agent-mail
Inter-agent communication for multi-agent workflows. Use when multiple agents need to coordinate, share information, or reserve resources.
What this skill does
# Agent Mail System
Communication system for coordinating multiple agents.
## Overview
Agent mail enables:
- Message passing between agents
- File reservation to prevent conflicts
- Session tracking across agents
- Thread-based conversations
## Session Management
### Start Agent Session
Register agent and get inbox:
```bash
# Initialize session
curl -X POST http://localhost:3847/api/session/start \
-H "Content-Type: application/json" \
-d '{
"project_path": "/path/to/project",
"program": "claude-code",
"model": "opus-4",
"agent_name": "agent-1",
"task_description": "Working on auth module"
}'
```
### List Agents
```bash
curl http://localhost:3847/api/agents?project_path=/path/to/project
```
### Agent Info
```bash
curl http://localhost:3847/api/agents/agent-1?project_path=/path/to/project
```
## Messaging
### Send Message
```bash
curl -X POST http://localhost:3847/api/mail/send \
-H "Content-Type: application/json" \
-d '{
"project_path": "/path/to/project",
"sender_name": "agent-1",
"to": ["agent-2"],
"subject": "Auth module complete",
"body_md": "## Summary\nAuth implementation is done.\n\n## Files changed\n- src/auth/*",
"importance": "normal",
"ack_required": false
}'
```
### Check Inbox
```bash
curl "http://localhost:3847/api/mail/inbox?project_path=/path/to/project&agent_name=agent-1"
```
### Reply to Message
```bash
curl -X POST http://localhost:3847/api/mail/reply \
-H "Content-Type: application/json" \
-d '{
"project_path": "/path/to/project",
"message_id": 123,
"sender_name": "agent-2",
"body_md": "Thanks! I'\''ll start on the API integration."
}'
```
### Acknowledge Message
```bash
curl -X POST http://localhost:3847/api/mail/ack \
-H "Content-Type: application/json" \
-d '{
"project_path": "/path/to/project",
"agent_name": "agent-2",
"message_id": 123
}'
```
### Search Messages
```bash
curl "http://localhost:3847/api/mail/search?project_path=/path/to/project&query=authentication"
```
## File Reservations
Prevent conflicts when multiple agents edit files.
### Reserve Files
```bash
curl -X POST http://localhost:3847/api/files/reserve \
-H "Content-Type: application/json" \
-d '{
"project_path": "/path/to/project",
"agent_name": "agent-1",
"paths": ["src/auth/*.ts", "src/config.ts"],
"exclusive": true,
"reason": "Implementing authentication",
"ttl_seconds": 3600
}'
```
### Check Reservations
```bash
curl "http://localhost:3847/api/files/reservations?project_path=/path/to/project"
```
### Release Files
```bash
curl -X POST http://localhost:3847/api/files/release \
-H "Content-Type: application/json" \
-d '{
"project_path": "/path/to/project",
"agent_name": "agent-1",
"paths": ["src/auth/*.ts"]
}'
```
## Thread Management
### Get Thread Summary
```bash
curl "http://localhost:3847/api/mail/thread/THREAD_ID/summary?project_path=/path/to/project"
```
### Thread Operations
Threads are automatically created when replying to messages.
## Coordination Patterns
### Task Handoff
```markdown
Agent 1 completes task:
1. Reserve output files
2. Complete work
3. Send message to Agent 2 with handoff details
4. Release file reservations
Agent 2 receives:
1. Get inbox
2. Reserve input files
3. Continue work
4. Acknowledge receipt
```
### Parallel Work
```markdown
Coordinator:
1. Reserve coordination files
2. Send tasks to agents
3. Wait for completion messages
4. Merge results
Workers:
1. Reserve assigned files
2. Complete task
3. Send completion message
4. Release files
```
### Review Request
```markdown
Author:
1. Complete code
2. Send review request to reviewer agents
3. Wait for feedback
Reviewers:
1. Get inbox
2. Review code (read-only, no reservation needed)
3. Send feedback message
```
## Health Check
```bash
curl http://localhost:3847/api/health
```
## Message Importance Levels
| Level | Use Case |
|-------|----------|
| `low` | FYI, status updates |
| `normal` | Standard communication |
| `high` | Needs attention soon |
| `urgent` | Blocking, needs immediate response |
## Best Practices
1. **Reserve before editing** - Prevent conflicts
2. **Use meaningful subjects** - Easy inbox scanning
3. **Acknowledge important** - Confirm receipt when `ack_required`
4. **Release promptly** - Don't hold reservations unnecessarily
5. **Use threads** - Keep related messages together
6. **Check inbox regularly** - Don't miss messages
7. **Handoff cleanly** - Include all needed context
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.