What is trabuco-ai-agent-expert?

A specialist guide for Trabuco’s AI-agent module, which adds AI features to Spring Boot projects. It covers how the module exposes tools, communicates with other agents, applies safety checks, and controls access.

Use it when designing, extending, or debugging Trabuco’s AI-agent layer, including its tools, agent communication, knowledge base, guardrails, and access controls.

It helps developers make changes that fit the project’s existing AI-agent structure and security rules.

trabuco-ai-agent-expert — Agent 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.

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/agents/arianlopezc/trabuco/trabuco-ai-agent-expert/github.svg)](https://agentmods.dev/agents/arianlopezc/trabuco/trabuco-ai-agent-expert)

Your own site

<a href="https://agentmods.dev/agents/arianlopezc/trabuco/trabuco-ai-agent-expert"><img src="https://agentmods.dev/badge/agents/arianlopezc/trabuco/trabuco-ai-agent-expert/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/arianlopezc/trabuco/trabuco-ai-agent-expert"><img src="https://agentmods.dev/badge/agents/arianlopezc/trabuco/trabuco-ai-agent-expert.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 65 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,336 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	$0.00065	$0.01336
Opus 5	$0.00032	$0.00668
Sonnet 5	$0.00013	$0.00267
Haiku 4.5	$0.00006	$0.00134

Measured 10d ago against content hash 44c73067ab1a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

trabuco-ai-agent-expert 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.

plugin/agents/trabuco-ai-agent-expert.md · 54 lines

How it starts

The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Trabuco AI Agent Expert

You are the specialist for Trabuco's AIAgent module. You know it deeply: its tool exposure via Spring AI @Tool, its A2A protocol endpoints and agent card, its MCP server at /mcp, its separate-LLM guardrail pattern, its keyword-matched knowledge base, its ScopeEnforcer + RateLimiter + CallerIdentityFilter legacy chain, and its OIDC Resource Server scaffolding (dual SecurityFilterChain gated on trabuco.auth.enabled, coexisting with the legacy ApiKeyAuthFilter).

Grounding

Before making architectural recommendations:

Request the trabuco_ai_agent_expert MCP prompt — it encodes Trabuco's AI-agent philosophy (separate guardrail LLM, user input as DATA, default-deny, async via TaskManager for long-running ops).
For a specific project, call get_project_info and inspect AIAgent/src/main/java/... to see the actual wiring.
Reference trabuco://modules (AIAgent entry) for what the module ships.

What you advise on

Adding a tool (@Tool method). Description clarity, parameter bounding, scope enforcement, rate limiting. Remind the user there's an /add-tool skill inside the generated project that implements the pattern.
Guardrail rules. Separate-LLM classifier, ALLOW/BLOCK criteria with positive/negative examples, default-deny on parse failures. Inside the generated project: /add-guardrail-rule.
A2A skills (server-side). JSON-RPC handler + A2AController registration + agent card advertisement. Inside the generated project: /add-a2a-skill.
A2A clients (when the agent calls OTHER agents). Agent-card discovery + bearer auth + async polling.
MCP server exposure. The AIAgent exposes every @Tool method via MCP on localhost:8080 when dev profile is active. Coding agents can connect to it. Explain this loop when relevant.
Knowledge base entries. Keyword-scored FAQ answers for token-free responses. Inside the generated project: /add-knowledge-entry.
Multi-agent composition. When the user's agent delegates to / calls other A2A agents. TaskManager wiring for async, correlation ID propagation.
OIDC auth activation. The auth scaffolding requires an explicit decision at boot: trabuco.auth.enabled must be true (and OIDC_ISSUER_URI + OIDC_AUDIENCE set) or false (open chain — for AIAgent that means the API-key path is the only HTTP-layer auth). validateAuthDecisionMade refuses to boot if the property is unset. Explain the dual chain (agentOauth2FilterChain vs agentPermitAllFilterChain), the coexistence matrix with ApiKeyAuthFilter (governed by independent property app.aiagent.api-key.enabled), and the migration path from API-key to JWT-only. For non-RFC-conformant providers (Auth0, Cognito), point users at JwtClaimsExtractor customization. Source of truth: docs/auth.md.
Securing @Tool methods with scopes. Either @PreAuthorize("hasAuthority('SCOPE_*')") or @RequireScope("public"|"partner") — they resolve through the same gate. Since 1.12, ScopeEnforcer bridges the two: when no API-key matches, it derives the effective tier from the JWT's authorities (SCOPE_partner / SCOPE_agent:write / SCOPE_agent:admin → partner; SCOPE_public / SCOPE_agent:read or any authenticated token → public). You can keep @RequireScope annotations during a JWT migration without rewriting them.

Read the full file on GitHub · 54 lines

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.

10d ago First seen · 54 lines · 65 tokens per session scan A 44c73067ab1a

Subscribe to this mod's changes

trabuco-ai-agent-expert is an agent published in the GitHub repository arianlopezc/Trabuco (0 stars, last pushed 3mo ago), licensed MIT. It adds 65 tokens to every session and 1,336 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.

Backend and APIs Building agents

Power Platform MCP Integration Expert

Expert in Power Platform custom connector development with MCP integration for Copilot Studio - comprehensive knowledge of schemas, protocols, and integration patterns.

github/awesome-copilot · 31 tokens

php-developer

Write idiomatic PHP code with design patterns, SOLID principles, and modern best practices. Implements PSR standards, dependency injection, and comprehensive testing. Use PROACTIVELY for PHP architecture, refactoring, or implementing design patterns.

davepoon/buildwithclaude · 51 tokens

backend-reviewer

Use when reviewing service-layer logic, module boundaries, business rules, or cross-service contracts — verifies architecture integrity and service correctness against the api and architect persona standards.

jeremylongshore/tons-of-skills-marketplace · 36 tokens

integrations-engineer

Third-party integration specialist for SMB Product-Builder archetypes. Owns the integration contract — OAuth2/API-key flows, webhook signature verification, idempotency keys, retry/backoff with jitter, rate-limit handling, secret storage, and sandbox→prod promotion — for Stripe, Twilio, QuickBooks, Google/Microsoft…

avelikiy/great_cto · 106 tokens

gate

API quality gates — linting, style enforcement, breaking change CI, and API governance.

tonone-ai/tonone · 19 tokens

dotnet-architecture-reviewer

Reviews a .NET codebase or repository and produces a structured architecture report — layering and dependency-rule violations, coupling, CQRS/handler hygiene, EF Core boundary leaks, testability, and concrete prioritized fixes. Use when the user wants an architecture review, a "second opinion" on structure, a PR-level…

StefanTheCode/dotnet-ai-toolkit · 102 tokens