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-cookgit 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-cook)<a href="https://agentmods.dev/skills/giltotherescue/velocity-agent-skills/vl-cook"><img src="https://agentmods.dev/badge/skills/giltotherescue/velocity-agent-skills/vl-cook/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-cook"><img src="https://agentmods.dev/badge/skills/giltotherescue/velocity-agent-skills/vl-cook.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 | $0.00119 | $0.01698 |
| Opus 5 | $0.00060 | $0.00849 |
| Sonnet 5 | $0.00024 | $0.00340 |
| Haiku 4.5 | $0.00012 | $0.00170 |
Grade A, and why
vl-cook 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 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.
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 — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Velocity Cook
Use this skill when the user wants execution, not just a plan. Keep working through implementation, tests, app/browser checks, review, and handoff until the work is ready for human review.
You are the executing agent. Do not write a prompt for another agent. Do not stop because the first patch compiles. Continue until the requested outcome behaves correctly, is verified, and is easy to review.
Operating Mode
- Act autonomously when the request is clear enough.
- Ask at most 1-3 questions only when the answer materially changes what to build.
- Read project instructions first:
AGENTS.md,CLAUDE.md, README files, and relevant docs. - Follow existing project conventions before adding new architecture.
- Preserve user work and avoid destructive git commands.
- Keep a task plan for multi-step work.
- Prefer small, reversible slices over one large speculative rewrite.
Decide The Max Useful Loop
Default to the strongest reasonable loop for the task:
- Code changes.
- Focused tests.
- Typecheck, lint, format, or build checks.
- Local staging or browser checks when the work has an app surface.
- Contact sheets or other review artifacts when the work is visual.
- A handoff when another person or agent will review or continue.
Skip expensive steps only when they do not prove the outcome, would spend real provider budget unnecessarily, or the user explicitly limits scope.
Use /vl-stage when any of these are true:
- The main checkout is being used for other testing.
- The work needs a stable local URL, dev server, or app runtime.
- A worktree, branch, container, database, cache, session, queue, or port needs isolation.
- Browser testing is part of proving the work.
- The agent is running in a cloud/remote environment and needs to decide what "staged" can realistically mean there.
Decide whether staging should use a worktree:
- Use the current checkout for small changes, documentation, narrow fixes, or work that the user is already doing in this checkout.
- Infer that a worktree is appropriate when the main checkout is dirty with unrelated work, the user mentions parallel testing, the work will take multiple iterations, or local services/state could interfere with another task.
- Ask one brief question when the choice is ambiguous and the setup cost is meaningful, for example: "Should I keep this in the current checkout, or create/use a worktree so it can run separately?"
- If the user has already implied isolation, proceed with
/vl-stageand a worktree without asking again. - In cloud-agent sandboxes, usually keep the existing checkout and let
/vl-stagedefine the available staged environment instead of creating local worktrees or assuming access to the user's machine.
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 · 185 lines · 119 tokens per session scan A 16138430d409
vl-cook is a skill published in the GitHub repository giltotherescue/velocity-agent-skills (3 stars, last pushed 3mo ago), licensed MIT. It adds 119 tokens to every session and 1,698 once invoked, about $0.0006 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 2026-08-31.
Other skills, from other repositories
projectatlas
Use ProjectAtlas as the atlas-first orientation layer before broad source reads, with MCP-first task startup, short-alias worktree registration and routing, safe targeted initialization, ranked navigation, exact or federated graph evidence, purpose curation, health, lint, and repository-wide token reporting.
codex-coding-plugin
Build, review, or fix ProjectAtlas plugin/runtime installer integration for Codex, Claude Code, and OpenCode, especially version convergence, stale ProjectAtlas cache repair, MCP config generation, skill artifacts, host smoke tests, and fake-host tests for ProjectAtlas releases.
breaking-down-the-work
Splits scope into a product-first work breakdown that follows the 100% rule, keeps pieces from overlapping, uses outline numbers, and gives every piece a dictionary entry. Use when an epic, feature, or new subsystem needs a clean split into deliverables, or one source of truth before folders or work begin. Do not use…
staying-on-mission
Tests the current work against a written, lasting mission anchor and forces one choice, re-anchor, escalate, or stop. Use when an agent keeps finishing tasks but the work drifts from the goal, scope creeps, the same action repeats in a loop, or standards slip one small step at a time. Do not use for a tiny edit with…
closing-stale-packets
Brings an abandoned or half-filled change packet to an honest terminal state by completing it, closing it with a recorded rationale, or deleting it. Use when ng status flags a scaffold or invalid packet, a long session left a draft behind, or work was abandoned mid-packet. Do not use for an actively in-progress…
learning-from-experience
Turns incidents, near misses, bad handoffs, review surprises, escaped bugs, and signals from real use into lasting fixes to your safeguards. Use after something went wrong or nearly did and a future safeguard should change. Do not use during a live incident, which comes first, or to blame someone.