An advice tool for deciding what to add next to an existing Trabuco project. It examines the current project and compares it with the requirements for a proposed capability.

It is for proposing modules or patterns that address a concrete goal, such as new data handling or higher request capacity. Each proposal includes what to add, why it helps, its trade-off and a rough effort estimate.

It helps turn a broad goal into specific additions while making the cost and complexity of each architectural choice clear.

extend — Skill for Claude Code by arianlopezc

Install

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.

Any agent

npx skills add arianlopezc/Trabuco --skill extend

Clone the repo

git clone --depth 1 https://github.com/arianlopezc/Trabuco

Made for: Claude Code.

Or install trabuco, the plugin that ships this one along with the rest of its 10 skills, 24 agents, 2 hooks, 1 MCP server.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/arianlopezc/trabuco/extend.svg)](https://agentmods.dev/skills/arianlopezc/trabuco/extend)

Your own site

<a href="https://agentmods.dev/skills/arianlopezc/trabuco/extend"><img src="https://agentmods.dev/badge/skills/arianlopezc/trabuco/extend.svg" alt="Measured on agentmods" height="20"></a>

Per session 75 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 600 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00075	$0.00600
Opus 5	$0.00037	$0.00300
Sonnet 5	$0.00015	$0.00120
Haiku 4.5	$0.00007	$0.00060

Measured 5d ago against content hash f9edcce06625, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

extend 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 5d 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.

plugin/skills/extend/SKILL.md · 37 lines

What it actually says

Advise on extending an existing Trabuco project

Flow

Load context:
- mcp__trabuco__get_project_info for the current project
- If ambiguous, use Read/Glob/Grep on the project root (pom.xml, */pom.xml, source layout) to fill in missing details
- Read trabuco://modules resource to know the full catalog
Load expertise: request the extend_project MCP prompt (argument: project path). This loads Trabuco's extension philosophy — the reasoning framework the advice should follow.
Understand the goal: if the user's argument is vague, ask specifically what they want to enable. "Make it faster" is too vague; "handle 10k concurrent requests" is actionable.
Match against patterns: call mcp__trabuco__suggest_architecture with the extended requirements (current + goal). Compare the recommended config against what's currently installed. The delta is the extension proposal.
Present as a plan, not a wall of text: for each proposed addition, say:
- What (specific module or pattern)
- Why (how it addresses the goal)
- Trade-off (what complexity it adds)
- Effort (rough)
Offer to execute: if the user approves, delegate to /trabuco:add-module for each addition. If the proposal involves creating new entities/endpoints/events, mention that the project's own .claude/skills/ already has /add-entity, /add-endpoint, etc. for the implementation work.

Rules

Don't over-prescribe. If the current project already does what the user wants and the bottleneck is elsewhere, say that. "You don't need to change the architecture — you need to fix the query in FooRepository.findAll()" is a valid answer.
Respect limitations. Read trabuco://limitations before proposing something Trabuco can't help with (e.g., adding GraphQL, adding a React frontend).
Prefer conservative additions. Adding a module is cheap to propose but expensive to maintain. Default to "fewer modules, clearer boundaries."

Changes

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.

5d ago First seen · 37 lines · 75 tokens per session scan A f9edcce06625

Subscribe to this mod's changes

extend is a skill published in the GitHub repository arianlopezc/Trabuco (0 stars, last pushed 3mo ago), licensed MIT. It adds 75 tokens to every session and 600 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 2026-08-31.

Planning

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

microsoft/ai-agents-for-beginners · 200 tokens

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…

vercel/next.js · 95 tokens

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.

microsoft/vscode · 53 tokens

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…

microsoft/vscode · 71 tokens

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…

vercel/next.js · 83 tokens