termcast AGENTS.md

Project instructions for Termcast, a tool that ports Raycast's developer interface to a different runtime. They specify coding conventions, dependency commands, file types, testing commands, and how to separate supported APIs.

In plain words
What is it for?
Use them when adding Termcast components, hooks, APIs, TypeScript files, tests, dependencies, or ported Raycast functionality.
Why use it?
They keep changes consistent with the repository and prevent common mistakes such as using the wrong imports, test commands, or package manager.

Instructions file for CodexOpenCode

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/remorses/termcast/agents-md
Clone the repo
git clone --depth 1 https://github.com/remorses/termcast

Made for: Codex, OpenCode.

Per session 13,726 This file is loaded in full into every session.
When invoked 13,726 The same file — it is already loaded in full.
Security scan A 1 finding. 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.

ModelPer sessionOnce invoked
Fable 5 $0.13726 $0.13726
Opus 5 $0.06863 $0.06863
Sonnet 5 $0.02745 $0.02745
Haiku 4.5 $0.01373 $0.01373

Measured 2d ago against content hash 974701b9109b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

termcast AGENTS.md 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 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -s https://developers.raycast.com/api-reference/user-interface/list.md
AGENTS.md · 1,333 lines

How it starts

The opening of the file, as written. The whole thing — 1,333 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Project Coding Guidelines

NOTICE: AGENTS.md is generated using pnpm agents.md and should NEVER be manually updated. only update PREFIX.md

ALWAYS use pnpm to install dependencies


termcast specific rules

Porting @raycast/api components and hooks to termcast

ALWAYS use termcast to import things, instead of relative imports. This is possible thanks to exports in package.json. for example:

import {List} from 'termcast'

ALWAYS use .tsx extension for every new file.

NEVER use mocks in vitest tests

When running the e2e vitest suite, ALWAYS use the repo scripts (pnpm e2e, pnpm e2e <file>, pnpm e2e -u). NEVER run vitest directly.

prefer object args instead of positional args. as a way to implement named arguments, put the typescript definition inline

see files in the repo

use git ls-files | tree --fromfile to see files in the repo. this command will ignore files ignored by git

Goal

This project ports @raycast/api components and apis to use @opentui/react and other Bun APIs

We are basically implementing the package @raycast/api from scratch. DO NOT implement functions exported by @raycast/utils

This should be done one piece at a time, one hook and component at a time

Porting a new Raycast component or feature

Here is the process to follow to implement each API:

  • decide which component or hook or function we are porting
  • read the .d.ts of the @raycast/api package for the component or hook
  • generate a new file or decide to which file to add this new API in src folder
  • start by adding a signature without any actual implementation. Only a function or class or constant without any actual implementation
  • try typechecking with pnpm run tsc. fix any errors that is not related to the missing implementation (like missing returns)
  • then think, is the signature the same as Raycast?
  • start implementing the component or function, before doing this
    • decide on what @opentui/react components to use
    • do so by reading opentui .d.ts files and see available components
    • read .d.ts to understand available styling options and attributes
  • typecheck
  • if the added feature is a component or adds support for a new prop for a component, add an example usage component in the src/examples directory. create a descriptive name for it in the file. use simple-{component-name} for basic implementations examples
  • if the implemented feature is function or other API, add an action in the file examples/miscellaneus.tsx, add a list item for the new feature, for example "show a error toast" if we are implementing toasts
  • do not add an example if our feature is already covered by other example files
  • DO NOT run the examples then. instead ask me to do it. do not add these as scripts in package.json
  • typecheck to make sure the example is correct

Read the full file on GitHub · 1,333 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.

  1. 2d ago First seen · 1,333 lines · 13,726 tokens per session scan A 974701b9109b

Subscribe to this mod's changes

termcast AGENTS.md is an instructions file published in the GitHub repository remorses/termcast (337 stars, last pushed 20d ago), licensed MIT. It adds 13,726 tokens to every session, about $0.0686 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.

Related

Other instructions, from other repositories

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,345 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

next.js AGENTS.md

Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens