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 instructions/roxyapi/claude-plugin/agents-mdgit clone --depth 1 https://github.com/RoxyAPI/claude-pluginWhat 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 | $0.00457 | $0.00457 |
| Opus 5 | $0.00229 | $0.00229 |
| Sonnet 5 | $0.00091 | $0.00091 |
| Haiku 4.5 | $0.00046 | $0.00046 |
Grade A, and why
claude-plugin AGENTS.md scanned grade A with 0 findings 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 yesterday.
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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
RoxyAPI Claude Code plugin - Agent Guide
This repo is a Claude Code plugin and self hosted marketplace for RoxyAPI, the multi domain spiritual intelligence API. Installing it gives Claude Code a skill plus the keyless Docs MCP for RoxyAPI.
Install
/plugin marketplace add RoxyAPI/claude-plugin
/plugin install roxyapi@roxyapi
What ships
skills/roxyapi/SKILL.md: model invoked skill. Teaches Claude when and how to call RoxyAPI (location first rule,X-API-Keyauth, per domain endpoints, error contract, SDK and Remote MCP paths). Body is the live agent playbook fromhttps://roxyapi.com/AGENTS.md..mcp.json: auto connects the keyless Docs MCP athttps://roxyapi.com/mcp/docs(one tool,search_docs). No key needed..claude-plugin/plugin.jsonand.claude-plugin/marketplace.json: plugin and marketplace manifests.
Generated, not hand written
Every artifact is regenerated from the live OpenAPI spec and /AGENTS.md by scripts/sync.ts. The spec at https://roxyapi.com is the single source of truth. Do not hand edit skills/, .mcp.json, or .claude-plugin/. To change the plugin, change the API.
Live API calls
The Docs MCP is keyless. For live calls add a per domain server with your key:
{ "mcpServers": { "roxy-astrology": { "type": "http", "url": "https://roxyapi.com/mcp/astrology", "headers": { "X-API-Key": "YOUR_KEY" } } } }
Get a key at https://roxyapi.com/account. See https://roxyapi.com/docs/mcp.
Links
- MCP guide: https://roxyapi.com/docs/mcp
- API reference: https://roxyapi.com/api-reference
- SDKs: https://roxyapi.com/docs/sdk
- Pricing: https://roxyapi.com/pricing
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.
- yesterday First seen · 38 lines · 457 tokens per session scan A 782423406419
claude-plugin AGENTS.md is an instructions file published in the GitHub repository RoxyAPI/claude-plugin (1 stars, last pushed 3d ago), licensed MIT. It adds 457 tokens to every session, about $0.0023 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
aurora-agent AGENTS.md
AGENTS.md instructions for AURORA-NEURO/aurora-agent, covering aurora agent, what we can never compromise on, 1. honest labelling is the product, 2. invariants belong in the type system, not in comments and 3. determinism, byte for byte.
aurora-agent CLAUDE.md
Claude Code instructions for AURORA-NEURO/aurora-agent: See AGENTS.md. It is the single source of truth for how to work in this repository; this file exists only so Claude Code finds it by its conventional name.
sap-api-policy-skill CLAUDE.md
Instructions for marianfoo/sap-api-policy-skill, covering claude.md — sap-api-policy-skill, what this repo is, the one invariant — never break this, layout and editing rules.
ue-official-mcp CLAUDE.md
Instructions for tc-imba/ue-official-mcp, covering claude.md, what this is, core invariants — don't break these, common commands and architecture pointers.
msp-skills AGENTS.md
AGENTS.md instructions for Servosity/msp-skills, covering agents.md - msp-skills, what this repo is, before you reprint or re-onboard a connector (read this), when a connector flips to live-verified (read this too) and general.
sap-api-policy-skill AGENTS.md
Instructions for marianfoo/sap-api-policy-skill: This repo's contributor/agent guide lives in CLAUDE.md — read that. It applies to all agents (Claude Code, Codex, Cursor, …), not just Claude.