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 Undertone0809/rudder --skill rudder-worktree-preview-maintainergit clone --depth 1 https://github.com/Undertone0809/rudderWrote 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/undertone0809/rudder/rudder-worktree-preview-maintainer)<a href="https://agentmods.dev/skills/undertone0809/rudder/rudder-worktree-preview-maintainer"><img src="https://agentmods.dev/badge/skills/undertone0809/rudder/rudder-worktree-preview-maintainer/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/undertone0809/rudder/rudder-worktree-preview-maintainer"><img src="https://agentmods.dev/badge/skills/undertone0809/rudder/rudder-worktree-preview-maintainer.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 | $0.00049 | $0.01936 |
| Opus 5 | $0.00024 | $0.00968 |
| Sonnet 5 | $0.00010 | $0.00387 |
| Haiku 4.5 | $0.00005 | $0.00194 |
Grade A, and why
rudder-worktree-preview-maintainer scanned grade A with 1 finding 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 10d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -fsS http://127.0.0.1:<port>/api/health How it starts
The opening of the file, as written. The whole thing — 207 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Rudder Worktree Preview Maintainer
Run the current Rudder checkout as a temporary preview so the user can inspect the feature in a browser without leaving a foreground command running.
This skill is for the common post-implementation hand-off: the branch already contains the work, and the user wants a local URL to test. It is not a PR checkout workflow, it is not a broad process cleanup workflow, and it is not the canonical developer environment for Codex-managed worktrees.
Rudder's normal pnpm dev entrypoint is the canonical development path. In
Codex-managed worktrees under ~/.codex/worktrees/<id>/<repo>, pnpm dev
auto-derives an isolated RUDDER_HOME, instance id, server port, embedded
PostgreSQL port, and worktree branding when no repo-local .rudder/ config
exists. Use this preview skill only when the user wants a managed background
preview handoff with health verification, logs, and a stop command.
Preview readiness is environment proof, not product proof. A healthy URL means the checkout can be opened; it does not prove that a feature, workflow, agent path, or UI regression is fixed. When this skill is used inside a lifecycle handoff or review gate, the owning workflow must still exercise the relevant route, command, agent run, or Desktop/browser interaction and report the observed terminal state.
Use This Skill When
- The user asks to run the current branch or current worktree locally.
- The user wants to manually test a recently implemented UI or workflow change.
- The assistant needs to hand off a stable preview URL after implementation
without leaving
pnpm devin the foreground. - The user asks for logs, a stop command, or a temporary preview that can be cleaned up independently.
- The task is to provide a preview URL, not to package Desktop or publish a release.
Do Not Use This Skill When
- The user asks to check out or preview a GitHub PR; use
pr-local-preview-maintainerinstead. - The user asks only to stop or clean local dev processes; use
stop-rudder-dev-maintainerinstead. - The user is asking why Codex worktrees interfere, how normal development
should be isolated, or whether
pnpm devis using the current worktree. In that case inspectscripts/dev-local-env.mjs,doc/engineering/DEVELOPING.md, and the/api/healthpayload for the active dev runtime. - The user simply wants to develop inside the current Codex worktree. Use
pnpm dev, which should auto-isolate Codex-managed worktrees, instead of starting a separate/tmp/rudder-worktree-previewinstance. - The change needs packaged Desktop verification; follow the Desktop validation workflow in the repo docs.
- The user wants production-like
pnpm prodbehavior rather than a dev preview.
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.
- 10d ago First seen · 207 lines · 49 tokens per session scan A 81b4f57f32de
rudder-worktree-preview-maintainer is a skill published in the GitHub repository Undertone0809/rudder (288 stars, last pushed today), licensed Apache-2.0. It adds 49 tokens to every session and 1,936 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
opencli-sitemap-author
Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
interactive-login
How to complete browser/interactive logins (aws / gh / glab / gcloud). The platform backgrounds the login poller so it survives the human's browser round-trip — and when that does NOT work.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
azure-messaging-webpubsub-java
Build real-time web applications with Azure Web PubSub SDK for Java. Use when implementing WebSocket-based messaging, live updates, chat applications, or server-to-client push notifications.
google-safe-browsing
Prevent and fix Google Safe Browsing "Dangerous site" flags. Use when launching a public web app, buying/picking a domain, building a login or signup page, or when any site shows a red "Dangerous site" / "Deceptive site" warning in Chrome, Brave, Safari, Firefox, or Edge. Triggers on "dangerous site", "deceptive…