marktantongco/opencode-accomplishments/agent-roles
Claude Code and agent skill by marktantongco/opencode-accomplishments
- community
Checking that the SKILL.md file is still in the repository.
Unified multi-agent role system — Builder, Coder, Council, Orchestrator, Plan, Researcher, Reviewer, Scribe. Use when use when coordinating multi-agent workflows with role delegation Triggers on keywords: agents, roles, orchestration, delegation.
Install
npx vskill@latest install marktantongco/opencode-accomplishments/agent-rolesSKILL.md
Agent Role System
context
Unified multi-agent role system — Builder, Coder, Council, Oracle modes with automatic role selection based on task type and complexity. This skill provides system-level capabilities that maintain agent state, ensure consistency, and optimize resource usage across sessions and projects.
instructions
Step 1: Assess System Needs
- Identify the system operation required — memory, sync, compression, or role management
- Determine scope — single session, multi-session, or cross-project
- Map dependencies — what other systems or tools are involved
- Establish operational parameters — retention, frequency, thresholds
Step 2: Execute System Operation
- Initialize — Set up or load required state and configuration
- Process — Execute the core operation with proper error handling
- Validate — Verify the operation completed correctly
- Report — Document what was done and any issues encountered
Step 3: Generate System Report
Step 4: Verify System Health
- [ ] Operation completed without errors
- [ ] State is consistent and valid
- [ ] No resource leaks or orphaned data
- [ ] Logging and monitoring are active
- [ ] Backup/recovery procedures are in place
constraints
- NEVER modify system state without logging the change.
- NEVER assume operations succeed — always validate results.
- NEVER skip cleanup — system resources must be properly released.
- ALWAYS handle concurrent access and race conditions.
- ALWAYS maintain backward compatibility with existing state.
examples
Example: System Operation
Input: "Use when coordinating multi-agent workflows with role delegation"
Output:
Security
- Security scanPassed, 95 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingskills/agent-roles/SKILL.md
Popularity
- 7-day trend score
- 5
Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/marktantongco/opencode-accomplishments/agent-roles)