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/termio-sh/termio/agents-mdgit clone --depth 1 https://github.com/termio-sh/termioWhat 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 | $0.03293 | $0.03293 |
| Opus 5 | $0.01647 | $0.01647 |
| Sonnet 5 | $0.00659 | $0.00659 |
| Haiku 4.5 | $0.00329 | $0.00329 |
Grade A, and why
termio 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.
How it starts
The opening of the file, as written. The whole thing — 265 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This file provides guidance to AI coding agents working in this repository.
Core rules
- termio is a deliberately small, focused tool. Keep the surface area minimal; prefer clarity over cleverness. Do not add features that were not requested.
- Keep changes scoped to the request. Do not refactor unrelated code.
- Respect existing worktree changes. Do not revert the user's edits unless asked.
- Prefer editing existing files over creating new ones. Do not add new documentation files unless requested.
- Commit or push only when the user asks.
- Never add an SPM dependency that ships resources — see "Dependencies" below. This has shipped as a release-only crash twice.
- Read
CONTRIBUTING.mdfor the long-form version of the build, branching, and release flow. This file is the short, agent-facing subset.
Repo overview
termio is a native macOS terminal app for AI coding agents: Swift + AppKit/SwiftUI on top of libghostty (Ghostty's terminal core). It is free software with no backend, no account, and no license server.
Sources/termio— the macOS app (SwiftPM executable target). Organized by feature:Terminal,Sidebar,TermioStore,Agents,Companion,Git,FileBrowser,Editor,Issues,Settings,Welcome,Info,CommandPalette,Keybindings,Browser,Theme,App.Shared/— SwiftPM package (TermioShared) shared by the Mac app and the iOS companion. The companion wire protocol lives here so both ends stay in sync.ios/— the iOS companion app (TermioMobile.xcodeproj, schemeTermioMobile).web/landing— the marketing site (Next.js + Tailwind + shadcn/ui), deployed to Vercel.scripts/—build-app.sh(packages the.app),termio(the CLI that drives a running app over its control socket), plus icon and stats helpers.packaging/—Info.plist, entitlements, icon assets for the bundle.docs/— design docs, RFCs, runbooks, bug handoffs, essays. See "Docs" below.skills/— agent skills. See "Skills" below.
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.
- 2d ago First seen · 265 lines · 3,293 tokens per session scan A f2e0ec37a73d
termio AGENTS.md is an instructions file published in the GitHub repository termio-sh/termio (359 stars, last pushed 2d ago), licensed MIT. It adds 3,293 tokens to every session, about $0.0165 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.
Other instructions, from other repositories
framework AGENTS.md
Instructions for ai-driven-dev/framework, covering agents.md, behavior, communication, action and memory management.
platform CLAUDE.md
Instructions for ambient-code/platform, covering ambient code platform, structure, key files, session flow and commands.
autogen copilot-instructions.md
Copilot instructions for microsoft/autogen, covering autogen multi-agent ai framework, working effectively, prerequisites and environment setup, python development workflow and quick validation (under 1 second each).
toh-framework CLAUDE.md
Instructions for wasintoh/toh-framework, covering claude.md — toh framework (repo development guide), what this is, everyday commands, verification protocol and single source, transformed per ide.
jentic-one GEMINI.md
Instructions for jentic/jentic-one: Otherwise, read AGENTS.md — this repo's canonical agent guidance.
hatch3r CLAUDE.md
Instructions for hatch3r/hatch3r, covering hatch3r — development instructions, architecture, development commands, two-axis pillar framework (2.0.0) and orchestrator self-discipline (bypass protection).