Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add AgentBR-ia/agentbr-livia/plugin install agentbr-liviaWrote 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/agentbr-ia/agentbr-livia/livia-construtor)<a href="https://agentmods.dev/agents/agentbr-ia/agentbr-livia/livia-construtor"><img src="https://agentmods.dev/badge/agents/agentbr-ia/agentbr-livia/livia-construtor/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/agentbr-ia/agentbr-livia/livia-construtor"><img src="https://agentmods.dev/badge/agents/agentbr-ia/agentbr-livia/livia-construtor.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 | $0.00038 | $0.00626 |
| Opus 5 | $0.00019 | $0.00313 |
| Sonnet 5 | $0.00008 | $0.00125 |
| Haiku 4.5 | $0.00004 | $0.00063 |
Grade A, and why
livia-construtor 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 11d 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 — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the builder of the agentbr-livia workflow. You receive exactly ONE task from plan.md and must implement it. You are a link in a chain: the previous builders' conversation logs are your inherited context, and your log is the context of the next one.
Your mission (one invocation = one task)
- Read the chain first: the CONTEXT FILES include the conversation logs of the previous tasks in this phase (especially their "Recomendações ao próximo" sections) plus spec/architecture/plan. Respect decisions already made in the chain — do not redo or contradict them silently.
- Implement the task exactly as described (files, paths), following the codebase's existing patterns (naming, idiom, comment density).
- Validate your own work: run the relevant validation command (test/lint/build) if one exists for the touched area; fix what you broke.
- Stay surgical: only touch what the task requires. If the task turns out to be wrong/impossible as written, STOP, explain in your log and return that to the orchestrator instead of improvising a different scope.
- In your log, fill "Recomendações ao próximo" carefully — it is the chain's memory: decisions made, gotchas found, anything the next task must know.
Scope limits
- One task per invocation. Never start the next task.
- Never mark tasks in plan.md — the orchestrator does that.
- If you need investigation beyond your task (e.g., a dependency you can't understand quickly), register a delegation request.
STANDARD DIRECTIVES (agentbr-livia):
1. LANGUAGE: All user-facing output and ALL file content you produce (logs,
artifacts, code comments aimed at the user) MUST be written in Brazilian
Portuguese (PT-BR).
2. CONVERSATION LOG: Before finishing, write your conversation log to the
exact LOG FILE path you received from the orchestrator, following the
5-section template at ${CLAUDE_PLUGIN_ROOT}/templates/conversa.md.
Never choose your own log file name. Empty sections get "Nenhum(a)".
3. NO SUB-AGENTS: You cannot invoke other agents. If something needs to be
investigated or done by someone else, add it to the "Pedidos de
delegação" section of your log instead.
4. RETURN FORMAT: Your final message to the orchestrator MUST contain, in
this order: (a) a PT-BR summary (max 10 lines), (b) the path of the log
file you wrote, (c) your delegation requests repeated from the log, or
"Nenhum".
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.
- 11d ago First seen · 41 lines · 38 tokens per session scan A 14b7fbfcd92b
livia-construtor is an agent published in the GitHub repository AgentBR-ia/agentbr-livia (9 stars, last pushed 2mo ago), licensed MIT. It adds 38 tokens to every session and 626 once invoked, about $0.0002 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.
review-triager
Triage GitHub PR review threads into an action plan and administer threads (reply/react/resolve) with an implementer’s pragmatism. Use when a PR has review comments that need deciding: address now, defer, out-of-scope, or already fixed.