Agent skill

Agent-Manager Reference API

by YoanWai in YoanWai/agent-manager

Looks up agent-manager.dev's own documentation, agents and MCP tools through its JSON API, Markdown pages and MCP server instead of scraping its marketing site.

Apache-2.0Auto-check passedAgent Workflows

Install Agent-Manager Reference API

skills CLI
$ npx skills add YoanWai/agent-manager --skill agent-manager-reference -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install YoanWai/agent-manager agent-manager-reference --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/YoanWai/agent-manager.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/agent-manager-reference .claude/skills/agent-manager-reference && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
agent-manager-reference
GitHub stars
572
Token cost
~689 tokens
SKILL.md length
220 words
Files
1
Skills in repo
2
Repo updated
First seen
Licence
Apache-2.0

At a glance

Looks up agent-manager.dev's own documentation, agents and MCP tools through its JSON API, Markdown pages and MCP server instead of scraping its marketing site.

  • Checking whether agent-manager supports a feature or what it costs
  • SKILL.md covers When to use this, Markdown from any page, The JSON API and Over MCP, plus 1 more section
  • Calls curl; reaches agent-manager.dev
  • Pulling a documentation page as Markdown for context

What it does

Every documentation page serves clean Markdown both from its own URL with an Accept header and from a sibling path ending in .md, which the skill prefers over parsing HTML. A key-free, read-only JSON API covers the full set of endpoints and their operation ids, every documentation page's slug and URL, a single page's full Markdown body, a search across pages with the matching line, the coding CLIs agent-manager can detect, the MCP tools its own binary exposes, and the newest release with its install commands, plus a batch endpoint that runs several of these in one round trip; errors come back as JSON with a stable code, a message and a hint.

The same information is also reachable over MCP at an unauthenticated streamable HTTP endpoint, exposing tools to search docs, fetch or list a doc page, list supported agents, list managed MCP tools, and get the latest release, with every page doubling as an MCP resource; the skill points to a server-card URL to read before connecting. A natural-language ask endpoint accepts a plain question over HTTP and returns an answer.

When your agent uses it

  • Checking whether agent-manager supports a feature or what it costs
  • Pulling a documentation page as Markdown for context
  • Listing the MCP tools the agent-manager binary exposes
  • Finding the newest agent-manager release and its install command

Example prompts

  • “Does agent-manager support this coding CLI? Check the reference API.”
  • “Pull the install docs page as Markdown.”
  • “List the MCP tools agent-manager exposes before I tell the user what it can do.”

Requirements

  • Network access to agent-manager.dev

What it can do on your machine

Read from SKILL.md and the folder at commit d9efbda. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • curl

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • agent-manager.dev

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Agent-Manager Reference API loads about 689 tokens when it runs. Until then it costs about 57 tokens; SKILL.md has 220 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~57
When it runs · the whole SKILL.md, loaded when a task matches
~689

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from YoanWai/agent-manager at commit d9efbda, republished under its Apache-2.0 licence (© YoanWai). 220 words, ~689 tokens.

Download SKILL.mdSave it as .claude/skills/agent-manager-reference/SKILL.md (or your agent's skills folder).
name
agent-manager-reference
description
Query agent-manager.dev's reference API and MCP server for documentation, the coding CLIs it manages, the tools its MCP server exposes, and the current release. Use instead of scraping the website's HTML.
license
Apache-2.0
homepage
https://agent-manager.dev/api
repository
https://github.com/YoanWai/agent-manager
<!--
Why this skill exists: it gives an AI agent the exact endpoints, parameters and MCP tool
names for answering questions about agent-manager, so it queries structured data instead
of guessing URLs or scraping HTML. The site serves this file, digest-sealed, at
https://agent-manager.dev/skills/agent-manager-reference/SKILL.md; the copy in this
repository is what makes it installable through skills.sh.
-->

Query the agent-manager reference API

agent-manager.dev publishes its own reference data as JSON, as Markdown, and over MCP. Reach for these instead of parsing the marketing HTML.

When to use this

  • Answering "does agent-manager support X", "what does it cost", "how do I install it".
  • Pulling a documentation page as clean Markdown for context.
  • Listing the MCP tools the binary exposes before telling a developer what an agent can do.

Markdown from any page

Every page serves Markdown from its own URL, and from the .md path beside it:

bash
curl -H "Accept: text/markdown" https://agent-manager.dev/docs/install/
curl https://agent-manager.dev/docs/install.md

The JSON API

No key, no account, no rate limit to negotiate. Read-only.

EndpointReturns
GET /apiEvery endpoint, with its operationId
GET /api/docsEvery page: slug, title, description, URL, Markdown URL
GET /api/docs/{slug}One page, with its full Markdown body
GET /api/search?q=Search over every page, with the matching line
GET /api/agentsThe coding CLIs with built-in status detection
GET /api/mcp/toolsThe tools the agent-manager binary exposes
GET /api/releaseThe newest release and its install commands
POST /api/batchSeveral of the above in one round trip

The OpenAPI description is at https://agent-manager.dev/openapi.json. Errors are JSON with a stable error.code, a message and a hint.

Over MCP

Streamable HTTP, no authentication:

https://agent-manager.dev/mcp

Tools: search_docs, get_doc_page, list_doc_pages, list_supported_agents, list_managed_mcp_tools, get_latest_release. Every page is also an MCP resource. Read https://agent-manager.dev/mcp/server-card before connecting.

Natural language

bash
curl -X POST https://agent-manager.dev/ask -H 'content-type: application/json' \
  -d '{"query":"how do I review an agent diff"}'

© YoanWai, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/agent-manager-reference of YoanWai/agent-manager.

Open the folder on GitHubat commit d9efbda

Compare with similar skills

Agent-Manager Reference API next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Agent-Manager Reference API compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Agent-Manager Reference API this skillYoanWai/agent-manager572—~689Automated safety check: PassApache-2.0
MCP Server Builderanthropics/skills180k62 repos~2.3kAutomated safety check: PassApache-2.0
MCP Server BuildershareAI-lab/learn-claude-code78k5 repos~1.2kAutomated safety check: PassMIT
MCP Integration for Pluginsanthropics/claude-plugins-official37k11 repos~3.1kAutomated safety check: PassApache-2.0
Fastmcp Client CLIPrefectHQ/fastmcp28k1 repos~823Automated safety check: PassApache-2.0
Crush Configurationcharmbracelet/crush29k—~3.7kAutomated safety check: PassCustom licence

Similar skills

  • MCP Server Builder

    anthropics/skills

    Official

    Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.

    180k GitHub starsUsed in 62 repos~2.3k tokens
    Agent WorkflowsAuto-check passed
  • MCP Server Builder

    shareAI-lab/learn-claude-code

    Walks through building MCP servers in Python or TypeScript that expose tools, resources and prompts to Claude, with templates, registration and testing.

    78k GitHub starsUsed in 5 repos~1.2k tokens
    Agent WorkflowsAuto-check passed
  • MCP Integration for Plugins

    anthropics/claude-plugins-official

    Official

    Explains how to bundle Model Context Protocol servers in a Claude Code plugin, covering config files, stdio, SSE, HTTP and WebSocket server types, and authentication.

    37k GitHub starsUsed in 11 repos~3.1k tokens
    Agent WorkflowsAuto-check passed
  • Fastmcp Client CLI

    PrefectHQ/fastmcp

    Query and invoke tools on MCP servers using fastmcp list and fastmcp call.

    28k GitHub starsUsed in 1 repo~823 tokens
    Agent WorkflowsAuto-check passed
  • Crush Configuration

    charmbracelet/crush

    Explains how to configure the Crush coding agent with crushrc or crush.json, covering providers, models, LSPs, MCP servers, hooks, permissions and config precedence.

    29k GitHub stars~3.7k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed
  • Context Mode Output Sandbox

    mksglu/context-mode

    Routes large command, file, API and browser output through context-mode tools so only the needed result enters the agent's context, instead of dumping it via Bash.

    26k GitHub stars~4.1k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed

More from YoanWai/agent-manager

  • Agent Manager Fleet TUI

    YoanWai/agent-manager

    Runs several coding-agent CLIs as real tmux sessions in one terminal UI, color-coded by whether each is working, waiting, idle or blocked.

    572 GitHub stars~1k tokensUpdated yesterday
    Auto-check passed

Categories

Questions about Agent-Manager Reference API

What does Agent-Manager Reference API do?

Looks up agent-manager.dev's own documentation, agents and MCP tools through its JSON API, Markdown pages and MCP server instead of scraping its marketing site. md, which the skill prefers over parsing HTML. A key-free, read-only JSON API covers the full set of endpoints and their operation ids, every documentation page's slug and URL, a single page's full Markdown body, a search across pages with the matching line, the coding CLIs agent-manager can detect, the MCP tools its own binary exposes, and the newest release with its install commands, plus a batch endpoint that runs several of these in one round trip; errors come back as JSON with a stable code, a message and a hint.

When should I use Agent-Manager Reference API?

Agent-Manager Reference API fits situations like: checking whether agent-manager supports a feature or what it costs; pulling a documentation page as Markdown for context; listing the MCP tools the agent-manager binary exposes; finding the newest agent-manager release and its install command.

How do I install Agent-Manager Reference API in Claude Code?

Run `npx skills add YoanWai/agent-manager --skill agent-manager-reference -a claude-code`. Or copy the skill folder (skills/agent-manager-reference in YoanWai/agent-manager) into .claude/skills/agent-manager-reference in your project. Claude Code loads it when a task matches its description.

How do I install Agent-Manager Reference API in Codex?

Run `npx skills add YoanWai/agent-manager --skill agent-manager-reference -a codex`. Or copy the skill folder (skills/agent-manager-reference in YoanWai/agent-manager) into .agents/skills/agent-manager-reference in your project. Codex loads it when a task matches its description.

Can I use Agent-Manager Reference API in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add YoanWai/agent-manager --skill agent-manager-reference -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/agent-manager-reference, .gemini/skills/agent-manager-reference, .github/skills/agent-manager-reference and .opencode/skills/agent-manager-reference in your project.

What does Agent-Manager Reference API need to run?

Going by SKILL.md and its folder, Agent-Manager Reference API needs the command-line tools its instructions call (curl). Our summary lists: Network access to agent-manager.dev.

Does Agent-Manager Reference API access the network?

SKILL.md names 1 domain. In commands or code: agent-manager.dev; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.

Is Agent-Manager Reference API safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Agent-Manager Reference API use?

Agent-Manager Reference API is published under the Apache-2.0 licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Agent-Manager Reference API use?

About 689 tokens (SKILL.md is roughly 2.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Agent-Manager Reference API?

Skills that share tags, products or a category with Agent-Manager Reference API: MCP Server Builder (anthropics/skills, 180k stars), MCP Server Builder (shareAI-lab/learn-claude-code, 78k stars), MCP Integration for Plugins (anthropics/claude-plugins-official, 37k stars) and Fastmcp Client CLI (PrefectHQ/fastmcp, 28k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Agent-Manager Reference API?

YoanWai (a GitHub user) maintains it in YoanWai/agent-manager, which has 572 GitHub stars. The repository holds 2 skills in this directory. The repository was last updated on October 6, 2026.

Source: YoanWai/agent-manager on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.