ghfs AGENTS.md

A set of repository and interface rules for ghfs, including where different code belongs and how keyboard access should work. It covers the command-line tool, GitHub integration, utilities, tests, and user-interface controls.

In plain words
What is it for?
Changing ghfs command-line behavior, GitHub providers, utility functions, tests, or the interface while following the project's file boundaries and keyboard-accessibility requirements.
Why use it?
It helps agents place changes in the correct modules and avoid duplicating logic. It also ensures buttons, inputs, shortcuts, and other interactive elements can be used without a mouse.

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

Made for: Codex, OpenCode.

Per session 2,139 This file is loaded in full into every session.
When invoked 2,139 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.

ModelPer sessionOnce invoked
Fable 5 $0.02139 $0.02139
Opus 5 $0.01069 $0.01069
Sonnet 5 $0.00428 $0.00428
Haiku 4.5 $0.00214 $0.00214

Measured 2d ago against content hash e868beb83fba, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ghfs 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 · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Rules

  • CLI related logics, usage of @clack/prompts, console.log can only be under src/cli/
  • GitHub related logics, usage of octokit can only be under src/providers/github/
  • Pure/simple functions should better be under src/utils/ and be tested alongside.
  • Avoid duplicating logics, refactor them to reuse.
  • Always use pathe instead of node:path
  • At this moment, we don't care about breaking changes at all, don't worry about migration or backward compatibility.

Keyboard accessibility (UI)

  • Every interactive element under ui/ must be operable without a mouse. When adding a button, tab, pill, or dialog action, pair it with either (a) native Tab + Enter/Space — the default focus ring must be visible — or (b) a command registered in ui/composables/useAppCommands.ts, and render <Kbd command="..." /> next to it so the binding is discoverable.
  • Text inputs & textareas get a single-key focus shortcut (e.g. / for search, n for comment). Escape already blurs focused inputs globally via ui/composables/useCommandHandler.ts — do not re-implement it. Tag the element with data-shortcut="<id>" so the command's run() can querySelector it.
  • Submit-from-input (e.g. Cmd/Ctrl + Enter on a textarea): add a local @keydown.meta.enter / @keydown.ctrl.enter handler on the element. The global handler routes modifier combos to keybindings (e.g. mod+k opens the command palette); element-local Cmd/Ctrl+Enter handlers are still preferred for textarea submit so the registry stays focused on app-level actions.
  • Prefer single-key shortcuts. The handler supports multi-key sequences via an 800 ms tail-match buffer (longer sequences win), and modifier combos via mod+x / mod+shift+x (alias mod resolves to Cmd on Mac, Ctrl elsewhere). Multi-key bindings are reserved for cases where every reasonable single letter already collides.
  • Gate commands declaratively via the when field — a whenexpr string evaluated against useWhenContext() (e.g. 'hasActiveItem && activeItemState == "open"'). Add a new key to WhenContext in ui/composables/useWhenContext.ts rather than reaching for a JS predicate.
  • Every command is callable from the command palette (mod+k / mod+shift+p). Use help: false on internal palette commands to keep them out of <HelpOverlay>, or help: '<when>' to scope visibility (e.g. help: 'hubMode').
  • Every new btn-* variant in ui/uno.config.ts must include outline-none focus-visible:ring-2 focus-visible:ring-primary-500/40, matching the existing tab-trigger shortcut.
  • The ? help overlay (ui/components/HelpOverlay.vue) auto-renders every registered command grouped by its category — keep each command title short and user-facing.

Read the full file on GitHub · 66 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 · 66 lines · 2,139 tokens per session scan A e868beb83fba

Subscribe to this mod's changes

ghfs AGENTS.md is an instructions file published in the GitHub repository antfu/ghfs (271 stars, last pushed 2mo ago), licensed MIT. It adds 2,139 tokens to every session, about $0.0107 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.

Related

Other instructions, from other repositories

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

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

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