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/jabrena/plinth/create-worktreegit clone --depth 1 https://github.com/jabrena/plinthWhat 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 | $0.00014 | $0.00674 |
| Opus 5 | $0.00007 | $0.00337 |
| Sonnet 5 | $0.00003 | $0.00135 |
| Haiku 4.5 | $0.00001 | $0.00067 |
Grade A, and why
create-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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
create-worktree
Always create a new branch and linked Git worktree for isolated or parallel work without changing the current checkout.
Usage
/create-worktree <issue-or-change|type description> [<target-path>] [<base-reference>]
Accepted Inputs
- An issue/change identifier, or an explicit branch type and description
- Optional preferred target path
- Optional base reference
- Supported branch types:
feat,fix,docs,refactor, andchore - Preferred branch format:
<type>/<issue-or-change>-<kebab-case-description>when an issue or OpenSpec change is available, otherwise<type>/<kebab-case-description> - Fresh-name rule: if the preferred branch name or target path already exists, derive the next unused suffix such as
-2,-3, and continue with the fresh branch/worktree
Owning Agent
@plinth-tech-lead
Associated Capabilities
- Git branch naming and validation
- Git linked worktrees
- Parallel OpenSpec child-change coordination
Workflow
- Resolve the preferred branch name from the issue/change identifier or explicit branch details.
- Resolve an absolute preferred target path and the base reference.
- Resolve the repository default branch and the current branch.
- Verify the current checkout is
mainor the repository default branch before creating the worktree branch. - If the current branch is not
mainor the default branch, stop and ask whether to switch to the default branch, choose a different base, or continue explicitly from the current branch. - Verify the repository and selected base reference are valid before creating anything.
- Derive a fresh branch name and fresh target path when the preferred branch exists, is checked out in another worktree, or the preferred target path exists.
- Verify the final branch name does not exist, is not checked out in another worktree, and the final target path does not exist.
- Run the equivalent of
git worktree add -b <branch> <target-path> <base-reference>. - Report the created branch, absolute worktree path, base reference, and cleanup command.
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 · 68 lines · 14 tokens per session scan A 10f8f9db8b77
create-worktree is a command published in the GitHub repository jabrena/plinth (435 stars, last pushed yesterday), licensed Apache-2.0. It adds 14 tokens to every session and 674 once invoked, about $0.0001 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
ai-do
You are a routing assistant for DSPy AI skills. Understand the user's problem, pick the best skill, and generate a ready-to-run prompt.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
constitution
Create or update the project constitution from interactive or provided principle inputs.