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 giltotherescue/velocity-agent-skills --skill vl-stagegit clone --depth 1 https://github.com/giltotherescue/velocity-agent-skillsWrote 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/giltotherescue/velocity-agent-skills/vl-stage)<a href="https://agentmods.dev/skills/giltotherescue/velocity-agent-skills/vl-stage"><img src="https://agentmods.dev/badge/skills/giltotherescue/velocity-agent-skills/vl-stage/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/giltotherescue/velocity-agent-skills/vl-stage"><img src="https://agentmods.dev/badge/skills/giltotherescue/velocity-agent-skills/vl-stage.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00108 | $0.02396 |
| Opus 5 | $0.00054 | $0.01198 |
| Sonnet 5 | $0.00022 | $0.00479 |
| Haiku 4.5 | $0.00011 | $0.00240 |
Grade A, and why
vl-stage 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 12d 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.
If the platform exposes forwarded ports, start the app with the normal dev command and verify the printed or forwarded URL. If not, verify with local `curl` from inside the sandbox: How it starts
The opening of the file, as written. The whole thing — 270 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Velocity Stage
Use this skill when work needs to run somewhere real: a local URL, dev server, container, framework-specific local environment, isolated worktree, or cloud-agent sandbox. It is especially useful for web apps, where browser-facing behavior needs to be tested like a user without disrupting the user's main checkout.
Prefer the simplest strategy that proves the work:
- Existing checkout + dev server when there is no isolation risk.
- Existing git worktree when one already exists.
- New git worktree when the main checkout is busy or the user asks for parallel work.
- Framework dev server for most JS, Python, Rails, or PHP apps.
- Docker Compose when the project already uses it.
- Framework-specific local hosting when that is clearly the project's convention.
- Existing cloud-agent environment when the task is already running in a remote sandbox.
Cloud-Agent Compatibility
Cloud agents such as Claude Code on the web, Cursor cloud agents, and Codex web often already run each task in an isolated cloud environment. In that context, the cloud environment is usually the stage.
Before doing local-machine setup, detect whether the session is remote or ephemeral:
env | sort | rg -i 'CODEX|CLAUDE|CURSOR|CODESPACE|GITHUB_ACTIONS|CI|REMOTE|CONTAINER|DEVCONTAINER'
pwd
hostname
git worktree list
When running in a cloud-agent environment:
- Prefer the existing checkout/sandbox over creating or moving git worktrees.
- Do not assume access to the user's local browser,
localhostfrom their machine, Herd/Valet, desktop apps, keychain, or parked site directories. - Prefer project setup scripts, checked-in devcontainer/Dockerfile config, package scripts, and documented test commands.
- Start servers on
127.0.0.1or0.0.0.0only when the platform supports local port access or browser automation from inside the sandbox. - Use headless browser tools when available. If they are not available, run build/test/static checks and document that interactive browser verification was not possible in the cloud environment.
- Treat secrets and network access as environment-scoped. Do not ask the user to paste secrets into chat; ask them to configure environment secrets/settings when needed.
- Save review artifacts inside the repository or a clearly named artifact folder so they can be included in the branch, PR, or handoff.
- Make teardown lightweight: stop processes you started, but do not remove the cloud checkout unless the platform explicitly requires it.
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.
- 12d ago First seen · 270 lines · 108 tokens per session scan A 2e7960500cc3
vl-stage is a skill published in the GitHub repository giltotherescue/velocity-agent-skills (3 stars, last pushed 3mo ago), licensed MIT. It adds 108 tokens to every session and 2,396 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
agentplane-testkit-migration
Use when migrating Agentplane tests to @agentplane/testkit, replacing local test helpers, fixing testkit export/build failures, splitting large CLI/backend suites, or diagnosing missing testkit dist exports in package builds.
verifying-final-artifacts
Verifies the delivered artifact a consumer actually receives (a figure, chart, PDF, SVG, screenshot, compiled build, or deployed response) by regenerating it fresh and directly observing the output, not the source that produces it, and ends in one honest verdict. Use when the deliverable is a produced artifact and…
stress-testing-agent-changes
Attacks your own agent change, tool grant, dependency, model, or release on purpose, across risk types such as prompt injection, gaining extra power, unsafe output, and tool misuse, and records what you tried, what happened, and the leftover risk. Use when a change widens an agent's power, data access, or network…
qamap-pr-qa
Local zero-LLM PR QA workflow. Use when an agent is preparing, updating, finalizing, or reviewing a pull request, asks what the PR should test, or needs commit-backed change intent, affected behavior, QA scenarios, evidence, validation commands, optional automation drafts, and manifest repair guidance.
create-plugin
Use when authoring a new octomux plugin package — package layout, the apply(ctx) export, choosing a registrar, shipping kind presets, testing locally, and confirming with octomux doctor.
debugging
Investigate failures whose root cause is still unknown — narrow the search space, instrument, and test falsifiable hypotheses. Use for intermittent or environment-dependent behavior, unexplained stack traces, regressions with no known trigger, or any symptom without a confirmed cause. Ends once the root cause is…