2026-01-06 08:52:00 +01:00
|
|
|
{
|
2026-02-17 09:15:15 +01:00
|
|
|
"Chiron (Assistant)": {
|
2026-01-06 08:52:00 +01:00
|
|
|
"description": "Personal AI assistant (Plan Mode). Read-only analysis, planning, and guidance.",
|
|
|
|
|
"mode": "primary",
|
2026-02-17 09:15:15 +01:00
|
|
|
"model": "zai-coding-plan/glm-5",
|
2026-01-06 08:52:00 +01:00
|
|
|
"prompt": "{file:./prompts/chiron.txt}",
|
|
|
|
|
"permission": {
|
2026-02-17 09:15:15 +01:00
|
|
|
"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"
|
|
|
|
|
},
|
2026-02-02 19:06:49 +01:00
|
|
|
"external_directory": {
|
2026-02-17 09:15:15 +01:00
|
|
|
"*": "ask",
|
2026-02-02 19:06:49 +01:00
|
|
|
"~/p/**": "allow",
|
2026-02-17 09:15:15 +01:00
|
|
|
"~/.config/opencode/**": "allow",
|
|
|
|
|
"/tmp/**": "allow",
|
|
|
|
|
"/run/agenix/**": "allow"
|
2026-02-03 20:04:26 +01:00
|
|
|
}
|
2026-01-24 19:40:38 +01:00
|
|
|
}
|
Create agents.json with 6 agent definitions (Wave 1, Task 1)
- Added all 6 agents: chiron, chiron-forge, hermes, athena, apollo, calliope
- Primary agents (2): chiron (Plan Mode), chiron-forge (Build Mode)
- Subagents (4): hermes (communications), athena (work knowledge), apollo (private knowledge), calliope (writing)
- All agents use model: zai-coding-plan/glm-4.7
- Prompt references use file pattern: {file:./prompts/<name>.txt}
- Permission structure: primaries have external_directory rules, subagents have simple question: allow
- Verified with Python JSON validation (6 agents, correct names)
- Documented patterns and learnings in notepad
2026-02-03 20:14:34 +01:00
|
|
|
},
|
2026-02-17 09:15:15 +01:00
|
|
|
"Chiron Forge (Builder)": {
|
Create agents.json with 6 agent definitions (Wave 1, Task 1)
- Added all 6 agents: chiron, chiron-forge, hermes, athena, apollo, calliope
- Primary agents (2): chiron (Plan Mode), chiron-forge (Build Mode)
- Subagents (4): hermes (communications), athena (work knowledge), apollo (private knowledge), calliope (writing)
- All agents use model: zai-coding-plan/glm-4.7
- Prompt references use file pattern: {file:./prompts/<name>.txt}
- Permission structure: primaries have external_directory rules, subagents have simple question: allow
- Verified with Python JSON validation (6 agents, correct names)
- Documented patterns and learnings in notepad
2026-02-03 20:14:34 +01:00
|
|
|
"description": "Personal AI assistant (Build Mode). Full execution and task completion capabilities with safety prompts.",
|
|
|
|
|
"mode": "primary",
|
2026-02-17 09:15:15 +01:00
|
|
|
"model": "zai-coding-plan/glm-5",
|
Create agents.json with 6 agent definitions (Wave 1, Task 1)
- Added all 6 agents: chiron, chiron-forge, hermes, athena, apollo, calliope
- Primary agents (2): chiron (Plan Mode), chiron-forge (Build Mode)
- Subagents (4): hermes (communications), athena (work knowledge), apollo (private knowledge), calliope (writing)
- All agents use model: zai-coding-plan/glm-4.7
- Prompt references use file pattern: {file:./prompts/<name>.txt}
- Permission structure: primaries have external_directory rules, subagents have simple question: allow
- Verified with Python JSON validation (6 agents, correct names)
- Documented patterns and learnings in notepad
2026-02-03 20:14:34 +01:00
|
|
|
"prompt": "{file:./prompts/chiron-forge.txt}",
|
|
|
|
|
"permission": {
|
2026-02-17 09:15:15 +01:00
|
|
|
"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"
|
|
|
|
|
},
|
Create agents.json with 6 agent definitions (Wave 1, Task 1)
- Added all 6 agents: chiron, chiron-forge, hermes, athena, apollo, calliope
- Primary agents (2): chiron (Plan Mode), chiron-forge (Build Mode)
- Subagents (4): hermes (communications), athena (work knowledge), apollo (private knowledge), calliope (writing)
- All agents use model: zai-coding-plan/glm-4.7
- Prompt references use file pattern: {file:./prompts/<name>.txt}
- Permission structure: primaries have external_directory rules, subagents have simple question: allow
- Verified with Python JSON validation (6 agents, correct names)
- Documented patterns and learnings in notepad
2026-02-03 20:14:34 +01:00
|
|
|
"external_directory": {
|
2026-02-17 09:15:15 +01:00
|
|
|
"*": "ask",
|
Create agents.json with 6 agent definitions (Wave 1, Task 1)
- Added all 6 agents: chiron, chiron-forge, hermes, athena, apollo, calliope
- Primary agents (2): chiron (Plan Mode), chiron-forge (Build Mode)
- Subagents (4): hermes (communications), athena (work knowledge), apollo (private knowledge), calliope (writing)
- All agents use model: zai-coding-plan/glm-4.7
- Prompt references use file pattern: {file:./prompts/<name>.txt}
- Permission structure: primaries have external_directory rules, subagents have simple question: allow
- Verified with Python JSON validation (6 agents, correct names)
- Documented patterns and learnings in notepad
2026-02-03 20:14:34 +01:00
|
|
|
"~/p/**": "allow",
|
2026-02-17 09:15:15 +01:00
|
|
|
"~/.config/opencode/**": "allow",
|
|
|
|
|
"/tmp/**": "allow",
|
|
|
|
|
"/run/agenix/**": "allow"
|
Create agents.json with 6 agent definitions (Wave 1, Task 1)
- Added all 6 agents: chiron, chiron-forge, hermes, athena, apollo, calliope
- Primary agents (2): chiron (Plan Mode), chiron-forge (Build Mode)
- Subagents (4): hermes (communications), athena (work knowledge), apollo (private knowledge), calliope (writing)
- All agents use model: zai-coding-plan/glm-4.7
- Prompt references use file pattern: {file:./prompts/<name>.txt}
- Permission structure: primaries have external_directory rules, subagents have simple question: allow
- Verified with Python JSON validation (6 agents, correct names)
- Documented patterns and learnings in notepad
2026-02-03 20:14:34 +01:00
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
},
|
2026-02-17 09:15:15 +01:00
|
|
|
"Hermes (Communication)": {
|
Create agents.json with 6 agent definitions (Wave 1, Task 1)
- Added all 6 agents: chiron, chiron-forge, hermes, athena, apollo, calliope
- Primary agents (2): chiron (Plan Mode), chiron-forge (Build Mode)
- Subagents (4): hermes (communications), athena (work knowledge), apollo (private knowledge), calliope (writing)
- All agents use model: zai-coding-plan/glm-4.7
- Prompt references use file pattern: {file:./prompts/<name>.txt}
- Permission structure: primaries have external_directory rules, subagents have simple question: allow
- Verified with Python JSON validation (6 agents, correct names)
- Documented patterns and learnings in notepad
2026-02-03 20:14:34 +01:00
|
|
|
"description": "Work communication specialist. Handles Basecamp tasks, Outlook email, and MS Teams meetings.",
|
|
|
|
|
"mode": "subagent",
|
2026-02-17 09:15:15 +01:00
|
|
|
"model": "zai-coding-plan/glm-5",
|
Create agents.json with 6 agent definitions (Wave 1, Task 1)
- Added all 6 agents: chiron, chiron-forge, hermes, athena, apollo, calliope
- Primary agents (2): chiron (Plan Mode), chiron-forge (Build Mode)
- Subagents (4): hermes (communications), athena (work knowledge), apollo (private knowledge), calliope (writing)
- All agents use model: zai-coding-plan/glm-4.7
- Prompt references use file pattern: {file:./prompts/<name>.txt}
- Permission structure: primaries have external_directory rules, subagents have simple question: allow
- Verified with Python JSON validation (6 agents, correct names)
- Documented patterns and learnings in notepad
2026-02-03 20:14:34 +01:00
|
|
|
"prompt": "{file:./prompts/hermes.txt}",
|
|
|
|
|
"permission": {
|
2026-02-17 09:15:15 +01:00
|
|
|
"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"
|
|
|
|
|
}
|
Create agents.json with 6 agent definitions (Wave 1, Task 1)
- Added all 6 agents: chiron, chiron-forge, hermes, athena, apollo, calliope
- Primary agents (2): chiron (Plan Mode), chiron-forge (Build Mode)
- Subagents (4): hermes (communications), athena (work knowledge), apollo (private knowledge), calliope (writing)
- All agents use model: zai-coding-plan/glm-4.7
- Prompt references use file pattern: {file:./prompts/<name>.txt}
- Permission structure: primaries have external_directory rules, subagents have simple question: allow
- Verified with Python JSON validation (6 agents, correct names)
- Documented patterns and learnings in notepad
2026-02-03 20:14:34 +01:00
|
|
|
}
|
|
|
|
|
},
|
2026-02-17 09:15:15 +01:00
|
|
|
"Athena (Researcher)": {
|
Create agents.json with 6 agent definitions (Wave 1, Task 1)
- Added all 6 agents: chiron, chiron-forge, hermes, athena, apollo, calliope
- Primary agents (2): chiron (Plan Mode), chiron-forge (Build Mode)
- Subagents (4): hermes (communications), athena (work knowledge), apollo (private knowledge), calliope (writing)
- All agents use model: zai-coding-plan/glm-4.7
- Prompt references use file pattern: {file:./prompts/<name>.txt}
- Permission structure: primaries have external_directory rules, subagents have simple question: allow
- Verified with Python JSON validation (6 agents, correct names)
- Documented patterns and learnings in notepad
2026-02-03 20:14:34 +01:00
|
|
|
"description": "Work knowledge specialist. Manages Outline wiki, documentation, and knowledge organization.",
|
|
|
|
|
"mode": "subagent",
|
2026-02-17 09:15:15 +01:00
|
|
|
"model": "zai-coding-plan/glm-5",
|
Create agents.json with 6 agent definitions (Wave 1, Task 1)
- Added all 6 agents: chiron, chiron-forge, hermes, athena, apollo, calliope
- Primary agents (2): chiron (Plan Mode), chiron-forge (Build Mode)
- Subagents (4): hermes (communications), athena (work knowledge), apollo (private knowledge), calliope (writing)
- All agents use model: zai-coding-plan/glm-4.7
- Prompt references use file pattern: {file:./prompts/<name>.txt}
- Permission structure: primaries have external_directory rules, subagents have simple question: allow
- Verified with Python JSON validation (6 agents, correct names)
- Documented patterns and learnings in notepad
2026-02-03 20:14:34 +01:00
|
|
|
"prompt": "{file:./prompts/athena.txt}",
|
|
|
|
|
"permission": {
|
2026-02-17 09:15:15 +01:00
|
|
|
"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"
|
|
|
|
|
}
|
Create agents.json with 6 agent definitions (Wave 1, Task 1)
- Added all 6 agents: chiron, chiron-forge, hermes, athena, apollo, calliope
- Primary agents (2): chiron (Plan Mode), chiron-forge (Build Mode)
- Subagents (4): hermes (communications), athena (work knowledge), apollo (private knowledge), calliope (writing)
- All agents use model: zai-coding-plan/glm-4.7
- Prompt references use file pattern: {file:./prompts/<name>.txt}
- Permission structure: primaries have external_directory rules, subagents have simple question: allow
- Verified with Python JSON validation (6 agents, correct names)
- Documented patterns and learnings in notepad
2026-02-03 20:14:34 +01:00
|
|
|
}
|
|
|
|
|
},
|
2026-02-17 09:15:15 +01:00
|
|
|
"Apollo (Knowledge Management)": {
|
Create agents.json with 6 agent definitions (Wave 1, Task 1)
- Added all 6 agents: chiron, chiron-forge, hermes, athena, apollo, calliope
- Primary agents (2): chiron (Plan Mode), chiron-forge (Build Mode)
- Subagents (4): hermes (communications), athena (work knowledge), apollo (private knowledge), calliope (writing)
- All agents use model: zai-coding-plan/glm-4.7
- Prompt references use file pattern: {file:./prompts/<name>.txt}
- Permission structure: primaries have external_directory rules, subagents have simple question: allow
- Verified with Python JSON validation (6 agents, correct names)
- Documented patterns and learnings in notepad
2026-02-03 20:14:34 +01:00
|
|
|
"description": "Private knowledge specialist. Manages Obsidian vault, personal notes, and private knowledge graph.",
|
|
|
|
|
"mode": "subagent",
|
2026-02-17 09:15:15 +01:00
|
|
|
"model": "zai-coding-plan/glm-5",
|
Create agents.json with 6 agent definitions (Wave 1, Task 1)
- Added all 6 agents: chiron, chiron-forge, hermes, athena, apollo, calliope
- Primary agents (2): chiron (Plan Mode), chiron-forge (Build Mode)
- Subagents (4): hermes (communications), athena (work knowledge), apollo (private knowledge), calliope (writing)
- All agents use model: zai-coding-plan/glm-4.7
- Prompt references use file pattern: {file:./prompts/<name>.txt}
- Permission structure: primaries have external_directory rules, subagents have simple question: allow
- Verified with Python JSON validation (6 agents, correct names)
- Documented patterns and learnings in notepad
2026-02-03 20:14:34 +01:00
|
|
|
"prompt": "{file:./prompts/apollo.txt}",
|
|
|
|
|
"permission": {
|
2026-02-17 09:15:15 +01:00
|
|
|
"question": "allow",
|
|
|
|
|
"edit": {
|
|
|
|
|
"*": "allow",
|
|
|
|
|
"/run/agenix/**": "deny"
|
|
|
|
|
},
|
|
|
|
|
"bash": {
|
|
|
|
|
"*": "ask",
|
|
|
|
|
"cat *": "allow"
|
|
|
|
|
},
|
|
|
|
|
"external_directory": {
|
|
|
|
|
"*": "ask",
|
|
|
|
|
"~/p/**": "allow",
|
|
|
|
|
"~/.config/opencode/**": "allow",
|
|
|
|
|
"/tmp/**": "allow",
|
|
|
|
|
"/run/agenix/**": "allow"
|
|
|
|
|
}
|
Create agents.json with 6 agent definitions (Wave 1, Task 1)
- Added all 6 agents: chiron, chiron-forge, hermes, athena, apollo, calliope
- Primary agents (2): chiron (Plan Mode), chiron-forge (Build Mode)
- Subagents (4): hermes (communications), athena (work knowledge), apollo (private knowledge), calliope (writing)
- All agents use model: zai-coding-plan/glm-4.7
- Prompt references use file pattern: {file:./prompts/<name>.txt}
- Permission structure: primaries have external_directory rules, subagents have simple question: allow
- Verified with Python JSON validation (6 agents, correct names)
- Documented patterns and learnings in notepad
2026-02-03 20:14:34 +01:00
|
|
|
}
|
|
|
|
|
},
|
2026-02-17 09:15:15 +01:00
|
|
|
"Calliope (Writer)": {
|
Create agents.json with 6 agent definitions (Wave 1, Task 1)
- Added all 6 agents: chiron, chiron-forge, hermes, athena, apollo, calliope
- Primary agents (2): chiron (Plan Mode), chiron-forge (Build Mode)
- Subagents (4): hermes (communications), athena (work knowledge), apollo (private knowledge), calliope (writing)
- All agents use model: zai-coding-plan/glm-4.7
- Prompt references use file pattern: {file:./prompts/<name>.txt}
- Permission structure: primaries have external_directory rules, subagents have simple question: allow
- Verified with Python JSON validation (6 agents, correct names)
- Documented patterns and learnings in notepad
2026-02-03 20:14:34 +01:00
|
|
|
"description": "Writing specialist. Creates documentation, reports, meeting notes, and prose.",
|
|
|
|
|
"mode": "subagent",
|
2026-02-17 09:15:15 +01:00
|
|
|
"model": "zai-coding-plan/glm-5",
|
Create agents.json with 6 agent definitions (Wave 1, Task 1)
- Added all 6 agents: chiron, chiron-forge, hermes, athena, apollo, calliope
- Primary agents (2): chiron (Plan Mode), chiron-forge (Build Mode)
- Subagents (4): hermes (communications), athena (work knowledge), apollo (private knowledge), calliope (writing)
- All agents use model: zai-coding-plan/glm-4.7
- Prompt references use file pattern: {file:./prompts/<name>.txt}
- Permission structure: primaries have external_directory rules, subagents have simple question: allow
- Verified with Python JSON validation (6 agents, correct names)
- Documented patterns and learnings in notepad
2026-02-03 20:14:34 +01:00
|
|
|
"prompt": "{file:./prompts/calliope.txt}",
|
|
|
|
|
"permission": {
|
2026-02-17 09:15:15 +01:00
|
|
|
"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"
|
|
|
|
|
}
|
Create agents.json with 6 agent definitions (Wave 1, Task 1)
- Added all 6 agents: chiron, chiron-forge, hermes, athena, apollo, calliope
- Primary agents (2): chiron (Plan Mode), chiron-forge (Build Mode)
- Subagents (4): hermes (communications), athena (work knowledge), apollo (private knowledge), calliope (writing)
- All agents use model: zai-coding-plan/glm-4.7
- Prompt references use file pattern: {file:./prompts/<name>.txt}
- Permission structure: primaries have external_directory rules, subagents have simple question: allow
- Verified with Python JSON validation (6 agents, correct names)
- Documented patterns and learnings in notepad
2026-02-03 20:14:34 +01:00
|
|
|
}
|
2026-01-06 08:52:00 +01:00
|
|
|
}
|
|
|
|
|
}
|