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 arianlopezc/Trabuco --skill suggestgit clone --depth 1 https://github.com/arianlopezc/TrabucoWrote 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/arianlopezc/trabuco/suggest)<a href="https://agentmods.dev/skills/arianlopezc/trabuco/suggest"><img src="https://agentmods.dev/badge/skills/arianlopezc/trabuco/suggest/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/arianlopezc/trabuco/suggest"><img src="https://agentmods.dev/badge/skills/arianlopezc/trabuco/suggest.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 | $0.00061 | $0.00628 |
| Opus 5 | $0.00030 | $0.00314 |
| Sonnet 5 | $0.00012 | $0.00126 |
| Haiku 4.5 | $0.00006 | $0.00063 |
Grade A, and why
suggest 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 8d 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 — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Architecture advice, no generation
This skill advises. It does not create files. For generation, use /trabuco:new-project, /trabuco:design-system, or /trabuco:add-module.
Flow
-
Delegate to the specialist if possible: invoke the
trabuco-architectsubagent. It loads thetrabuco_expertMCP prompt and has the full reasoning framework. Only handle in-skill if the subagent isn't available. -
Gather the requirement if missing: 2–3 tight questions, not a survey. Focus on what differentiates architectures:
- Data shape (relational / document / cache / mix)
- Traffic shape (sync REST, async events, scheduled jobs, long-running tasks, real-time streams)
- AI agent involvement (will users interact with an LLM-backed agent?)
- Scale posture (small internal tool / B2B service / large-scale SaaS)
-
Get the recommendation: call
mcp__trabuco__suggest_architecturewith the requirement. It returns ranked patterns + a recommended module config. -
Present as reasoned advice, not a list dump:
- Top recommendation with rationale grounded in the returned patterns
- What tradeoff you're making (e.g., "Kafka gives durability but costs operational complexity vs RabbitMQ")
- What you'd change if the requirements shifted (e.g., "if latency matters more than throughput, I'd drop EventConsumer and stick with REST + async jobs")
-
Cite sources: when you make a claim about what a module does, reference
trabuco://modulesorlist_modulesoutput. When you cite a pattern, referencetrabuco://patterns. Don't hallucinate. -
Offer to act: "If you want me to generate this, use
/trabuco:new-project" — but only if they ask. Don't push.
Rules
- No generation from this skill. Period. The user picks when to commit.
- Be honest about fit. If Trabuco isn't the right tool (read
trabuco://limitations), say so — "for a React frontend, Trabuco won't help; pair it with a Next.js or Vaadin service." - Don't over-architect. If a single-module service is enough, say that. Resist the urge to recommend 8 modules when 3 suffice.
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.
- 8d ago First seen · 39 lines · 61 tokens per session scan A de90521136d2
suggest is a skill published in the GitHub repository arianlopezc/Trabuco (0 stars, last pushed 3mo ago), licensed MIT. It adds 61 tokens to every session and 628 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…