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/drakulavich/kesha-voice-kit/worktreegit clone --depth 1 https://github.com/drakulavich/kesha-voice-kitWrote 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/drakulavich/kesha-voice-kit/worktree)<a href="https://agentmods.dev/commands/drakulavich/kesha-voice-kit/worktree"><img src="https://agentmods.dev/badge/commands/drakulavich/kesha-voice-kit/worktree.svg" alt="Measured on agentmods" 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 | $0.00025 | $0.00316 |
| Opus 5 | $0.00013 | $0.00158 |
| Sonnet 5 | $0.00005 | $0.00063 |
| Haiku 4.5 | $0.00003 | $0.00032 |
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 6d 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.
What it actually says
Run just worktree <slug> [branch] from the root checkout and report where the new tree landed.
Arguments: $ARGUMENTS → first token is <slug> (required), optional second token is the branch name. If the slug is missing, ask for it and stop.
The recipe owns the ritual — fetching origin/main, branching off it rather than off the possibly-stale local main, and refusing to run from inside an existing worktree. Do not reconstruct the git worktree commands here or reach past it.
- The branch defaults to the slug (slug
vad-fix→ branchvad-fix). - If the recipe refuses because you are inside a worktree,
cdto the root checkout and rerun; do not work around it. - If the branch already exists,
git worktree add -bfails — report that rather than picking another name.
Then tell the user to cd .worktrees/<slug>, and that edit/test/commit/PR all happen inside the worktree while cleanup (just worktree-rm <slug>) happens back in the root checkout.
Reference: the worktree recipe in justfile, CLAUDE.md "MAIN STAYS IN THE ROOT CHECKOUT".
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.
- 6d ago First seen · 20 lines · 25 tokens per session scan A f6395d0aa227
worktree is a command published in the GitHub repository drakulavich/kesha-voice-kit (73 stars, last pushed today), licensed MIT. It adds 25 tokens to every session and 316 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
start-talking
Start talking with Cadence Code.
jump-in
Jump In and add spoken guidance.
voice-settings
Choose Cadence Code speech models.
wrap-up
End the active Cadence Code conversation.
upgrade-webkit
Upgrade Bun's WebKit fork to the latest upstream version of WebKit.
audit_docs
Audit all project metadata files for stale counts, version mismatches, broken references, and missing entries. Reports discrepancies without auto-fixing.