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/phase-previewnpx skills add Cavalry-Collective/visual-stack --skill phase-previewgit 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 | $0.00107 | $0.02423 |
| Opus 5 | $0.00053 | $0.01211 |
| Sonnet 5 | $0.00021 | $0.00485 |
| Haiku 4.5 | $0.00011 | $0.00242 |
Grade A, and why
phase-preview 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 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.
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 — 176 lines — stays where its author put it; the contents beside it link to each section on GitHub.
One design in, one screen per phase out. Each phase file shows everything available by that phase and nothing that isn't, in exactly the positions the approved design already put them — so a phase screen is the real build target for that release, not a redrawing of it. Nothing here is drawn: this is the approved design with the later releases taken out, which is why it can be checked mechanically rather than by eye.
base.html ──┬──► phase-1/base.html only what ships in phase 1
├──► phase-2/base.html phase 1 + phase 2
└──► phase-3/base.html phase 1 + 2 + 3 ( = the base, if phases cover it all )
Subtract only. Nothing is moved, resized, restyled or repositioned; nothing new is invented. That is the entire discipline of this skill, and §4 proves it mechanically rather than trusting the eye.
1 · Resolve the two inputs
The base wireframe — one self-contained HTML file. If the user hasn't named one, ask; don't guess
among the files in design/. Never work from an already-phased file: every phase is cut from the
original.
The phases, and what belongs to each. In priority order:
- A story map (
*.jsonfrom/vstack:user-story-map) —phases[]gives the order and goals,stories[]give what lands when. This is the best input; ask for one if a story map exists. - A spec with P1/P2/P3 priorities, or a roadmap.
- The user tells you the phases in the conversation.
If none of those exist, stop and ask — inventing a release plan is not this skill's job.
2 · Write the phase plan before touching any HTML
Open the base and inventory every element, component and interaction in it. Assign each one the earliest phase it exists in. Write that out and show the user before generating anything:
| Element | Earliest phase | Why |
|---|---|---|
| Candidate table + search | 1 | "Search candidates by name" |
| Bulk-select toolbar | 2 | "Move several candidates at once" |
| "Ask AI" button + drawer | 3 | "Summarise a candidate with AI" |
| Export button | — | not in any story — flag it |
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 · 176 lines · 107 tokens per session scan A a107810baebe
phase-preview is a skill published in the GitHub repository Cavalry-Collective/visual-stack (11 stars, last pushed 13d ago), licensed MIT. It adds 107 tokens to every session and 2,423 once invoked, about $0.0005 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 2026-08-30.
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'…