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 commands/taoidle/plan-cascade/worktreegit clone --depth 1 https://github.com/Taoidle/plan-cascadeWhat 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 | $0.00065 | $0.02852 |
| Opus 5 | $0.00032 | $0.01426 |
| Sonnet 5 | $0.00013 | $0.00570 |
| Haiku 4.5 | $0.00006 | $0.00285 |
Grade A, and why
worktree 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 — 361 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Planning with Files - Git Worktree Mode
You are now starting a task in Git Worktree Mode. This creates an isolated environment for your task with its own branch and directory, enabling parallel multi-task development.
Path Storage Modes
Plan Cascade supports two path storage modes for runtime files:
New Mode (Default)
Runtime files are stored in a user directory, keeping the project root clean:
- Windows:
%APPDATA%/plan-cascade/<project-id>/.worktree/ - Unix/macOS:
~/.plan-cascade/<project-id>/.worktree/
Where <project-id> is a unique identifier based on the project name and path hash (e.g., my-project-a1b2c3d4).
Legacy Mode
Files are stored in the project root for backward compatibility:
- Worktrees:
<project-root>/.worktree/
To check which mode is active, use:
uv run python -c "from plan_cascade.state.path_resolver import PathResolver; from pathlib import Path; r=PathResolver(Path.cwd()); print('Mode:', 'legacy' if r.is_legacy_mode() else 'new'); print('Worktree dir:', r.get_worktree_dir())"
Note: User-visible files like findings.md and progress.md remain in the worktree directory itself, not in the user data directory.
What is Git Worktree Mode?
Git worktree allows you to have multiple working trees attached to the same repository, each on a different branch. This means:
- Multiple tasks, no conflicts: Each task works in its own directory
- No branch switching: Stay on your main branch while working on feature branches
- Isolated environments: Each task has its own files and planning documents
- Easy cleanup: When done, merge and remove the worktree
Step 1: Determine Configuration
First, check for existing worktrees:
git worktree list
If there are existing worktrees, show them to the user and ask if they want to create another one.
Step 2: Parse Parameters
Parse the user's command arguments:
- Task name:
{{args}}- First argument (or usetask-YYYY-MM-DD-HHMMformat for uniqueness) - Target branch: Second argument (or auto-detect
main/master)
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 · 361 lines · 65 tokens per session scan A 6c63815e522b
worktree is a command published in the GitHub repository Taoidle/plan-cascade (124 stars, last pushed 5mo ago), licensed MIT. It adds 65 tokens to every session and 2,852 once invoked, about $0.0003 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 commands, from other repositories
conv_release
Command "conv_release" from John-Wendell/Attention-MoA, covering chatbot arena conversations, all conversations and prompt distribution.
data_cleaning
Command "data_cleaning" from John-Wendell/Attention-MoA, covering data cleaning, requirements, steps, convert html to markdown and keep or remove specific languages.
pypi
Command "pypi" from John-Wendell/Attention-MoA, covering requirement and upload.
local_cluster
node-01.
webserver
Command "webserver" from John-Wendell/Attention-MoA, covering install, launch servers, check the launch time, increase the limit of max open files and gradio edit (3.35.2).
leaderboard
Command "leaderboard" from John-Wendell/Attention-MoA, covering get logs, clean battle data, run elo analysis, copy files to hf space and update files on webserver.