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 BloomLabsInc/agent-skills --skill bloom-visual-planninggit clone --depth 1 https://github.com/BloomLabsInc/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/bloomlabsinc/agent-skills/bloom-visual-planning)<a href="https://agentmods.dev/skills/bloomlabsinc/agent-skills/bloom-visual-planning"><img src="https://agentmods.dev/badge/skills/bloomlabsinc/agent-skills/bloom-visual-planning/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/bloomlabsinc/agent-skills/bloom-visual-planning"><img src="https://agentmods.dev/badge/skills/bloomlabsinc/agent-skills/bloom-visual-planning.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 | $0.00059 | $0.00790 |
| Opus 5 | $0.00030 | $0.00395 |
| Sonnet 5 | $0.00012 | $0.00158 |
| Haiku 4.5 | $0.00006 | $0.00079 |
Grade A, and why
bloom-visual-planning 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 9d 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 — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Visual planning — a plan is a frame
The move: don't hand the user a wall of prose — build the plan as a frame. A plan is a TSX live fragment on the Bloom canvas — the same React the app runs — so it can hold a decision matrix with live axes, an animated concept explainer, or a draggable trade-off space. The canvas is the plan editor; there is no second tool and no plan DSL. The user reads by looking, and edits by direct manipulation.
This is a living skill — the archetypes and examples will grow. Treat the examples as starting points, not a fixed menu.
Steps
- Align before you draw. Get the decision sharp enough to be worth a frame: what is being chosen, what the options are, what axes actually decide it. If it's fuzzy, interview first (a grilling pass) — a plan frame built on a vague question just renders the vagueness prettily. Done when: you can name the options and the 2–4 axes that separate them.
- Pick the archetype that fits the decision, then read its pattern + example in
references/visual-planning-patterns.md:- comparing discrete options → decision matrix (
assets/examples/decision-matrix-frame.tsx) - explaining how something works / a sequence → concept explainer (
assets/examples/concept-explainer-frame.tsx) - exploring a design space with knobs → trade-off space (pattern doc)
- comparing discrete options → decision matrix (
- Seed the frame. Adapt an example into a new canvas frame with
write_files(a@bloom-frame/_new_<name>placeholder — seebloom-mcp). Populate it with the real options and axes, not lorem. Prefer live data (a Convex query via the Bloom SDK) over numbers you typed once and will forget to update. Done when: the frame renders the actual decision, and every option/axis is real. - Iterate visually with the user. Hand them the frame, not a paragraph. Let them re-rank, drag a slider, swap a variant — the frame recomputes, and those edits are the canonical record of the decision. Adjust the frame with
edit_filesas the conversation moves. Done when: the user has converged on the frame, and it reflects the choice they made.
What ships with it
3 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.
- 9d ago First seen · 37 lines · 59 tokens per session scan A 3bf5c7a02f84
bloom-visual-planning is a skill published in the GitHub repository BloomLabsInc/agent-skills (2 stars, last pushed 2mo ago), licensed MIT. It adds 59 tokens to every session and 790 once invoked, about $0.0003 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
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ralph with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.
make-resume
A Chinese-language tool for creating editable HTML resumes that can be changed in a browser and printed to PDF. It uses available resume templates when they are installed and otherwise provides a simpler fallback.