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/coderabbitai/git-worktree-runner/testinggit clone --depth 1 https://github.com/coderabbitai/git-worktree-runnerWhat 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 | $0.00766 | $0.00766 |
| Opus 5 | $0.00383 | $0.00383 |
| Sonnet 5 | $0.00153 | $0.00153 |
| Haiku 4.5 | $0.00077 | $0.00077 |
Grade A, and why
git-worktree-runner testing.instructions.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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Testing Instructions
Run after core or adapter changes; all manual (no automated tests).
# Basic create/remove
./bin/gtr new test-feature # folder test-feature
./bin/gtr rm test-feature # removed
# Branch sanitization
./bin/gtr new feature/auth # folder feature-auth
# Remote branch (if exists)
./bin/gtr new existing-remote-branch # checks out tracking branch
# Local existing branch
./bin/gtr new existing-local-branch # reuses local branch
# New branch creation
./bin/gtr new brand-new-feature # creates branch + worktree
# Machine-readable creation (stdout: path, branch, hook_status records)
./bin/gtr new agent-feature --from HEAD --no-fetch --porcelain
# Force multiple worktrees same branch
./bin/gtr new test-feature --force --name backend # test-feature-backend
# Editor + AI adapters
./bin/gtr config set gtr.editor.default cursor
./bin/gtr open test-feature
./bin/gtr config set gtr.ai.default claude
./bin/gtr ai test-feature
# Listing
./bin/gtr list # human table
./bin/gtr list --porcelain # path\tbranch\tstatus
# Navigation
cd "$(./bin/gtr go 1)" # repo root
cd "$(./bin/gtr go test-feature)" # worktree path
# Config commands
./bin/gtr config set gtr.editor.default cursor
./bin/gtr config get gtr.editor.default
./bin/gtr config set gtr.editor.default vscode --global
./bin/gtr config unset gtr.editor.default
# Copy patterns
git config --add gtr.copy.include "**/.env.example"
git config --add gtr.copy.exclude "**/.env"
./bin/gtr new test-copy # copies example, not real env
# Hooks
git config --add gtr.hook.postCreate "echo 'Created!' > /tmp/gtr-test"
./bin/gtr new test-hooks # /tmp/gtr-test exists
git config --add gtr.hook.postRemove "echo 'Removed!' > /tmp/gtr-removed"
./bin/gtr rm test-hooks # /tmp/gtr-removed exists
Installation & Environment Verification
git --version
./bin/gtr doctor # checks repo, adapters, platform
./bin/gtr adapter # lists editors + AI tools
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 · 100 lines · 766 tokens per session scan A 81c5a00d8365
git-worktree-runner testing.instructions.md is an instructions file published in the GitHub repository coderabbitai/git-worktree-runner (1,754 stars, last pushed 5d ago), licensed Apache-2.0. It adds 766 tokens to every session, about $0.0038 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
mulmoterminal CLAUDE.md
Instructions for receptron/mulmoterminal, covering claude.md — mulmoterminal, stack & package manager, run after changes, import a component at module scope, never inside a test and no emojis.
operator-oss CLAUDE.md
Instructions for iishyfishyy/operator-oss, covering claude.md, commands, architecture, the turn lifecycle (core flow) and key modules (by responsibility).
vibe-tree CLAUDE.md
Instructions for sahithvibudhi/vibe-tree, covering claude instructions, github actions failed build logs, electron app startup issues, launch with project and pull requests.
CommandMate CLAUDE.md
Instructions for Kewton/CommandMate, covering claude.md, ⚠️ 重要: モジュール詳細を claude.md に書かないこと, プロジェクト概要, 基本情報 and 技術スタック.
vscode-ext-tmux-worktree AGENTS.md
Instructions for kargnas/vscode-ext-tmux-worktree, covering ai agent guidelines, instruction, tested vs code, 1. codebase understanding and project structure.
CommandMate AGENTS.md
Instructions for Kewton/CommandMate, covering agents.md, scope, project context, working principles and coding rules.