TEDI: Instructions file for Codex

AGENTS.md

TEDI AGENTS.md is an instructions file for Codex, OpenCode from IlhamriSKY/TEDI. It costs 2,959 tokens per session, scanned A, original, Apache-2.0.

Repository instructions for TEDI, a cross-platform terminal and editor built with Tauri, Rust, React and TypeScript. They document its commands, code layout and development rules.

In plain words
What is it for?
Use them when developing TEDI to run type checks, linting, builds, Rust checks and tests, and to understand where its terminal, editor, desktop and web-interface code lives.
Why use it?
They give coding agents the project-specific checks and conventions needed to make safe changes without guessing how the repository works.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions AGENTS.md.

This is IlhamriSKY/TEDI's own configuration. It tells Codex and OpenCode how to work on TEDI itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything TEDI configures →

Reuse

Borrowing it

Nothing to install: this file belongs to IlhamriSKY/TEDI. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/IlhamriSKY/TEDI/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/IlhamriSKY/TEDI

Made for: Codex, OpenCode.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for TEDI AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/ilhamrisky/tedi/agents-md/github.svg)](https://agentmods.dev/instructions/ilhamrisky/tedi/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/ilhamrisky/tedi/agents-md"><img src="https://agentmods.dev/badge/instructions/ilhamrisky/tedi/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for TEDI AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/ilhamrisky/tedi/agents-md"><img src="https://agentmods.dev/badge/instructions/ilhamrisky/tedi/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,959 This file is loaded in full into every session.
When invoked 2,959 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.02959 $0.02959
Opus 5.5 $0.01184 $0.01184
Sonnet 5.5 $0.00592 $0.00592
Haiku 4.5 $0.00296 $0.00296

Measured 1mo ago against content hash 761bdd5c5c99, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

TEDI 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 1mo 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 · 199 lines

How it starts

The opening of the file, as written. The whole thing — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.

TEDI

Cross-platform terminal with split panes, tab groups, workspaces, a CodeMirror editor, a BYOK AI agent and a runtime extension system. Tauri 2 + Rust owns every OS resource; a React 19 webview owns the UI. Forked from Crynta/Terax v0.5.9.

Stack: Tauri 2, Rust (portable-pty, russh), React 19 + TS, xterm.js (WebGL), CodeMirror 6, shadcn/ui, Tailwind v4, @ai-sdk/* v6. Package manager is pnpm.

Commands

pnpm exec tsc --noEmit    # frontend types
pnpm lint:imports         # module import discipline
pnpm verify               # the invariant suite; `pnpm verify ai` filters to one folder
pnpm build                # frontend build
pnpm tauri:dev            # dev, ISOLATED data dir (`pnpm tauri dev` shares prod data)
pnpm tauri:dev:ext        # same, plus symlink local extensions/ into the dev profile
cd src-tauri && cargo check && cargo clippy && cargo test

CI runs exactly those. It does not run pnpm format:check, which already fails on files nobody touched, so format only your own paths (pnpm exec prettier --write <files>) and never repo-wide pnpm format.

Where things live

  • src-tauri/src/lib.rs: every Tauri command (invoke_handler), app boot and CLI dispatch.
  • src-tauri/src/modules/: one folder or file per OS resource. pty/ runs terminals and pty_daemon/ is the sidecar that keeps them alive across a window close; also fs/, shell/, git/, ssh/, extensions/, browser/, and mcp_bridge.rs (the local socket outside AI CLIs connect through).
  • src/app/App.tsx: cross-module wiring only.
  • src/modules/<area>/: every feature. ai/ is the agent, terminal/ the xterm side, tabs/ + panes/ + workspaces/ the layout model, extensions/ the extension host, automation/bridge.ts everything an outside driver may call in-realm.
  • src/settings/: the Settings window, a SEPARATE webview. Its state layer is src/modules/settings/, shared with the main window through the store.
  • scripts/: the verify suite (one folder per subsystem), mcp/ (the stdio MCP server and its shared tool table) and release/.
  • extensions/: gitignored working copies of the extension repos. Only README.md, tedi.d.ts and manifest.schema.json are committed here.

Read the full file on GitHub · 199 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. 1mo ago First seen · 199 lines · 2,959 tokens per session scan A 761bdd5c5c99

Subscribe to this mod's changes

TEDI AGENTS.md is an instructions file published in the GitHub repository IlhamriSKY/TEDI (169 stars, last pushed 2d ago), licensed Apache-2.0. It adds 2,959 tokens to every session, about $0.0118 per session on Opus 5.5. 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 2026-09-20.

Related

Other instructions, from other repositories