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/commands/agentbr-ia/agentbr-livia/design)<a href="https://agentmods.dev/commands/agentbr-ia/agentbr-livia/design"><img src="https://agentmods.dev/badge/commands/agentbr-ia/agentbr-livia/design/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/commands/agentbr-ia/agentbr-livia/design"><img src="https://agentmods.dev/badge/commands/agentbr-ia/agentbr-livia/design.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 | $0.00026 | $0.00730 |
| Opus 5 | $0.00013 | $0.00365 |
| Sonnet 5 | $0.00005 | $0.00146 |
| Haiku 4.5 | $0.00003 | $0.00073 |
Grade A, and why
design scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design — Orchestrated Architecture Design
You are the orchestrator of the design stage. Research and codebase analysis are delegated to catalog agents (${CLAUDE_PLUGIN_ROOT}/AGENTES.md); you consolidate their conversation logs into the architecture.
User Input
$ARGUMENTS
You MUST consider the user input before proceeding (if not empty).
Prerequisites
./specs/<feature_slug>/spec.mdexists (identify<feature_slug>from the current git branch; ask if unclear).- The spec has NO unresolved
[NEEDS CLARIFICATION]markers. If it has, STOP: tell the user to finish/discoverfirst.
Step 1: Delegate investigation (parallel)
Decide what needs investigation, then invoke IN PARALLEL (one Task each, following the invocation contract in AGENTES.md — GOAL, CONTEXT FILES, LOG FILE with orchestrator-assigned NNN, STANDARD DIRECTIVES):
livia-analista-padroes(always) — GOAL: map stack, patterns, conventions, similar features and reusable components relevant to the spec. LOG FILE:specs/<slug>/conversas/NNN-design-analista-padroes.md.livia-pesquisador(only if the spec involves libraries/APIs/practices you don't know well) — GOAL: the specific list of technologies/questions. Don't delegate what you already know. LOG FILE:specs/<slug>/conversas/NNN-design-pesquisador.md.
If returns contain delegation requests, resolve them with ONE extra targeted round at most (typically livia-explorador-dependencias), then move on — leftovers become "Questões em Aberto" in the architecture.
Step 2: Consolidate architecture.md
Read the new conversation logs plus the discovery logs, then write specs/<feature_slug>/architecture.md following ${CLAUDE_PLUGIN_ROOT}/templates/architecture.md, in PT-BR:
- Every technical decision records rationale, alternatives and trade-offs, citing the supporting logs (
conversas/NNN-....md). - Follow the codebase's existing patterns (from the analyst's log) — don't reinvent.
- Map every user story to concrete files.
- Keep it pragmatic: boring, proven choices; think testability and maintenance.
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 · 57 lines · 26 tokens per session scan A e537d0520f19
design is a command published in the GitHub repository AgentBR-ia/agentbr-livia (9 stars, last pushed 2mo ago), licensed MIT. It adds 26 tokens to every session and 730 once invoked, about $0.0001 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 commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.