refactor: modernize agent configs, remove beads, update README

- Upgrade all agents from glm-4.7 to glm-5 with descriptive names - Add comprehensive permission configs (bash, edit, external_directory) for all agents - Remove .beads/ issue tracking directory - Update README: fix opencode URL to opencode.ai, remove beads sections, formatting cleanup
2026-02-17 09:15:15 +01:00
parent 923e2f1eaa
commit 6fceea7460
8 changed files with 154 additions and 266 deletions
--- a/.beads/.gitignore
+++ b/.beads/.gitignore
@@ -1,39 +0,0 @@
-# SQLite databases
-*.db
-*.db?*
-*.db-journal
-*.db-wal
-*.db-shm
-
-# Daemon runtime files
-daemon.lock
-daemon.log
-daemon.pid
-bd.sock
-sync-state.json
-last-touched
-
-# Local version tracking (prevents upgrade notification spam after git ops)
-.local_version
-
-# Legacy database files
-db.sqlite
-bd.db
-
-# Worktree redirect file (contains relative path to main repo's .beads/)
-# Must not be committed as paths would be wrong in other clones
-redirect
-
-# Merge artifacts (temporary files from 3-way merge)
-beads.base.jsonl
-beads.base.meta.json
-beads.left.jsonl
-beads.left.meta.json
-beads.right.jsonl
-beads.right.meta.json
-
-# NOTE: Do NOT add negation patterns (e.g., !issues.jsonl) here.
-# They would override fork protection in .git/info/exclude, allowing
-# contributors to accidentally commit upstream issue databases.
-# The JSONL files (issues.jsonl, interactions.jsonl) and config files
-# are tracked by git by default since no pattern above ignores them.
--- a/.beads/README.md
+++ b/.beads/README.md
@@ -1,81 +0,0 @@
-# Beads - AI-Native Issue Tracking
-
-Welcome to Beads! This repository uses **Beads** for issue tracking - a modern, AI-native tool designed to live directly in your codebase alongside your code.
-
-## What is Beads?
-
-Beads is issue tracking that lives in your repo, making it perfect for AI coding agents and developers who want their issues close to their code. No web UI required - everything works through the CLI and integrates seamlessly with git.
-
-**Learn more:** [github.com/steveyegge/beads](https://github.com/steveyegge/beads)
-
-## Quick Start
-
-### Essential Commands
-
-```bash
-# Create new issues
-bd create "Add user authentication"
-
-# View all issues
-bd list
-
-# View issue details
-bd show <issue-id>
-
-# Update issue status
-bd update <issue-id> --status in_progress
-bd update <issue-id> --status done
-
-# Sync with git remote
-bd sync
-```
-
-### Working with Issues
-
-Issues in Beads are:
- **Git-native**: Stored in `.beads/issues.jsonl` and synced like code
- **AI-friendly**: CLI-first design works perfectly with AI coding agents
- **Branch-aware**: Issues can follow your branch workflow
- **Always in sync**: Auto-syncs with your commits
-
-## Why Beads?
-
-✨ **AI-Native Design**
- Built specifically for AI-assisted development workflows
- CLI-first interface works seamlessly with AI coding agents
- No context switching to web UIs
-
-🚀 **Developer Focused**
- Issues live in your repo, right next to your code
- Works offline, syncs when you push
- Fast, lightweight, and stays out of your way
-
-🔧 **Git Integration**
- Automatic sync with git commits
- Branch-aware issue tracking
- Intelligent JSONL merge resolution
-
-## Get Started with Beads
-
-Try Beads in your own projects:
-
-```bash
-# Install Beads
-curl -sSL https://raw.githubusercontent.com/steveyegge/beads/main/scripts/install.sh | bash
-
-# Initialize in your repo
-bd init
-
-# Create your first issue
-bd create "Try out Beads"
-```
-
-## Learn More
-
- **Documentation**: [github.com/steveyegge/beads/docs](https://github.com/steveyegge/beads/tree/main/docs)
- **Quick Start Guide**: Run `bd quickstart`
- **Examples**: [github.com/steveyegge/beads/examples](https://github.com/steveyegge/beads/tree/main/examples)
-
---
-
-*Beads: Issue tracking that moves at the speed of thought* ⚡
--- a/.beads/config.yaml
+++ b/.beads/config.yaml
@@ -1,62 +0,0 @@
-# Beads Configuration File
-# This file configures default behavior for all bd commands in this repository
-# All settings can also be set via environment variables (BD_* prefix)
-# or overridden with command-line flags
-
-# Issue prefix for this repository (used by bd init)
-# If not set, bd init will auto-detect from directory name
-# Example: issue-prefix: "myproject" creates issues like "myproject-1", "myproject-2", etc.
-# issue-prefix: ""
-
-# Use no-db mode: load from JSONL, no SQLite, write back after each command
-# When true, bd will use .beads/issues.jsonl as the source of truth
-# instead of SQLite database
-# no-db: false
-
-# Disable daemon for RPC communication (forces direct database access)
-# no-daemon: false
-
-# Disable auto-flush of database to JSONL after mutations
-# no-auto-flush: false
-
-# Disable auto-import from JSONL when it's newer than database
-# no-auto-import: false
-
-# Enable JSON output by default
-# json: false
-
-# Default actor for audit trails (overridden by BD_ACTOR or --actor)
-# actor: ""
-
-# Path to database (overridden by BEADS_DB or --db)
-# db: ""
-
-# Auto-start daemon if not running (can also use BEADS_AUTO_START_DAEMON)
-# auto-start-daemon: true
-
-# Debounce interval for auto-flush (can also use BEADS_FLUSH_DEBOUNCE)
-# flush-debounce: "5s"
-
-# Git branch for beads commits (bd sync will commit to this branch)
-# IMPORTANT: Set this for team projects so all clones use the same sync branch.
-# This setting persists across clones (unlike database config which is gitignored).
-# Can also use BEADS_SYNC_BRANCH env var for local override.
-# If not set, bd sync will require you to run 'bd config set sync.branch <branch>'.
-# sync-branch: "beads-sync"
-
-# Multi-repo configuration (experimental - bd-307)
-# Allows hydrating from multiple repositories and routing writes to the correct JSONL
-# repos:
-#   primary: "."  # Primary repo (where this database lives)
-#   additional:   # Additional repos to hydrate from (read-only)
-#     - ~/beads-planning  # Personal planning repo
-#     - ~/work-planning   # Work planning repo
-
-# Integration settings (access with 'bd config get/set')
-# These are stored in the database, not in this file:
-# - jira.url
-# - jira.project
-# - linear.url
-# - linear.api-key
-# - github.org
-# - github.repo
--- a/.beads/interactions.jsonl
+++ b/.beads/interactions.jsonl
--- a/.beads/issues.jsonl
+++ b/.beads/issues.jsonl
@@ -1,15 +0,0 @@
-{"id":"AGENTS-1jw","title":"Athena prompt: Convert to numbered responsibility format","description":"Athena prompt uses bullet points under 'Core Capabilities' section instead of numbered lists. Per agent-development skill best practices, responsibilities should be numbered (1, 2, 3) for clarity. Update prompts/athena.txt to use numbered format.","status":"closed","priority":2,"issue_type":"task","owner":"p@m3ta.dev","created_at":"2026-01-24T19:32:16.133701271+01:00","created_by":"m3tm3re","updated_at":"2026-01-26T19:32:26.165270695+01:00","closed_at":"2026-01-26T19:32:26.165270695+01:00","close_reason":"Converted responsibility subsections from ### numbered headers to numbered list format (1., 2., 3., 4.) with bold titles"}
-{"id":"AGENTS-27m","title":"Create prompts/chiron-forge.txt with Chiron-Forge's build/execution mode system prompt","status":"closed","priority":2,"issue_type":"task","owner":"p@m3ta.dev","created_at":"2026-02-03T18:47:31.083994237+01:00","created_by":"m3tm3re","updated_at":"2026-02-03T18:48:45.012894731+01:00","closed_at":"2026-02-03T18:48:45.012894731+01:00","close_reason":"Created prompts/chiron-forge.txt with Chiron-Forge's build/execution mode system prompt (3185 chars, 67 lines)"}
-{"id":"AGENTS-7gt","title":"Athena prompt: Rename Core Capabilities to exact header","description":"Athena prompt uses 'Core Capabilities' section header instead of 'Your Core Responsibilities:'. Per agent-development skill guidelines, the exact header 'Your Core Responsibilities:' should be used for consistency. Update prompts/athena.txt to use the exact recommended header.","status":"closed","priority":1,"issue_type":"task","owner":"p@m3ta.dev","created_at":"2026-01-24T19:32:07.223102836+01:00","created_by":"m3tm3re","updated_at":"2026-01-26T19:31:19.080626796+01:00","closed_at":"2026-01-26T19:31:19.080626796+01:00","close_reason":"Renamed 'Core Capabilities' section header to exact 'Your Core Responsibilities:' in prompts/athena.txt"}
-{"id":"AGENTS-8ie","title":"Set up PARA work structure with 10 Basecamp projects","description":"Create 01-projects/work/ structure with project folders for all Basecamp projects. Each project needs: _index.md (MOC with Basecamp link), meetings/, decisions/, notes/. Also set up 02-areas/work/ for ongoing responsibilities.","status":"closed","priority":0,"issue_type":"task","owner":"p@m3ta.dev","created_at":"2026-01-28T18:47:56.048622809+01:00","created_by":"m3tm3re","updated_at":"2026-01-28T18:57:09.033627658+01:00","closed_at":"2026-01-28T18:57:09.033627658+01:00","close_reason":"Created complete PARA work structure: 01-projects/work/ with 10 project folders (each with _index.md, meetings/, decisions/, notes/), 02-areas/work/ with 5 area files. Projects use placeholder names - user can customize with actual Basecamp data."}
-{"id":"AGENTS-9cs","title":"Configure basecamp skill with real projects","description":"Configure basecamp skill to work with real projects. Need to: get user's Basecamp projects, map them to PARA structure, test morning planning workflow with Basecamp todos.","status":"closed","priority":0,"issue_type":"task","owner":"p@m3ta.dev","created_at":"2026-01-28T18:47:56.04844425+01:00","created_by":"m3tm3re","updated_at":"2026-01-28T18:57:14.097333313+01:00","closed_at":"2026-01-28T18:57:14.097333313+01:00","close_reason":"Enhanced basecamp skill with project mapping configuration. Added section on mapping Basecamp projects to PARA structure, with configuration examples and usage patterns. Ready for user to fetch actual projects and set up mappings."}
-{"id":"AGENTS-b74","title":"Create skills/msteams/SKILL.md with MS Teams Graph API integration documentation","status":"closed","priority":2,"issue_type":"task","owner":"p@m3ta.dev","created_at":"2026-02-03T18:50:21.728376088+01:00","created_by":"m3tm3re","updated_at":"2026-02-03T18:52:08.609302234+01:00","closed_at":"2026-02-03T18:52:08.609302234+01:00","close_reason":"Created skills/msteams/SKILL.md with complete MS Teams Graph API integration documentation covering channels, messages, meetings, and chat operations"}
-{"id":"AGENTS-ch2","title":"Create skills/outlook/SKILL.md with Outlook Graph API documentation","status":"closed","priority":2,"issue_type":"task","owner":"p@m3ta.dev","created_at":"2026-02-03T18:49:24.814232462+01:00","created_by":"m3tm3re","updated_at":"2026-02-03T18:54:30.910986438+01:00","closed_at":"2026-02-03T18:54:30.910986438+01:00","close_reason":"Completed: Created skills/outlook/SKILL.md with Outlook Graph API documentation including mail CRUD, calendar, contacts, folders, and workflow examples. Validation passed."}
-{"id":"AGENTS-der","title":"Create Outline skill for MCP integration","status":"closed","priority":2,"issue_type":"feature","owner":"p@m3ta.dev","created_at":"2026-01-28T18:47:56.042886345+01:00","created_by":"m3tm3re","updated_at":"2026-01-28T18:51:21.662507568+01:00","closed_at":"2026-01-28T18:51:21.662507568+01:00","close_reason":"Created outline/SKILL.md with comprehensive workflows, tool references, and integration patterns. Added references/outline-workflows.md and references/export-patterns.md for detailed examples."}
-{"id":"AGENTS-fac","title":"Design Teams transcript processing workflow (manual)","description":"Design manual workflow for Teams transcript processing: DOCX upload → extract text → AI analysis → meeting note + action items → optional Basecamp sync. Create templates and integration points.","status":"closed","priority":2,"issue_type":"task","owner":"p@m3ta.dev","created_at":"2026-01-28T18:47:56.052076817+01:00","created_by":"m3tm3re","updated_at":"2026-01-28T18:56:34.567325504+01:00","closed_at":"2026-01-28T18:56:34.567325504+01:00","close_reason":"Created comprehensive Teams transcript workflow guide in skills/meeting-notes/references/teams-transcript-workflow.md. Includes: manual step-by-step process, Python script for DOCX extraction, AI analysis prompts, Obsidian templates, Basecamp sync integration, troubleshooting guide."}
-{"id":"AGENTS-in5","title":"Athena prompt: Standardize section headers","description":"Athena prompt uses 'Ethical Guidelines' and 'Methodological Rigor' headers instead of standard 'Quality Standards' and 'Edge Cases' headers. While semantically equivalent, skill recommends exact headers for consistency. Consider renaming in prompts/athena.txt.","status":"closed","priority":2,"issue_type":"task","owner":"p@m3ta.dev","created_at":"2026-01-24T19:32:21.720932741+01:00","created_by":"m3tm3re","updated_at":"2026-01-26T19:33:15.959382333+01:00","closed_at":"2026-01-26T19:33:15.959382333+01:00","close_reason":"Renamed '## Ethical Guidelines' to '## Quality Standards' for consistency with agent-development skill guidelines"}
-{"id":"AGENTS-lyd","title":"Athena agent: Add explicit mode field","description":"Athena agent is missing the explicit 'mode': 'subagent' field. Per agent-development skill guidelines, all agents should explicitly declare mode for clarity. Current config relies on default which makes intent unclear.","status":"closed","priority":0,"issue_type":"task","owner":"p@m3ta.dev","created_at":"2026-01-24T19:31:46.255196119+01:00","created_by":"m3tm3re","updated_at":"2026-01-26T19:30:46.191545632+01:00","closed_at":"2026-01-26T19:30:46.191545632+01:00","close_reason":"Added explicit 'mode': 'subagent' field to athena agent in agent/agents.json"}
-{"id":"AGENTS-mfw","title":"Athena agent: Add temperature setting","description":"Athena agent lacks explicit temperature configuration. Per agent-development skill, research/analysis agents should use temperature 0.0-0.2 for focused, deterministic, consistent results. Add 'temperature': 0.1 to agent config in agents.json.","status":"closed","priority":1,"issue_type":"task","owner":"p@m3ta.dev","created_at":"2026-01-24T19:31:55.726506579+01:00","created_by":"m3tm3re","updated_at":"2026-01-26T19:31:06.905697638+01:00","closed_at":"2026-01-26T19:31:06.905697638+01:00","close_reason":"Added 'temperature': 0.1 to athena agent in agent/agents.json for focused, deterministic results"}
-{"id":"AGENTS-mvv","title":"Enhance daily routines with work context","status":"closed","priority":1,"issue_type":"task","owner":"p@m3ta.dev","created_at":"2026-01-28T18:47:56.066628593+01:00","created_by":"m3tm3re","updated_at":"2026-01-28T18:56:34.576536473+01:00","closed_at":"2026-01-28T18:56:34.576536473+01:00","close_reason":"Enhanced daily-routines skill with full work context integration. Added sections for: morning planning with Basecamp/Outline, evening reflection with work metrics, weekly review with project status tracking, work area health review, work inbox processing."}
-{"id":"AGENTS-o45","title":"Agent development: Document validation script availability","description":"The agent-development skill references scripts/validate-agent.sh but this script doesn't exist in the repository. Consider either: (1) creating the validation script, or (2) removing the reference and only documenting the python3 alternative.","status":"closed","priority":2,"issue_type":"task","owner":"p@m3ta.dev","created_at":"2026-01-24T19:32:27.325525742+01:00","created_by":"m3tm3re","updated_at":"2026-01-26T19:34:17.846875543+01:00","closed_at":"2026-01-26T19:34:17.846875543+01:00","close_reason":"Removed references to non-existent scripts/validate-agent.sh and documented python3 validation as the primary method"}
-{"id":"AGENTS-o7l","title":"Create agents.json with 6 agent definitions","status":"closed","priority":2,"issue_type":"task","owner":"p@m3ta.dev","created_at":"2026-02-03T20:13:02.959856824+01:00","created_by":"m3tm3re","updated_at":"2026-02-03T20:13:58.186033248+01:00","closed_at":"2026-02-03T20:13:58.186033248+01:00","close_reason":"Created agents.json with all 6 agent definitions (chiron, chiron-forge, hermes, athena, apollo, calliope) with proper mode, model, prompt references, and permissions. Verified with Python JSON validation."}
--- a/.beads/metadata.json
+++ b/.beads/metadata.json
@@ -1,4 +0,0 @@
-{
-  "database": "beads.db",
-  "jsonl_export": "issues.jsonl"
-}
--- a/README.md
+++ b/README.md
@@ -1,6 +1,6 @@
 # Opencode Agent Skills & Configurations

-Central repository for [Opencode](https://opencode.dev) Agent Skills, AI agent configurations, custom commands, and AI-assisted workflows. This is an extensible framework for building productivity systems, automations, knowledge management, and specialized AI capabilities.
+Central repository for [Opencode](https://opencode.ai) Agent Skills, AI agent configurations, custom commands, and AI-assisted workflows. This is an extensible framework for building productivity systems, automations, knowledge management, and specialized AI capabilities.

 ## 🎯 What This Repository Provides

@@ -46,10 +46,9 @@ This repository serves as a **personal AI operating system** - a collection of s

 ### Prerequisites

- **Opencode** - AI coding assistant ([opencode.dev](https://opencode.dev))
+- **Opencode** - AI coding assistant ([opencode.dev](https://opencode.ai))
 - **Nix** (optional) - For declarative deployment via home-manager
 - **Python 3** - For skill validation and creation scripts
- **bd (beads)** (optional) - For issue tracking

 ### Installation

@@ -78,6 +77,7 @@ programs.opencode.settings.agent = builtins.fromJSON
 ```

 Rebuild your system:
+
 ```bash
 home-manager switch
 ```
@@ -116,6 +116,7 @@ python3 skill/skill-creator/scripts/init_skill.py my-skill-name --path skill/
 ```

 This creates:
+
 - `skill/my-skill-name/SKILL.md` - Main skill documentation
 - `skill/my-skill-name/scripts/` - Executable code (optional)
 - `skill/my-skill-name/references/` - Reference documentation (optional)
@@ -131,7 +132,6 @@ name: my-skill-name
 description: What it does and when to use it. Include trigger keywords.
 compatibility: opencode
 ---
-
 # My Skill Name

 ## Overview
@@ -161,7 +161,7 @@ The test script creates a temporary config directory with symlinks to this repo'
 ## 📚 Available Skills

 | Skill                    | Purpose                                                 | Status    |
-|-------|---------|--------|
+| ------------------------ | ------------------------------------------------------- | --------- |
 | **task-management**      | PARA-based productivity with Obsidian Tasks integration | ✅ Active |
 | **skill-creator**        | Guide for creating new Opencode skills                  | ✅ Active |
 | **reflection**           | Conversation analysis and skill improvement             | ✅ Active |
@@ -188,6 +188,7 @@ Chiron is a personal AI assistant focused on productivity and task management. N
 - Integration with productivity tools (Obsidian, ntfy, n8n)

 **Modes**:
+
 - **Chiron** (Plan Mode) - Read-only analysis and planning (`prompts/chiron.txt`)
 - **Chiron-Forge** (Worker Mode) - Full write access with safety prompts (`prompts/chiron-forge.txt`)

@@ -195,18 +196,6 @@ Chiron is a personal AI assistant focused on productivity and task management. N

 ## 🛠️ Development Workflow

-### Issue Tracking with Beads
-
-This project uses [beads](https://github.com/steveyegge/beads) for AI-native issue tracking:
-
-```bash
-bd ready              # Find available work
-bd create "title"     # Create new issue
-bd update <id> --status in_progress
-bd close <id>         # Complete work
-bd sync               # Sync with git
-```
-
 ### Quality Gates

 Before committing:
@@ -216,23 +205,6 @@ Before committing:
 3. **Check formatting**: Ensure YAML frontmatter is valid
 4. **Update docs**: Keep README and AGENTS.md in sync

-### Session Completion
-
-When ending a work session:
-
-1. File beads issues for remaining work
-2. Run quality gates
-3. Update issue status
-4. **Push to remote** (mandatory):
-   ```bash
-   git pull --rebase
-   bd sync
-   git push
-   ```
-5. Verify changes are pushed
-
-See `AGENTS.md` for complete developer documentation.
-
 ## 🎓 Learning Resources

 ### Essential Documentation
@@ -263,6 +235,7 @@ See `AGENTS.md` for complete developer documentation.
 ### Modify Agent Behavior

 Edit `agent/agents.json` for agent definitions and `prompts/*.txt` for system prompts:
+
 - `agent/agents.json` - Agent names, models, permissions
 - `prompts/chiron.txt` - Chiron (Plan Mode) system prompt
 - `prompts/chiron-forge.txt` - Chiron-Forge (Worker Mode) system prompt
@@ -272,6 +245,7 @@ Edit `agent/agents.json` for agent definitions and `prompts/*.txt` for system pr
 ### Update User Context

 Edit `context/profile.md` to configure:
+
 - Work style preferences
 - PARA areas and projects
 - Communication preferences
@@ -286,6 +260,7 @@ Create new command definitions in `command/` directory following the pattern in
 ### Personal Productivity

 Use the PARA methodology with Obsidian Tasks integration:
+
 - Capture tasks and notes quickly
 - Run daily/weekly reviews
 - Prioritize work based on impact
@@ -294,6 +269,7 @@ Use the PARA methodology with Obsidian Tasks integration:
 ### Knowledge Management

 Build a personal knowledge base:
+
 - Capture research findings
 - Organize notes and references
 - Link related concepts
@@ -302,6 +278,7 @@ Build a personal knowledge base:
 ### AI-Assisted Development

 Extend Opencode for specialized domains:
+
 - Create company-specific skills (finance, legal, engineering)
 - Integrate with APIs and databases
 - Build custom automation workflows
@@ -310,6 +287,7 @@ Extend Opencode for specialized domains:
 ### Team Collaboration

 Share skills and agents across teams:
+
 - Document company processes as skills
 - Create shared knowledge bases
 - Standardize communication templates
--- a/agents/agents.json
+++ b/agents/agents.json
@@ -1,62 +1,173 @@
 {
-  "chiron": {
+  "Chiron (Assistant)": {
    "description": "Personal AI assistant (Plan Mode). Read-only analysis, planning, and guidance.",
    "mode": "primary",
-    "model": "zai-coding-plan/glm-4.7",
+    "model": "zai-coding-plan/glm-5",
    "prompt": "{file:./prompts/chiron.txt}",
    "permission": {
+      "question": "allow",
+      "webfetch": "allow",
+      "websearch": "allow",
+      "edit": "deny",
+      "bash": {
+        "*": "ask",
+        "git status*": "allow",
+        "git log*": "allow",
+        "git diff*": "allow",
+        "git branch*": "allow",
+        "git show*": "allow",
+        "grep *": "allow",
+        "ls *": "allow",
+        "cat *": "allow",
+        "head *": "allow",
+        "tail *": "allow",
+        "wc *": "allow",
+        "which *": "allow",
+        "echo *": "allow",
+        "td *": "allow",
+        "bd *": "allow",
+        "nix *": "allow"
+      },
      "external_directory": {
+        "*": "ask",
        "~/p/**": "allow",
-        "*": "ask"
+        "~/.config/opencode/**": "allow",
+        "/tmp/**": "allow",
+        "/run/agenix/**": "allow"
      }
    }
  },
-  "chiron-forge": {
+  "Chiron Forge (Builder)": {
    "description": "Personal AI assistant (Build Mode). Full execution and task completion capabilities with safety prompts.",
    "mode": "primary",
-    "model": "zai-coding-plan/glm-4.7",
+    "model": "zai-coding-plan/glm-5",
    "prompt": "{file:./prompts/chiron-forge.txt}",
    "permission": {
+      "question": "allow",
+      "webfetch": "allow",
+      "websearch": "allow",
+      "edit": {
+        "*": "allow",
+        "/run/agenix/**": "deny"
+      },
+      "bash": {
+        "*": "allow",
+        "rm -rf *": "ask",
+        "git reset --hard*": "ask",
+        "git push*": "ask",
+        "git push --force*": "deny",
+        "git push -f *": "deny"
+      },
      "external_directory": {
+        "*": "ask",
        "~/p/**": "allow",
-        "*": "ask"
+        "~/.config/opencode/**": "allow",
+        "/tmp/**": "allow",
+        "/run/agenix/**": "allow"
      }
    }
  },
-  "hermes": {
+  "Hermes (Communication)": {
    "description": "Work communication specialist. Handles Basecamp tasks, Outlook email, and MS Teams meetings.",
    "mode": "subagent",
-    "model": "zai-coding-plan/glm-4.7",
+    "model": "zai-coding-plan/glm-5",
    "prompt": "{file:./prompts/hermes.txt}",
    "permission": {
-      "question": "allow"
+      "question": "allow",
+      "webfetch": "allow",
+      "edit": {
+        "*": "allow",
+        "/run/agenix/**": "deny"
+      },
+      "bash": {
+        "*": "ask",
+        "cat *": "allow",
+        "echo *": "allow"
+      },
+      "external_directory": {
+        "*": "ask",
+        "~/p/**": "allow",
+        "~/.config/opencode/**": "allow",
+        "/tmp/**": "allow",
+        "/run/agenix/**": "allow"
+      }
    }
  },
-  "athena": {
+  "Athena (Researcher)": {
    "description": "Work knowledge specialist. Manages Outline wiki, documentation, and knowledge organization.",
    "mode": "subagent",
-    "model": "zai-coding-plan/glm-4.7",
+    "model": "zai-coding-plan/glm-5",
    "prompt": "{file:./prompts/athena.txt}",
    "permission": {
-      "question": "allow"
+      "question": "allow",
+      "webfetch": "allow",
+      "websearch": "allow",
+      "edit": {
+        "*": "allow",
+        "/run/agenix/**": "deny"
+      },
+      "bash": {
+        "*": "ask",
+        "grep *": "allow",
+        "cat *": "allow"
+      },
+      "external_directory": {
+        "*": "ask",
+        "~/p/**": "allow",
+        "~/.config/opencode/**": "allow",
+        "/tmp/**": "allow",
+        "/run/agenix/**": "allow"
+      }
    }
  },
-  "apollo": {
+  "Apollo (Knowledge Management)": {
    "description": "Private knowledge specialist. Manages Obsidian vault, personal notes, and private knowledge graph.",
    "mode": "subagent",
-    "model": "zai-coding-plan/glm-4.7",
+    "model": "zai-coding-plan/glm-5",
    "prompt": "{file:./prompts/apollo.txt}",
    "permission": {
-      "question": "allow"
+      "question": "allow",
+      "edit": {
+        "*": "allow",
+        "/run/agenix/**": "deny"
+      },
+      "bash": {
+        "*": "ask",
+        "cat *": "allow"
+      },
+      "external_directory": {
+        "*": "ask",
+        "~/p/**": "allow",
+        "~/.config/opencode/**": "allow",
+        "/tmp/**": "allow",
+        "/run/agenix/**": "allow"
+      }
    }
  },
-  "calliope": {
+  "Calliope (Writer)": {
    "description": "Writing specialist. Creates documentation, reports, meeting notes, and prose.",
    "mode": "subagent",
-    "model": "zai-coding-plan/glm-4.7",
+    "model": "zai-coding-plan/glm-5",
    "prompt": "{file:./prompts/calliope.txt}",
    "permission": {
-      "question": "allow"
+      "question": "allow",
+      "webfetch": "allow",
+      "edit": {
+        "*": "allow",
+        "/run/agenix/**": "deny"
+      },
+      "bash": {
+        "*": "ask",
+        "cat *": "allow",
+        "wc *": "allow"
+      },
+      "external_directory": {
+        "*": "ask",
+        "~/p/**": "allow",
+        "~/.config/opencode/**": "allow",
+        "/tmp/**": "allow",
+        "/run/agenix/**": "allow"
+      }
    }
  }
 }