qwen/qwen-3-coder-next
+memory: project
 thinking: off
 tools: read, bash, grep, find
 max_turns: 20

skills/subagent-registry/SKILL.md

@@ -1,100 +0,0 @@
----
-name: subagent-registry
-description: Manage named subagent instances. MUST be used when spawning, resuming, listing, or deleting subagents. Read this skill FIRST before any subagent operation.
----
-
-# Subagent Registry — CRITICAL
-
-You MUST manage `<project>/.pi/subagents.json` for ALL subagent operations. Read the file before any operation. Write the file after any change.
-
-## File Location
-
-`<cwd>/.pi/subagents.json` (where cwd is the current project directory)
-
-## File Format
-
-```json
-{
-  "session": "<pi-session-name-or-project-dir>",
-  "agents": [
-    {
-      "name": "<human-readable-name>",
-      "id": "<agent-uuid-from-spawn-notification>",
-      "type": "<subagent_type>",
-      "provider": "<exact-provider-config-from-agent-frontmatter>",
-      "status": "running|completed|error",
-      "created": "<ISO-timestamp>"
-    }
-  ]
-}
-```
-
-## MANDATORY Operations
-
-### SPAWN — Always do this:
-1. Ask user for a name if not provided: "What should I name this subagent?"
-2. Spawn the agent: `Agent({ subagent_type, prompt, run_in_background: true })`
-3. Wait for completion notification — extract the agent ID from the response
-4. Read current `.pi/subagents.json`
-5. Append new agent entry with name, id, type, provider, status="running", timestamp
-6. Write updated `.pi/subagents.json`
-7. Tell user: "Created subagent '<name>' (<id-short>) using <provider>"
-
-### LIST — Always do this:
-1. Read `.pi/subagents.json`
-2. If file doesn't exist or agents array is empty: "No subagents found."
-3. Display compact table:
-```
-Name         Type        Provider    Status    Created
-----         ----        --------    ------    -------
-searcher     chat-search Google      ↻ run     15:35
-```
-4. Show: name, type, provider, status, created time
-
-### RESUME — Always do this:
-1. Read `.pi/subagents.json`, find agent by name
-2. If not found: "No subagent named '<name>'. Available: <list-of-names>"
-3. If found: `Agent({ subagent_type, resume: "<agent-id>", prompt: "<new-task>", run_in_background: true })`
-4. Update status to "running" in registry
-5. Tell user: "Resumed '<name>' (<id-short>) — <provider> cache warm"
-
-### DELETE — Always do this:
-1. Read `.pi/subagents.json`, find agent by name
-2. If running: steer to abort first
-3. Remove entry from registry array
-4. Write updated `.pi/subagents.json`
-5. Tell user: "Deleted '<name>'"
-
-### DELETE SESSION — Always do this:
-1. Read `.pi/subagents.json`
-2. Remove all agents where session matches
-3. Write updated `.pi/subagents.json`
-4. Tell user: "Deleted <N> subagents from session '<name>'"
-
-## Rules
-
-- **NEVER spawn without asking for a name first**
-- **NEVER skip writing to the registry** after spawn/resume/delete
-- **ALWAYS read the registry** before listing or resuming
-- **Provider config must be preserved exactly** from the agent's frontmatter (e.g., "only:DeepInfra")
-- **No auto-cleanup** — agents persist until explicitly deleted
-- **Each named agent gets `memory: project`** in its frontmatter for persistent memory
-
-## Example Workflow
-
-```
-User: "Spawn a coder-pro to fix the login module"
-You: "What should I name this subagent?"
-User: "auth-login"
-You: *spawn agent → get ID 7efad0d8-5a78-415*
-You: *read .pi/subagents.json → append entry → write file*
-You: "Created subagent 'auth-login' (7efad0d8) using DeepInfra"
-
-User: "List my subagents"
-You: *read .pi/subagents.json → display table*
-  auth-login    coder-pro  DeepInfra  ↻ running  20:00
-
-User: "Resume auth-login and add password reset"
-You: *read .pi/subagents.json → find ID → resume*
-You: "Resumed 'auth-login' (7efad0d8) — DeepInfra cache warm"
-```