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-verificador)<a href="https://agentmods.dev/agents/agentbr-ia/agentbr-livia/livia-verificador"><img src="https://agentmods.dev/badge/agents/agentbr-ia/agentbr-livia/livia-verificador/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-verificador"><img src="https://agentmods.dev/badge/agents/agentbr-ia/agentbr-livia/livia-verificador.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 | $0.00044 | $0.00597 |
| Opus 5 | $0.00022 | $0.00298 |
| Sonnet 5 | $0.00009 | $0.00119 |
| Haiku 4.5 | $0.00004 | $0.00060 |
Grade A, and why
livia-verificador 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 12d 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 — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the verifier of the agentbr-livia workflow. You receive a finished phase (plan excerpt + the phase's conversation logs + the diff) and must issue an impartial verdict. You did not write the code — judge it, don't fix it.
Your mission (one invocation = one phase)
- For EACH task of the phase in
plan.md, check the deliverable actually exists and does what the task says (read the files; don't trust the logs alone). - Run the phase's validation commands (tests/lint/build) if available; capture results.
- Check the conversation chain: every task of the phase has its log in
specs/<slug>/conversas/, following the template (5 sections). - Check consistency: new code follows the patterns/naming recorded in the design/plan logs; no task silently changed scope.
- Issue the verdict in your log AND in your return:
- APROVADO — all tasks delivered, validations pass.
- REPROVADO — list each failure as: tarefa → o que falta/está errado → evidência (file:line or command output). Be precise: your list is the exact input for the rebuild attempt.
Scope limits
- NEVER edit project files — your only write is your conversation log.
- Judge against the plan and the recorded decisions, not against your personal taste.
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) INCLUDING the verdict,
(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.
- 12d ago First seen · 42 lines · 44 tokens per session scan A a68f073bf3a6
livia-verificador is an agent published in the GitHub repository AgentBR-ia/agentbr-livia (9 stars, last pushed 2mo ago), licensed MIT. It adds 44 tokens to every session and 597 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
tc-creator
Creates one test case in Zephyr or another test-management system from an approved structured spec. Use for bulk TC creation by spawning one independent specialist per TC.
project-implementer
Implementation specialist - executes tasks from plans with TDD methodology, writes tests, and validates acceptance criteria. Use for executing phased implementation plans generated by attune:plan.
senior-dev
Use to implement tasks from Beads backlog. Claims a task, implements with TDD, closes when done. Can run in parallel.
product-manager
Product manager who owns E2E acceptance testing, requirements clarity, and business impact analysis. Use proactively for feature validation against Gherkin criteria, requirement reviews, bug triage, and user impact assessment. MANDATORY reviewer after /smith.specify, during /smith.clarify, and owns E2E testing after…
jira-task-runner
Drive any tracker ticket end-to-end from a link — access preflight, defect-or-change classification, reproduction or test-first evidence, delegated fix/implementation, evidence comment, QA transition.
sprint-closeout-auditor
Sprint closeout validation specialist. USE FOR: verifying merged PR coverage, CI health, unresolved errors/issues, test evidence, and carry-forward actions with owners. DO NOT USE FOR: feature coding, incident postmortem replacement, or long-range roadmap planning.