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-mcpgit 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-mcp)<a href="https://agentmods.dev/skills/bloomlabsinc/agent-skills/bloom-mcp"><img src="https://agentmods.dev/badge/skills/bloomlabsinc/agent-skills/bloom-mcp/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-mcp"><img src="https://agentmods.dev/badge/skills/bloomlabsinc/agent-skills/bloom-mcp.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 | $0.00055 | $0.00708 |
| Opus 5 | $0.00028 | $0.00354 |
| Sonnet 5 | $0.00011 | $0.00142 |
| Haiku 4.5 | $0.00006 | $0.00071 |
Grade A, and why
bloom-mcp 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 10d 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 — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Using the Bloom MCP
The Bloom MCP has one governing idea: frames, not files. The file-shaped tools (write_files, edit_files, read_files, delete_files) operate on canvas frames — React TSX at @bloom-frame/<uuid> — not on your repo and not on the app's sandbox source. Get this wrong and you'll write to the wrong place or have a call rejected.
Full tool catalog (generated from the API): references/tools.md.
Orient before you touch anything
Run these in order; each must return before the next:
whoami→ confirms the token and what it can reach (accessibleProjectCount).list_projects→ pickprojectId.list_branches→ pickbranchId(noteisMain).list_canvas_pages→ pickcanvasPageId. Required when a branch has more than one page — otherwise calls fail withMCP_PAGE_AMBIGUOUS.
Completion criterion: you hold a concrete { projectId, branchId, canvasPageId } from live calls — never invented IDs.
Frames, not files — the rules that keep you out of the ditch
- Frame paths are
@bloom-frame/<uuid>. To create one, write a@bloom-frame/_new_<localName>placeholder; the result echoes aplaceholderMintingMapgiving you the real UUID. Use that UUID from then on. @/<path>is the app's sandbox, not your editor's repo. Reading it is fine (read_files); writing a sandbox path is rejected (MCP_SANDBOX_PATH_REJECTED).kind:artboard(default) vscanvasComponent(importable from other frames). Set it on create; on overwrite it's ignored — promote later withedit_files.edit_filesneeds the current content —read_filesthe frame first, then edit against what's actually there.
Frames vs. the agent — pick the right tool for the change
- Editing what's on the canvas (a design, a mockup, a plan frame) →
write_files/edit_files. This is direct and immediate. - Full-stack or codebase work (routes, backend, sandbox source, multi-file features) →
trigger_agenton a branch. Don't try to hand-edit sandbox source through the canvas tools — you can't (@/writes are rejected), and the agent is the right instrument.
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.
- 10d ago First seen · 42 lines · 55 tokens per session scan A 7be1f9ce73e2
bloom-mcp is a skill published in the GitHub repository BloomLabsInc/agent-skills (2 stars, last pushed 2mo ago), licensed MIT. It adds 55 tokens to every session and 708 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…