wt AGENTS.md

AGENTS.md instructions for timvw/wt, covering guidelines for ai coding agents, golden rule: use worktrees!, ❌ don't: switch branches in the main repository, bad - don't do this! and ✅ do: create worktrees for each task.

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

Made for: Codex, OpenCode.

Per session 2,193 This file is loaded in full into every session.
When invoked 2,193 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin unknown 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 $0.02193 $0.02193
Opus 5 $0.01097 $0.01097
Sonnet 5 $0.00439 $0.00439
Haiku 4.5 $0.00219 $0.00219

Measured today against content hash b06c3c515437, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

wt 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 today.

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 · 321 lines

How it starts

The opening of the file, as written. The whole thing — 321 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Guidelines for AI Coding Agents

This document provides guidelines for AI coding agents (like Claude Code, Cursor, GitHub Copilot, etc.) working on the wt project.

Golden Rule: Use Worktrees!

IMPORTANT: As an AI agent, you should practice what this tool preaches - use worktrees for your work!

❌ DON'T: Switch branches in the main repository

# BAD - Don't do this!
cd /path/to/main/wt/repo
git checkout -b feature/new-branch

This leaves the user's main working directory on a feature branch.

✅ DO: Create worktrees for each task

# GOOD - Use wt to create isolated worktrees!
wt create feature/new-branch
# This creates: ~/dev/worktrees/wt/feature/new-branch
# Main repo stays on main branch

Agent Workflow

1. Starting New Work

When beginning a new feature or fix:

# Create a worktree for your feature
wt create feat/your-feature-name

# The worktree is automatically checked out to:
# ~/dev/worktrees/wt/feat/your-feature-name

2. Working in the Worktree

All file operations (Read, Write, Edit) should use paths in the worktree:

# Work in the worktree location
/Users/username/dev/worktrees/wt/feat/your-feature-name/

# NOT in the main repo:
# /Users/username/src/github/wt/  ❌

3. Committing and Creating PRs

# From within the worktree directory
git add .
git commit -m "feat: your feature description"
git push -u origin feat/your-feature-name

# Create PR
gh pr create --title "feat: your feature" --body "Description"

4. Cleaning Up

After the PR is merged:

# Remove the worktree
wt remove feat/your-feature-name
# or use the short alias:
wt rm feat/your-feature-name

Why This Matters for Agents

Benefits of Worktree-based Workflow

  1. Non-disruptive: User's main repository stays on main branch
  2. Isolated: Each feature gets its own directory
  3. Parallel work: Can work on multiple features simultaneously
  4. Clean state: No branch switching confusion
  5. Predictable: Always know where files are located

Read the full file on GitHub · 321 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. today First seen · 321 lines · 2,193 tokens per session scan A b06c3c515437

Subscribe to this mod's changes

wt AGENTS.md is an instructions file published in the GitHub repository timvw/wt (55 stars, last pushed 3d ago), licensed MIT. It adds 2,193 tokens to every session, about $0.0110 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 2026-09-01.

Related

Other instructions, from other repositories

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

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

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

spec-kit 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 · 7,040 tokens

langchain 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