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/typeship-ax/typescript/agents-mdgit clone --depth 1 https://github.com/typeship-ax/typescriptWhat 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 | $0.00538 | $0.00538 |
| Opus 5 | $0.00269 | $0.00269 |
| Sonnet 5 | $0.00108 | $0.00108 |
| Haiku 4.5 | $0.00054 | $0.00054 |
Grade A, and why
typescript 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.
How it starts
The opening of the file, as written. The whole thing — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.
typeship — agent context
This package contains the generated TypeScript SDK for typeship (API v1.0.0, package v1.0.0).
Resolve an OpenAPI or GraphQL Definition, diagnose it, and keep every selected SDK, CLI, and MCP Target current.
Every operation but one requires a bearer credential: an organization API key from the console, or an OAuth access token carrying the operation's read, generate, or write capability and the organization selected during consent. OAuth grants cannot switch organizations after consent. A browser session is not a credential for this API. The exception is POST /generate, which works anonymously with the free plan's limits.
Ground rules
- Generated code: never edit files in this package by hand — changes are lost on regeneration. Wrap the client in your own code instead.
- Zero runtime dependencies; everything runs on platform
fetch(Node 18+, browsers, edge). api.mdis the native method reference;api.jsonis the machine-readable operation, schema, safety, and example contract. Read them before guessing.
Authentication
- TypeScript SDK: pass the
bearerTokenclient option explicitly; the SDK does not read credential environment variables.
Using the SDK
import { TypeshipClient } from "@typeship-ax/sdk";
const client = new TypeshipClient({ /* auth options above */ });
- Awaiting a call returns
ApiResult<T, E>: checkresult.ok, orunwrap(result)to throw the typed error. - Paginated methods return a
PagePromise: awaiting it returns the first page'sApiResult;for await (const item of client.x.list())walks every page and throws the typed API error if a page fails. - Every method takes a last
{ timeoutMs, maxRetries, headers, signal }argument for per-call overrides; every result carriesresponse: { status, headers, requestId }. - Uploads take a
Blob(aFilefor a filename). debug: true(or a function) on the client logs one redacted line per request.
Documentation
- The reference for this exact package:
api.md(offline, always current with the code). - Conceptual guides live on the docs site. For questions about how the API's concepts fit together (flows, ordering, environments), fetch
https://typeship.dev/llms-full.txtand read the relevant sections;https://typeship.dev/llms.txtis the page index.
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 · 37 lines · 538 tokens per session scan A 5af50e01b4c8
typescript AGENTS.md is an instructions file published in the GitHub repository typeship-ax/typescript (0 stars, last pushed 7d ago), licensed MIT. It adds 538 tokens to every session, about $0.0027 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
wjx-ai-kit CLAUDE.md
Instructions for wjxcom/wjx-ai-kit, covering claude.md, what this is, build & test commands, install all workspace dependencies and build (from monorepo root) — cli is the main product.
agent-wallet-sdk AGENTS.md
Instructions for up2itnow0822/agent-wallet-sdk, covering agents.md -- agent wallet sdk, purpose, ownership, local contracts and work guidance.
gram AGENTS.md
AGENTS.md instructions for speakeasy-api/gram, a project described as: Securely scale AI usage across your organization. A single stack to Connect, Secure, Observe and Distribute agents, MCPs, and Skills within your company.
gram GEMINI.md
Gemini CLI instructions for speakeasy-api/gram, a project described as: Securely scale AI usage across your organization. A single stack to Connect, Secure, Observe and Distribute agents, MCPs, and Skills within your company.
unsurf AGENTS.md
Instructions for acoyfellow/unsurf, covering agents.md — unsurf, what this is, stack, architecture and directory.
ts-sdks AGENTS.md
AGENTS.md instructions for Suigar-Gaming/ts-sdks, covering agents.md, common commands, setup and build, initial setup and generate bindings and build the package.