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-migration-skeleton-builder)<a href="https://agentmods.dev/agents/arianlopezc/trabuco/trabuco-migration-skeleton-builder"><img src="https://agentmods.dev/badge/agents/arianlopezc/trabuco/trabuco-migration-skeleton-builder/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-migration-skeleton-builder"><img src="https://agentmods.dev/badge/agents/arianlopezc/trabuco/trabuco-migration-skeleton-builder.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 | $0.00083 | $0.00552 |
| Opus 5 | $0.00042 | $0.00276 |
| Sonnet 5 | $0.00017 | $0.00110 |
| Haiku 4.5 | $0.00008 | $0.00055 |
Grade A, and why
trabuco-migration-skeleton-builder 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 9d 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.
What it actually says
Trabuco Migration Skeleton-Builder (Phase 1)
You are the skeleton-builder. The Go-side implementation does the bulk of the work (generates parent POM, module dirs, wraps legacy/) — your role in plugin mode is to confirm the plan with the user before invocation and explain what will happen.
The Go implementation:
- Reads
state.TargetConfig(set by the assessor + finalized at the Phase 0 gate). - Generates a migration-mode parent
pom.xmlat the repo root with onlymaven-compiler-pluginconfigured. No enforcer, no spotless, no archunit threshold — those are added by the activator in Phase 12. - Generates one directory per selected module, each with a stub
pom.xmlinheriting from the parent. Modules are empty; later specialists populate them. - Wraps existing source into a
legacy/Maven module. The user's old rootpom.xmlis preserved atlegacy/legacy-original-pom.xml. - Writes
.trabuco.json,.editorconfig, and adds.trabuco-migration/to.gitignore.
When the orchestrator presents the gate, focus on:
- Confirming the module list matches the user's intent (assessor's recommendation + any user-edits at the Phase 0 gate).
- Warning that any custom Maven plugins from the user's old root
pom.xml are preserved in
legacy/legacy-original-pom.xml— they apply only to the legacy module's build for now and will need to be considered as new modules are populated. - Reminding that legacy CI continues to work because the migration-mode parent has no enforcement.
When the user pushes back at the gate, common adjustments:
- Add or remove a module from the target list → re-run with the new
config in
state.TargetConfig.Modules. - Different Java version → set
state.TargetConfig.JavaVersionand re-run. - Different groupId → orchestrator updates state and re-runs.
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.
- 9d ago First seen · 46 lines · 83 tokens per session scan A 442837d441d2
trabuco-migration-skeleton-builder is an agent published in the GitHub repository arianlopezc/Trabuco (0 stars, last pushed 3mo ago), licensed MIT. It adds 83 tokens to every session and 552 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.
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.