What is API AGENTS.md?

A set of instructions for coding agents working in the Terminal49/API repository. It covers the repository layout, documentation, serverless functions, and MCP server packages.

Useful for work on the Terminal49/API codebase, including its docs, Vercel functions, and MCP server.

It gives an agent the project-specific guidance needed to navigate and change the code correctly.

How Terminal49/API configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to Terminal49/API. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/Terminal49/API/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/Terminal49/API

Made for: Codex, OpenCode.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/terminal49/api/agents-md/github.svg)](https://agentmods.dev/instructions/terminal49/api/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/terminal49/api/agents-md"><img src="https://agentmods.dev/badge/instructions/terminal49/api/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/terminal49/api/agents-md"><img src="https://agentmods.dev/badge/instructions/terminal49/api/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 2,410 This file is loaded in full into every session.

When invoked 2,410 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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 5.1	$0.02410	$0.02410
Opus 5.5	$0.00964	$0.00964
Sonnet 5.5	$0.00482	$0.00482
Haiku 4.5	$0.00241	$0.00241

Measured 15d ago against content hash 917319e08a78, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

API 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 15d 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 · 109 lines

How it starts

The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Terminal49 API repository

This is a public repository. Do not commit API keys, secrets, internal URLs, customer data, or proprietary information. Use placeholders in every example, such as Authorization: Token YOUR_API_KEY.

This file is the only agent-instructions file in the repository. CLAUDE.md is a symlink to it, and Codex and Cursor read it directly. Edit AGENTS.md, never a copy.

What ships from this repo

Four things ship independently from one npm workspaces monorepo (packages/*, sdks/*):

Product	Path	Ships to
Documentation and the OpenAPI spec	`docs/`	Mintlify, through its Git integration
MCP server and OAuth gateway	`api/`, `packages/mcp/` (`@terminal49/mcp`)	`mcp.terminal49.com` on Vercel (`vercel.json`)
TypeScript SDK	`sdks/typescript-sdk/` (`@terminal49/sdk`)	npm
CLI	`sdks/typescript-sdk-cli/` (`@terminal49/cli`)	npm

The MCP server, SDK, and CLI are clients of the Terminal49 API at https://api.terminal49.com/v2. Nothing here runs a long-lived backend.

Where things live

docs/docs.json defines Mintlify navigation, branding, and tabs. Mintlify publishes every Markdown file under docs/, so keep repository notes out of that directory.
docs/openapi.json is the source of truth for the API reference, the SDK types, and the MCP filter schemas.
docs/images/ holds every image that a docs page uses. Pages reference them as /images/<file>.
api/ holds the Vercel functions. api/mcp.ts serves the MCP endpoint (Streamable HTTP, stateless) and resolves caller auth. The other files serve the /.well-known/* discovery documents that vercel.json routes to them.
packages/mcp/src/server.ts builds the server (createTerminal49McpServer()) for both the stdio entry (src/index.ts) and the api/ gateway. Tools are in src/tools/ and resources in src/resources/.
packages/mcp/src/resource.ts is the only place that derives the OAuth resource identifier. The protected-resource metadata and the WWW-Authenticate challenge both call it so they cannot diverge (RFC 9728). Do not derive the resource anywhere else.
skills/ holds repository skills. skills/terminal49-docs-writing/ is the docs-writing standard, and skills/agent-trust/ is the change-verification gate.

Read the full file on GitHub · 109 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.

15d ago Changed · +1 tokens per session 917319e08a78
18d ago Changed · -19 lines · -468 tokens per session b34703ea1e78
19d ago Changed · +8 lines · +235 tokens per session 329f6257e08f
28d ago Changed · +1 lines · +35 tokens per session 4932f9477168
1mo ago Changed · +5 tokens per session 643baaf9081a
1mo ago Changed · +2 lines · +60 tokens per session ddc28f26a53a
2mo ago First seen · 117 lines · 2,542 tokens per session scan A bbfe2b622f80

Subscribe to this mod's changes

API AGENTS.md is an instructions file published in the GitHub repository Terminal49/API (2 stars, last pushed today), licensed MIT. It adds 2,410 tokens to every session, about $0.0096 per session on Opus 5.5. 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.

ais-tracking api container-tracking docs global-trade mcp

API AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
API AGENTS.mdTerminal49/API	Instructions file	2	today	MIT	A	2,410	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

API: Instructions file for Codex