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 skills/cavalry-collective/visual-stack/startnpx skills add Cavalry-Collective/visual-stack --skill startgit clone --depth 1 https://github.com/Cavalry-Collective/visual-stackWhat 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 | $0.00103 | $0.02939 |
| Opus 5 | $0.00051 | $0.01470 |
| Sonnet 5 | $0.00021 | $0.00588 |
| Haiku 4.5 | $0.00010 | $0.00294 |
Grade C, and why
start scanned grade C 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 2d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf <name>/.git && git -C <name> init && git -C <name> add -A How it starts
The opening of the file, as written. The whole thing — 216 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Turns an idea — or an existing repo — into this project. One multi-step form, then whichever of three paths its answers call for.
┌─ skip dev ──► specs/ + design/ only (no clone)
idea ──► setup form ──► choice ──┤
└─ full ─────► clone ──► delete the rest ──► toolchain ──► ready
existing code ──► infer ──► confirm screen ──► recorded (nothing touched)
Every path ends with two files the rest of the chain reads: specs/product.md — what this product
is — and .vstack/pipeline.json — where the pipeline stands.
1 · Pick the mode
Look at the target directory first:
| The directory is | Mode |
|---|---|
| empty, missing, or has no real code | fresh — the form runs before anything exists |
template-derived (stacks/, add-ons/, design/, specs/ all present) |
template — don't clone again; the form reads the real inventory |
| a real codebase that isn't template-derived | existing — infer, confirm, record; never scaffold or delete |
In fresh mode, don't interrogate up front — the form asks the questions. The only thing worth asking before serving it is where the project directory should go if the user hasn't said.
2 · Serve the form
SKILL=<this skill dir>
node "$SKILL/assets/chooser-server.mjs" --repo <project dir> --port 7799
Start it with run_in_background: true, then tell the user to open http://localhost:7799/.
The form is four steps: what are you building → details (kind, name, one-liner) → stack & add-ons, with a pack recommended from the earlier answers — → confirm. On step 3 the user can instead skip development setup entirely; the whole path then produces UI and specs only.
Where the inventory comes from:
- Template mode (repo has
stacks/+add-ons/): scanned from disk — a pack added upstream appears with no change here. - Fresh mode (nothing on disk yet): the server fetches the live
stacks/+add-ons/listing ofvstack-template-basefrom GitHub ("source": "github"); offline or rate-limited it falls back to its built-in catalog snapshot ("source": "snapshot"). Either way, after cloning, reconcile: if the chosen pack or an add-on doesn't exist in the cloned template, stop and re-ask; if the template ships packs the form didn't show, mention them before deleting anything. - Existing mode: no inventory. Infer the facts first — read
package.json/ lockfiles / framework configs / the directory layout /README/ recent git log — write them as a prefill, and serve:
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.
- 2d ago First seen · 216 lines · 103 tokens per session scan C ca729ab94a71
start is a skill published in the GitHub repository Cavalry-Collective/visual-stack (11 stars, last pushed 12d ago), licensed MIT. It adds 103 tokens to every session and 2,939 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
ideogram-ultra
Build Ideogram 4 (Ideogram Ultra) txt2img and img2img workflows with the local open-weights model, dual conditional/unconditional models with DualModelGuider, Qwen3-VL text encoder, and structured JSON ("compositional deconstruction") prompts for strong text rendering and layout control.
model-compatibility
Model family compatibility matrix covering loaders, resolutions, samplers, CFG, VAE, ControlNet, and LoRA compatibility for SD 1.5, SDXL, Flux, SD3, and video models.
flux-txt2img
Build Flux txt2img workflows with Flux.1 Dev (SRPO), Flux 2 Klein 9B, Turbo LoRAs, FluxGuidance, and DualCLIPLoader patterns.
panel-node-pack-sync
Keep the ComfyUI sidebar panel node-pack (comfyui-agent-panel) in step with the orchestrator after comfyui-mcp updates. Use this whenever the orchestrator was just updated (installcomfyui (action:"selfupdate"), npm i -g comfyui-mcp, a new version in the ENVIRONMENT line), when a panel/bridge command fails in a way…
civitai
Discover Civitai models with the BUILT-IN downloadmodel action:"searchcivitai" and install/generate them locally. Find a checkpoint/LoRA/embedding on Civitai, download it into ComfyUI, and use its trigger words. Optionally pair the official Civitai MCP for community features (images browsing, posting, collections).
20-client-intake-brief-global
Use when an agency or freelancer takes on a NEW client and needs everything up front — an 11-section intake covering business overview, audience, current marketing, goals, budget, timeline, brand assets, approval process, and success criteria, written for the client to fill in and return. Trigger on 'client intake'…