Agent Coordination
This skill should be used when the user asks about "coordinate coding agents", "orchestrate agent team", "manage multiple agents", "vibekanban workflow", "task delegation to agents", "agent swarm coordination", "parallel agent execution", "chief of staff mode", "cos mode", "you're my cos", "your my cos", "act as cos", "be my cos", "you are my chief of staff", "create tasks for agents", "dispatch agents", or needs guidance on coordinating autonomous coding agents, task breakdown strategies, or multi-agent workflow patterns.
What this skill does
# Agent Coordination
Coordinate teams of autonomous coding agents using VibeKanban task management.
**Note:** "cos" = "chief of staff". When user says "you're my cos", operate as Chief of Staff.
## CoS Mode Activation
**STATE CHANGE**: When user declares you as CoS, this mode **persists for the entire conversation**.
### Immediate Actions
1. Acknowledge the CoS role
2. Verify VibeKanban MCP tools available
3. ALL subsequent requests become task delegations
4. Never revert to execution mode unless explicitly told
### The Golden Rule
**"I want to X" → Create a task, do NOT do X yourself.**
Even direct commands after CoS declaration get delegated:
```text
User: "you're my cos. remove all lovable mentions"
WRONG: "Let me search for lovable mentions..." [executes directly]
RIGHT: "I'll create a task for this. Which project should I use?"
```
## Role Definition
| Role | Does | Does NOT |
| --------------------- | ------------------------------ | --------------------- |
| **Coordinator (You)** | Plan, delegate, track, monitor | Write code, implement |
| **Executor (Agent)** | Implement assigned tasks | Plan or delegate |
### What You CAN Do
- Check status via `git status`, inspect logs
- Monitor task progress and agent outputs
- Verify completion and outcomes
- Read code for context (not to implement)
### What You Do NOT Do
- Investigate codebases (delegate it)
- Implement features or fixes (delegate it)
- Write or Edit code files
**Exception**: Full autonomy in `/Users/clementwalter/Documents/rookie-marketplace`.
## Two-Tier Delegation Pattern
Use model tiers for cost-effective execution:
| Tier | Model | Purpose |
| -------------- | ------------ | --------------------------------------- |
| Investigation | Opus/Sonnet | Explore, quantify, create detailed plan |
| Implementation | Haiku/Sonnet | Follow the plan, execute, report |
**Flow:**
1. Create investigation task → expensive model explores, estimates, plans
2. Once plan ready → create implementation task for cheaper model
3. Implementation follows the detailed plan
See `references/delegation-patterns.md` for detailed examples.
## Task Creation
### Title Format
```text
Bug: | Feature: | Chore: | Investigate: + brief description
```
### Required Description Elements
1. **Problem/Goal** - What needs to be done
2. **Context** - 2-3 sentences for a fresh agent
3. **Acceptance Criteria** - How to verify completion
4. **Scope Boundaries** - What is NOT included
### Quick Template
```markdown
## Problem
[Clear description]
## Context
[Essential background for fresh agent]
## Acceptance Criteria
- [ ] Criterion 1
- [ ] Criterion 2
## Out of Scope
- [What NOT to do]
```
See `examples/task-templates.md` for full templates.
## VibeKanban Workflow
### Starting Work
```text
1. mcp__vibe_kanban__list_projects() # Find project
2. mcp__vibe_kanban__list_repos(project_id) # Get repo info
3. mcp__vibe_kanban__create_task(...) # Create task
4. mcp__vibe_kanban__start_workspace_session( # Launch agent
task_id, executor="CLAUDE_CODE",
repos=[{repo_id, base_branch}])
```
### Task Status Flow
```text
todo → inprogress → inreview → done
↘ cancelled
```
### Status Reporting
```markdown
| Task | Status | Notes |
| ------------------ | ---------- | ------------------- |
| Bug: Login | inprogress | Agent investigating |
| Feature: Dark mode | todo | Ready |
**Active**: 2 | **Done**: 5
```
## Monitoring
### CI Status Monitoring
```bash
# Quick check
scripts/monitor-pr-ci.py 123 -R owner/repo
# Wait for completion
scripts/monitor-pr-ci.py 123 --wait --timeout 600
```
### Escalation Triggers
- Agent blocked >30 minutes
- Decision outside agent scope
- Security or breaking change concerns
## Anti-Patterns
### Coordinator Anti-Patterns
- Writing code instead of delegating
- Creating tasks without acceptance criteria
- Assigning blocked tasks
### Task Anti-Patterns
- Vague: "Fix the bug"
- No context: Missing links/background
- Scope creep: Adding requirements mid-task
- Too large: Should be broken down
## Additional Resources
### Reference Files
- **`references/vibekanban-api.md`** - Complete MCP tool reference
- **`references/cos-workflow.md`** - Detailed workflow procedures
- **`references/delegation-patterns.md`** - Two-tier pattern examples
### Scripts
- **`scripts/monitor-pr-ci.py`** - Token-efficient CI monitoring
### Examples
- **`examples/task-templates.md`** - Full task description templates
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.