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.
git clone --depth 1 https://github.com/aegntic/cldcdeWrote 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.
[](https://agentmods.dev/commands/aegntic/cldcde/worktree-create)<a href="https://agentmods.dev/commands/aegntic/cldcde/worktree-create"><img src="https://agentmods.dev/badge/commands/aegntic/cldcde/worktree-create/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.
<a href="https://agentmods.dev/commands/aegntic/cldcde/worktree-create"><img src="https://agentmods.dev/badge/commands/aegntic/cldcde/worktree-create.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00000 | $0.00149 |
| Opus 5.5 | $0.00000 | $0.00060 |
| Sonnet 5.5 | $0.00000 | $0.00030 |
| Haiku 4.5 | $0.00000 | $0.00015 |
Grade A, and why
worktree-create 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.
This is a copy
100% identical to worktree-create — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
Create a git worktree for parallel development on a separate branch without stashing.
Steps
- Verify the current repository supports worktrees:
- Determine the worktree configuration:
- Create the worktree:
- Set up the worktree environment:
- List active worktrees with
git worktree list. - Provide the path and instructions to switch to the new worktree.
Format
Worktree Created:
Path: <absolute path>
Branch: <branch name>
Base: <parent branch>
Rules
- Always create worktrees outside the main repository directory.
- Use descriptive branch names following project conventions.
- Do not copy .env files with secrets to worktrees.
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.
- 1mo ago First seen · 30 lines · 0 tokens per session scan A 5fafc64a8569
worktree-create is a command published in the GitHub repository aegntic/cldcde (12 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 149 tokens. A static security scan graded it A with 0 findings. It is 100% identical to worktree-create, differing in 0 lines, and is treated as a copy.
Other commands, from other repositories
git-commit
IMPORTANT: This command ONLY runs when explicitly invoked via /commit. Do NOT auto-commit after code modifications. Wait for user to explicitly run /commit.
scriptwriter-open
Open a REAL RECOGNISE REAL cascade with a peer at depth 1. Signs the canonical bytes locally, pushes the signed turn to the peer's /rrr/turn endpoint, records the cascade in this node's state.
scriptwriter-pair
Discover a peer scriptwriter node's /.well-known/scriptwriter descriptor and send a signed first-contact knock. Confirms the peer is reachable, verifies they speak the protocol, and exchanges greetings.
scriptwriter-status
Print a one-shot snapshot of this scriptwriter node — DID + handle + vibe, every active cascade (with depth + your-turn flag), every local room (with contribution counts). Use when the user wants to "see where they are" in the substrate.
customer-changelog-check
Audit whether user-visible changes in the current session have matching CHANGELOG.md entries; report MISSING with suggested lines; --fix auto-appends.
sync-claude
Update the vendored control plane + core commands in this repo to the latest heymegabyte/claude-bootstrap. Fires when the shared brain has moved on.