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-buildnpx skills add Cavalry-Collective/visual-stack --skill phase-buildgit 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 | $0.00086 | $0.01793 |
| Opus 5 | $0.00043 | $0.00897 |
| Sonnet 5 | $0.00017 | $0.00359 |
| Haiku 4.5 | $0.00009 | $0.00179 |
Grade A, and why
phase-build 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 — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
One release phase, built in three passes — API, then UI, then infrastructure — against a plan the user saw and adjusted first. The board shows three trees (Endpoints · Components · Resources), each node coloured by what it is: new this phase, changed (exists, this phase extends it), or already built. Press Start, and the same board becomes the progress view — nodes pulse while being built and fill in as they land.
story map slice + specs + phase screens ──► plan JSON ──► board ──► user adjusts ──► Start
│
done ◄── infra ◄── ui ◄── api — one node at a time, each reported to the board ◄┘
have is read from the codebase, never from a previous plan. A plan that colours from last
phase's intentions lies the first time a phase ships partial. Read the actual routes, components,
migrations and infra files; stamp when you read them.
1 · Scope the phase
- Pipeline mode: phase N is
phasein.vstack/pipeline.json. Its content is the phase-N slice ofspecs/story-map.json, the specs inartifacts.specs[], anddesign/phase-<n>/if phase wireframes exist. If"specsOnly": true, this stage doesn't apply — say so and offer/vstack:startto add development setup. - Standalone: whatever the user points at — a spec, a story list, "build this". Ask only what you can't infer.
2 · Read the codebase, then draft the plan
Walk the actual code: API routes and handlers, frontend components/pages, migrations, infra and
deploy files. Then write .vstack/build/phase-<n>.json:
{
"phase": 1,
"readAt": "2026-07-29 14:05",
"subjects": {
"api": { "mono": true, "root": { "id": "api", "kind": "API", "text": "/v1", "state": "have", "children": [] } },
"ui": { "root": { "id": "ui", "kind": "Frontend", "text": "<app>", "state": "have", "children": [] } },
"infra": { "root": { "id": "in", "kind": "Infra", "text": "<envs>", "state": "have", "children": [] } }
}
}
What ships with it
1 file 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 · 128 lines · 86 tokens per session scan A 000877cca9c1
phase-build is a skill published in the GitHub repository Cavalry-Collective/visual-stack (11 stars, last pushed 13d ago), licensed MIT. It adds 86 tokens to every session and 1,793 once invoked, about $0.0004 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'…