Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add radumarias/xorio-claude-plugin/plugin install xorioWrote 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/radumarias/xorio-claude-plugin/brainstorm)<a href="https://agentmods.dev/skills/radumarias/xorio-claude-plugin/brainstorm"><img src="https://agentmods.dev/badge/skills/radumarias/xorio-claude-plugin/brainstorm/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/radumarias/xorio-claude-plugin/brainstorm"><img src="https://agentmods.dev/badge/skills/radumarias/xorio-claude-plugin/brainstorm.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 | $0.00164 | $0.02077 |
| Opus 5.5 | $0.00066 | $0.00831 |
| Sonnet 5.5 | $0.00033 | $0.00415 |
| Haiku 4.5 | $0.00016 | $0.00208 |
Grade A, and why
brainstorm 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 1mo 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 — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
brainstorm
Run a structured multi-agent brainstorm on a topic: a Map → Ideate → Refute → Debate → Synthesize Workflow that emits many ideas across diverse lenses,
adversarially vets each (default-refuted majority vote), debates the
survivors, and returns a ranked, vetted report. Built for two jobs:
optimizing something specific, and getting several ideas to build a few of
them out.
The orchestration lives in workflow.js (next to this file). This skill's job is
to parse the request, ground it lightly, launch the workflow, and present results.
Model tiers — resolve at runtime, never hardcode
This skill refers to model tiers, not model names. Resolve them once at run start from the runtime environment — never from this file:
- STRONG — the most capable Claude model currently available. Identify it
from the session environment (the system context names the current flagship)
and the Agent/Workflow tool's
modeloptions. Use the flagship for STRONG even if the session runs on a cheaper model; when the session model already IS the flagship, omit themodelparam and inherit it. - MID — one tier below STRONG: capable and cheaper; mechanical/structured work (extraction, summarizing, convention checks).
- LIGHT — the smallest/cheapest available tier: trivial gates, yes/no checks.
workflow.js cannot read the environment itself — resolve the tiers BEFORE
launching and pass them as args.models = { strong, mid, light } (concrete
aliases from the Workflow tool's model options). If a tier is omitted, the
script degrades safely: those agents inherit the session model. Model names
must never be written into this skill or workflow.js; when a newer flagship
ships, this rule adopts it automatically.
--fable override. When --fable is passed, resolve STRONG to fable
(the fable option of the Workflow tool's model) and pass args.fable = true.
The best-model agents — Map, Synthesize, and every STRONG Ideate/Refute/Debate
slot — then run on Fable at MAX effort (workflow.js pins STRONG-tier effort
to max under --fable). MID/LIGHT are untouched: cheaper roles stay on their
tiers. This is the surgical middle ground between the default (mixed tiers) and
brainstorm-mythos (every agent on Fable). Opt-in — Fable is access-gated and
pricier; if the fable model option is unavailable in the runtime, note it and
fall back to the default STRONG resolution.
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.
- 1mo ago First seen · 122 lines · 164 tokens per session scan A 76354af56aba
brainstorm is a skill published in the GitHub repository radumarias/xorio-claude-plugin (3 stars, last pushed 6d ago), licensed MIT. It adds 164 tokens to every session and 2,077 once invoked, about $0.0007 per session on Opus 5.5. 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
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…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Optimize the meaningful UI available immediately from a Next.js route on an initial load (hard navigation) or named client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route and entry point at a time; the shipped test then guards…