What is Agentkey AGENTS.md?

A set of repository instructions for AgentKey, a service that lets coding agents access live external data through one connection.

Use it when developing or documenting AgentKey, testing changes across supported agents, or setting up its skill and MCP server.

It clarifies the project structure, installation steps, and the separate roles of the agent instructions and the remote service.

Agentkey AGENTS.md — Instructions file by chainbase-labs

Install

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.

agentmods

npx agentmods add instructions/chainbase-labs/agentkey/agents-md

Clone the repo

git clone --depth 1 https://github.com/chainbase-labs/Agentkey

Made for: Codex, OpenCode.

Per session 3,953 This file is loaded in full into every session.

When invoked 3,953 The same file — it is already loaded in full.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.03953	$0.03953
Opus 5	$0.01976	$0.01976
Sonnet 5	$0.00791	$0.00791
Haiku 4.5	$0.00395	$0.00395

Measured 2d ago against content hash 99c8cd6a00a6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Agentkey 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 2d 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.

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.

AGENTS.md · 148 lines

How it starts

The opening of the file, as written. The whole thing — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

This file provides guidance to coding agents (Codex, and any AGENTS.md-aware tool) when working with code in this repository. It mirrors .claude/CLAUDE.md — keep the two in sync.

What This Repo Is

AgentKey Skill ships the agent-side half of AgentKey: a single skill that teaches agents how to call the AgentKey MCP tools correctly.

AgentKey has two pieces and a full end-user install is two commands:

npx skills add chainbase-labs/agentkey — installs this skill. It does NOT register the MCP server.
npx -y @agentkey/cli --auth-login — runs the AgentKey CLI (@agentkey/cli from ../AgentKey-Server/cli). It mints an API key via device-code login and writes a remote-HTTP MCP block (pointing at https://api.agentkey.app/v1/mcp) into agent configs (Claude Code, Codex, Cursor, and 13 more). The hosted MCP server itself lives at /v1/mcp on AgentKey-Server.

The skill is useless without the MCP server; the MCP server works without the skill but the agent won't know to prefer it over built-in web search. Keep this mental model when editing docs — do not let either command drift into claiming it does both.

The same repo also works as:

a Claude Code plugin (.claude-plugin/plugin.json + root .mcp.json) — the remote HTTP entry has no static authentication header, so Claude Code follows the server's 401/RFC 9728 metadata into its native MCP OAuth flow, substituting for step 2.
a Codex plugin (.codex-plugin/plugin.json + .codex-plugin/mcp.json, distributed through .agents/plugins/marketplace.json; the repo is its own marketplace: codex plugin marketplace add chainbase-labs/agentkey). Codex plugins have no userConfig/header-interpolation mechanism, so auth uses MCP OAuth via the server's RFC 9728 metadata discovery (type + url only in mcp.json), substituting for step 2.
a Cursor plugin (.cursor-plugin/plugin.json). The Cursor-native manifest bundles skills/ and an inline remote-HTTP MCP entry. Cursor authenticates through the server's MCP OAuth discovery, substituting for step 2.
a Kimi Code plugin (.kimi-plugin/plugin.json). Kimi requires mcpServers to be an inline object in the manifest. The remote AgentKey endpoint uses Kimi's native MCP OAuth flow; after install Kimi shows the standard /reload hint, then the user signs in with /mcp-config login plugin-agentkey:agentkey when Kimi reports that OAuth is required.
a Gemini CLI extension (root gemini-extension.json + skills/). Gemini requires the manifest at the extension root, discovers bundled agent skills automatically, and connects to AgentKey with httpUrl plus native MCP OAuth discovery. oauth.enabled requests the browser flow automatically; /mcp auth agentkey is the manual fallback. Either substitutes for step 2.
an Antigravity 2.0 and Antigravity CLI plugin (root plugin.json + mcp_config.json + skills/). Both runtimes use the same package, require serverUrl for remote MCP, and authenticate through automatic OAuth discovery.
a CLI-managed DeepSeek Harness integration. The installers detect ${DSH_HOME:-~/.dsh} / dsh, install the skill globally through the Skills CLI's universal target (never skills add -a dsh), and let @agentkey/cli --auth-login --only dsh maintain one marked @deepseek-ai/dsh-mcp-client entry in $DSH_HOME/cordis.patch.yml. DSH composes that home layer over current and future profiles; running processes watch it through HMR. DSH rc.7 has no MCP OAuth authProvider, so this path requires the CLI-written Bearer key. Tool policy may still hide tools.

Read the full file on GitHub · 148 lines

Changes

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.

2d ago First seen · 148 lines · 3,953 tokens per session scan A 99c8cd6a00a6

Subscribe to this mod's changes

Agentkey AGENTS.md is an instructions file published in the GitHub repository chainbase-labs/Agentkey (625 stars, last pushed 8d ago), licensed Apache-2.0. It adds 3,953 tokens to every session, about $0.0198 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 2026-08-30.

dsh-plugin gemini-cli-extension

Agentkey AGENTS.md

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

AGENTS.md

What This Repo Is

What this file has done since we first saw it

Other instructions, from other repositories

skills AGENTS.md

notfair-plugin AGENTS.md

superdesign-skill AGENTS.md

domscribe CLAUDE.md

iPolloWork AGENTS.md

seektty AGENTS.md