agent-contacts
AI agent contacts — add, list, remove MCP contacts. Use when someone gives an agent URL, or when you need to view/remove contacts.
What this skill does
# Agent Contacts
> Contact book for AI agents. Add an MCP address and your Claude Code can communicate with other agents.
## When to use
- `/agent-contacts add <url>` — add a new contact
- `/agent-contacts list` — show all contacts
- `/agent-contacts remove <name>` — remove a contact
- When someone gives you an agent/bot URL
## Paths
| What | Path |
|------|------|
| Contacts DB | `~/.claude/agent-contacts.json` |
## contacts.json format
```json
[
{
"name": "Your Name",
"slug": "ivan-schedule",
"mcp_url": "https://your-agent.example.com/mcp/",
"discovery_url": "https://your-agent.example.com/.well-known/agent.json",
"capabilities": ["scheduling"],
"description": "Scheduling agent for Your Name",
"added": "2026-02-26"
}
]
```
## How to execute
Parse `$ARGUMENTS` to determine the command: first word is the command (`add`, `list`, `remove`), the rest is the argument.
### Add: `/agent-contacts add <url>`
```python
import json, re
from datetime import date
from pathlib import Path
CONTACTS_FILE = Path.home() / ".claude" / "agent-contacts.json"
# 1. Load existing contacts
if CONTACTS_FILE.exists():
contacts = json.loads(CONTACTS_FILE.read_text())
else:
contacts = []
# 2. Normalize URL — $ARGUMENTS[1] is the URL
url = "$1".strip().rstrip("/")
if not url.endswith("agent.json"):
discovery_url = url + "/.well-known/agent.json"
else:
discovery_url = url
url = url.rsplit("/.well-known/agent.json", 1)[0]
# 3. Use WebFetch to get agent.json content, then parse:
# - name = agent_data["name"]
# - description = agent_data.get("description", "")
# - capabilities = list(agent_data.get("capabilities", {}).keys())
# - mcp_url = agent_data["capabilities"][first_cap]["url"]
# Ensure mcp_url ends with "/"
# 4. Generate slug
slug = re.sub(r"[^a-z0-9-]", "", name.lower().replace(" ", "-"))
# 5. Check for duplicates
if any(c["slug"] == slug for c in contacts):
print(f"Contact '{name}' already exists.")
else:
contacts.append({
"name": name,
"slug": slug,
"mcp_url": mcp_url,
"discovery_url": discovery_url,
"capabilities": capabilities,
"description": description,
"added": str(date.today()),
})
CONTACTS_FILE.write_text(json.dumps(contacts, indent=2, ensure_ascii=False))
```
After saving to JSON, run:
```bash
claude mcp add <slug> --transport http <mcp_url>
```
Notify: "Contact `<name>` added. Restart Claude Code session to use their tools."
### List: `/agent-contacts list`
```python
import json
from pathlib import Path
CONTACTS_FILE = Path.home() / ".claude" / "agent-contacts.json"
if not CONTACTS_FILE.exists():
print("No agent contacts yet. Use '/agent-contacts add <url>' to add one.")
else:
contacts = json.loads(CONTACTS_FILE.read_text())
if not contacts:
print("No agent contacts yet.")
else:
for i, c in enumerate(contacts, 1):
caps = ", ".join(c.get("capabilities", []))
print(f" {i}. {c['name']} ({c['slug']})")
print(f" MCP: {c['mcp_url']}")
print(f" Capabilities: {caps}")
print()
```
### Remove: `/agent-contacts remove <name-or-slug>`
```python
import json
from pathlib import Path
CONTACTS_FILE = Path.home() / ".claude" / "agent-contacts.json"
target = "$1".strip().lower() # name or slug
contacts = json.loads(CONTACTS_FILE.read_text())
match = [c for c in contacts if c["slug"] == target or c["name"].lower() == target]
if not match:
print(f"Contact '{target}' not found.")
else:
slug = match[0]["slug"]
name = match[0]["name"]
contacts = [c for c in contacts if c["slug"] != slug]
CONTACTS_FILE.write_text(json.dumps(contacts, indent=2, ensure_ascii=False))
```
After removing from JSON, run:
```bash
claude mcp remove <slug>
```
Notify: "Contact `<name>` removed."
## How to share your address with others
Simply send the link:
```
https://your-agent.example.com/.well-known/agent.json
```
If the person has this skill:
```
/agent-contacts add https://your-agent.example.com
```
If they don't have the skill -- one command:
```bash
claude mcp add ivan-schedule --transport http https://your-agent.example.com/mcp/
```
## Important
- `agent-contacts.json` is created automatically on the first `add`
- Slug must be unique (used as MCP server name in Claude Code)
- MCP URL must end with `/` (trailing slash)
- After `add`, a **new session** of Claude Code is required for MCP tools to become available
- This skill has side effects (`claude mcp add/remove`), hence `disable-model-invocation: true`
## Related skills
- `deploy-website` — deploy page with instructions for new contacts
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.