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 skills add murray17/rovai-ai --skill worktreegit clone --depth 1 https://github.com/murray17/rovai-aiWrote 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/skills/murray17/rovai-ai/worktree)<a href="https://agentmods.dev/skills/murray17/rovai-ai/worktree"><img src="https://agentmods.dev/badge/skills/murray17/rovai-ai/worktree/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/skills/murray17/rovai-ai/worktree"><img src="https://agentmods.dev/badge/skills/murray17/rovai-ai/worktree.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00055 | $0.00807 |
| Opus 5.5 | $0.00022 | $0.00323 |
| Sonnet 5.5 | $0.00011 | $0.00161 |
| Haiku 4.5 | $0.00006 | $0.00081 |
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 20d 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Git Worktree
Use one reusable branch and worktree per logical change. Follow repository and user rules. Run later commands and edits in the selected worktree. Respond in the user's language.
Do not silently stash, move uncommitted work, overwrite directories, or force-delete branches or worktrees.
Inspect and reuse
git rev-parse --show-toplevel
git status --short --branch
git worktree list --porcelain
git branch --list
Read relevant repository instructions. Determine whether the current worktree fits the task, the target branch is checked out elsewhere, an existing branch/directory can be reused, uncommitted work is required, or governance documents must precede coding.
If uncommitted changes must move, ask the user to choose committing, making a patch, or staying in the current worktree. Do not transport them silently.
Conditional governance baseline
Only when repository or user rules require governance documents to enter the mainline before coding:
- Identify the actual mainline; do not assume
main. - Use its existing clean checkout and synchronize according to repository rules without overwriting other work.
- Change only required governance documents, run documentation gates, and commit them separately on the mainline.
- Record the immutable commit SHA as the coding baseline.
- Bring an empty coding worktree to that baseline. If it already contains code, integrate by the repository's merge rules without rewriting history.
If permissions or dirty state prevent this safely, report the obstacle before coding.
Select branch, base, and directory
Prefer user-specified names and repository conventions; otherwise use a short task slug with feat/, fix/, docs/, chore/, or work/ as appropriate.
Choose the base in this order: required governance commit, explicit user choice, repository rule, related branch, then current HEAD. Clarify a choice that materially changes the work. Fetch only when requested for freshness or required by repository rules; disclose an offline baseline.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 20d ago Changed · -119 lines · -11 tokens per session 2f9b586f08b5
- 1mo ago First seen · 182 lines · 66 tokens per session scan A 46f70637dd64
worktree is a skill published in the GitHub repository murray17/rovai-ai (201 stars, last pushed today), licensed MIT. It adds 55 tokens to every session and 807 once invoked, about $0.0002 per session on Opus 5.5. 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 skills, from other repositories
git-commit-message
Draft a Conventional-Commits message for a staged diff.
factory-update
Explains and drives the factory's update path — how improvements to the public template reach this office as a human-gated pull request. Invoke when the human asks 'is my factory up to date?', when a factory-update PR needs explaining hunk by hunk, or when an update was declined and needs a selective re-apply.
codex-pr-body
Update the title and body of one or more pull requests.
update-v8-version
Update Codex's pinned v8 / rustyv8 versions, validate the release-candidate path, and investigate failed V8 canary or artifact builds. Use when asked to bump V8, update rustyv8 artifacts, prepare or validate a V8 release candidate, check v8-canary, or diagnose why a V8 version update no longer builds.
agent-framework-py-release
Use when cutting a Python release for the microsoft/agent-framework monorepo. Triggers on "bump py versions", "cut a python release", "prepare release PR for python", "release py packages", "bump python to X.Y.Z", or similar requests to bump Python package versions and prepare a release PR. Handles all four lifecycle…
github
Use gh as the primary interface for GitHub data and actions. Keep this skill focused on basic operations and command safety, not maintainer triage strategy.