What is contextgo AGENTS.md?

A set of coding rules for ContextGo, covering file structure, naming, components, utilities, hooks, UI controls, and icons. It also points agents to the architecture guidance needed for structural changes.

Use it when adding or changing ContextGo files, modules, components, styles, hooks, or shared utilities. It guides naming, directory layout, interactive UI components, and icon usage.

It keeps the codebase organized and makes new code fit existing conventions. The directory-size and UI-library rules help avoid scattered structure and inconsistent interfaces.

contextgo AGENTS.md — Instructions file by contextgo

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/contextgo/contextgo/agents-md

Clone the repo

git clone --depth 1 https://github.com/contextgo/contextgo

Made for: Codex, OpenCode.

Per session 3,163 This file is loaded in full into every session.

When invoked 3,163 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	$0.03163	$0.03163
Opus 5	$0.01581	$0.01581
Sonnet 5	$0.00633	$0.00633
Haiku 4.5	$0.00316	$0.00316

Measured yesterday against content hash c67c1ddd915d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

contextgo 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.

AGENTS.md · 233 lines

How it starts

The opening of the file, as written. The whole thing — 233 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ContextGo - Project Guide

Code Conventions

File & Directory Structure

Directory size limit: A single directory must not exceed 10 direct children (files + subdirectories). Split by responsibility when approaching this limit.

See docs/conventions/file-structure.md for complete rules on directory naming, page module layout, and shared vs private code placement. Agents working in this repository must also read and follow the architecture skill (.claude/skills/architecture/SKILL.md) when creating files, modules, or making structure decisions.

Naming

Components: PascalCase (Button.tsx, Modal.tsx)
Utilities: camelCase (formatDate.ts)
Hooks: camelCase with use prefix (useTheme.ts)
Constants files: camelCase (constants.ts) — values inside use UPPER_SNAKE_CASE
Type files: camelCase (types.ts)
Style files: kebab-case or ComponentName.module.css
Unused params: prefix with _

UI Library & Icons

Components: @arco-design/web-react — no raw interactive HTML (<button>, <input>, <select>, etc.)
Icons: @icon-park/react
Icon alignment: renderer entry must keep @icon-park/react/styles/index.css imported globally; for icon+text rows, menu items, and icon buttons, use the shared classes in src/renderer/styles/icon.css (app-icon, app-icon-slot, app-icon-row, app-icon-button) instead of per-component marginTop / inline lineHeight fixes

CSS

Prefer UnoCSS utility classes; complex styles use CSS Modules (ComponentName.module.css)
Colors must use semantic tokens from uno.config.ts or CSS variables — no hardcoded values
Arco overrides go in the component's CSS Module via :global() — no global override files
Global styles only in src/renderer/styles/

See docs/conventions/file-structure.md for full CSS and UI library rules.

TypeScript

Strict mode enabled — no any, no implicit returns
Use path aliases: @/*, @process/*, @renderer/*, @worker/*
Prefer type over interface (per Oxlint config)
English for code comments; JSDoc for public functions

Read the full file on GitHub · 233 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.

yesterday First seen · 233 lines · 3,163 tokens per session scan A c67c1ddd915d

Subscribe to this mod's changes

contextgo AGENTS.md is an instructions file published in the GitHub repository contextgo/contextgo (54 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 3,163 tokens to every session, about $0.0158 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.

Frontend Planning

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

buildNext

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

contextgo AGENTS.md