Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/yoanwai/agent-manager/agent-manager-referencenpx skills add YoanWai/agent-manager --skill agent-manager-referencegit clone --depth 1 https://github.com/YoanWai/agent-managerWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/yoanwai/agent-manager/agent-manager-reference)<a href="https://agentmods.dev/skills/yoanwai/agent-manager/agent-manager-reference"><img src="https://agentmods.dev/badge/skills/yoanwai/agent-manager/agent-manager-reference.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00045 | $0.00661 |
| Opus 5 | $0.00023 | $0.00331 |
| Sonnet 5 | $0.00009 | $0.00132 |
| Haiku 4.5 | $0.00005 | $0.00066 |
Grade A, and why
agent-manager-reference scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -H "Accept: text/markdown" https://agent-manager.dev/docs/install/ How it starts
The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
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:
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.
| Endpoint | Returns |
|---|---|
GET /api |
Every endpoint, with its operationId |
GET /api/docs |
Every 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/agents |
The coding CLIs with built-in status detection |
GET /api/mcp/tools |
The tools the agent-manager binary exposes |
GET /api/release |
The newest release and its install commands |
POST /api/batch |
Several 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.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 4d ago First seen · 73 lines · 45 tokens per session scan A 400f5abdf2e6
agent-manager-reference is a skill published in the GitHub repository YoanWai/agent-manager (391 stars, last pushed yesterday), licensed Apache-2.0. It adds 45 tokens to every session and 661 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
verify-pr
This skill should be used to run a sandboxed deep verification of a qwen-code PR — "/verify-pr ", "深度验证这个 PR", A/B load-bearing proof against the base build, mock-free harnesses with wire oracles, and targeted gates — producing tmp/pr -verify- /report.md plus a machine-readable verdict. Designed for the token-free CI…
cua-driver
Drive a native GUI app (macOS, Windows, Linux) via the Qwen Cua Driver CLI (default) or MCP server; snapshot its accessibility tree, act through snapshot-bound element tokens, native menu paths, exact window geometry, or pixel coordinates, and verify from fresh state. Use when the user asks you to operate, drive…
codegraph
Analyze indexed codebases via graph database (neug) and vector index (zvec). Covers call graphs, dependencies, dead code, hotspots, module coupling, architecture reports, semantic search, impact analysis, bug root cause from GitHub issues, class diagrams (UML), and PR review (risk scoring, conflict detection…
goal-draft
Turn a fuzzy intention into a /goal objective the Goal verifier can actually judge - one outcome, numbered binary "Done when" checks that leave evidence in the transcript, guardrails, a budget, and a block protocol. Use when the user wants to set or define a goal, asks whether a goal is good enough, or says "keep…
stuck
Diagnose frozen, stuck, or slow Qwen Code sessions on this machine. Scans for problematic processes, high CPU/memory usage, hung subprocesses, and debug logs. Use /stuck or /stuck to focus on a specific process.
e2e-testing
Guide for running end-to-end tests of the Qwen Code CLI, including headless mode, MCP server testing, and API traffic inspection. Use this skill whenever you need to verify CLI behavior with real model calls, reproduce user-reported bugs end-to-end, test MCP tool integrations, or inspect raw API request/response…