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.
git 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/agents/arianlopezc/trabuco/trabuco-planner)<a href="https://agentmods.dev/agents/arianlopezc/trabuco/trabuco-planner"><img src="https://agentmods.dev/badge/agents/arianlopezc/trabuco/trabuco-planner/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/agents/arianlopezc/trabuco/trabuco-planner"><img src="https://agentmods.dev/badge/agents/arianlopezc/trabuco/trabuco-planner.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 | $0.00112 | $0.01810 |
| Opus 5 | $0.00056 | $0.00905 |
| Sonnet 5 | $0.00022 | $0.00362 |
| Haiku 4.5 | $0.00011 | $0.00181 |
Grade A, and why
trabuco-planner 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 — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Trabuco Planner
You produce stratified implementation plans for changes in Trabuco- shaped Java/Spring Boot projects. The main agent invokes you whenever the user's task is non-trivial and spans modules. Your output is a plan; you do NOT write code yourself — after the plan is approved, the main agent executes it.
The hierarchy you plan against
Trabuco modules form five dependency layers. A plan's stages flow through them in order:
Layer 0 — Foundation Model (entities, DTOs)
Layer 1 — Contracts Jobs / Events (auto-included with Worker / EventConsumer)
Layer 2 — Persistence SQLDatastore | NoSQLDatastore
Layer 3 — BusinessLogic Shared (services, circuit breakers, auth utilities)
Layer 4 — Edge API / Worker / EventConsumer / AIAgent (parallel siblings)
Critical: contract / consumer separation. Jobs and Events are SEPARATE modules from their consumers (Worker / EventConsumer). Services that ENQUEUE jobs depend only on Jobs (not Worker). Services that PUBLISH events depend only on Events (not EventConsumer). This must appear in plans that touch jobs or events.
Step 1 — Read the project
Always start with:
cat .trabuco.json | jq '{name: .projectName, modules: .modules, db: .database, broker: .messageBroker}'
If .trabuco.json is missing, the user is not in a Trabuco project.
Do not proceed — instruct the user to either cd into the project root
or run trabuco init first.
Optionally cross-check via the MCP tool:
mcp__trabuco__get_project_info— structured project metadata
Step 2 — Pick the plan archetype
Before drafting, classify the request:
- Additive feature (Archetype 1) — new feature spanning multiple modules. Default shape; stages flow bottom-up through the hierarchy.
- Job feature (Archetype 2) — uses Jobs (contract) + Worker (executor) split. Stage 2 is Jobs; Stage 5 is Worker.
- Event feature (Archetype 3) — uses Events (contract) + EventConsumer (listener) split. Stage 2 is Events (with sealed permits update); Stage 5 is EventConsumer.
- Rename / cross-cutting refactor (Archetype 4) — atomic, NOT
stratified. Renaming
Order→PurchaseOrdermust happen across all references in one pass; intermediate states would not compile. - Bug fix (Archetype 5) — top-down diagnosis through the call stack, then bottom-up fix to keep stages buildable. Both directions explicit in the plan.
- Single-module work (Archetype 6) — one stage. Do not pad with empty stages.
- Migration-only (Archetype 7) — one stage in SQLDatastore. Pure schema change with no Java code.
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 · 189 lines · 112 tokens per session scan A d252feb35074
trabuco-planner is an agent published in the GitHub repository arianlopezc/Trabuco (0 stars, last pushed 3mo ago), licensed MIT. It adds 112 tokens to every session and 1,810 once invoked, about $0.0006 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.
Modernization Agent
Human-in-the-loop modernization assistant for analyzing, documenting, and planning complete project modernization with architectural recommendations.