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/plan)<a href="https://agentmods.dev/commands/agentbr-ia/agentbr-livia/plan"><img src="https://agentmods.dev/badge/commands/agentbr-ia/agentbr-livia/plan.svg" alt="Measured on agentmods" 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 | $0.00020 | $0.00647 |
| Opus 5 | $0.00010 | $0.00324 |
| Sonnet 5 | $0.00004 | $0.00129 |
| Haiku 4.5 | $0.00002 | $0.00065 |
Grade A, and why
plan 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan — Orchestrated Task Planning
You are the orchestrator of the planning stage. The file-per-story mapping is delegated to livia-analista-padroes (catalog: ${CLAUDE_PLUGIN_ROOT}/AGENTES.md); you consolidate it into the task plan.
User Input
$ARGUMENTS
You MUST consider the user input before proceeding (if not empty).
Prerequisites
./specs/<feature_slug>/spec.mdandarchitecture.mdexist (feature from current git branch; ask if unclear).- Architecture has no unresolved "Questões em Aberto". If it has, STOP and tell the user to resolve them via
/design.
Step 1: Delegate work mapping
Invoke livia-analista-padroes in plan mode (invocation contract from AGENTES.md):
- GOAL: for each user story in the architecture, list exact files to create/modify, flag independent (parallelizable) vs colliding file groups, and list available validation commands (tests, linter, build).
- CONTEXT FILES: spec.md, architecture.md, contracts.md (if any), previous design logs.
- LOG FILE:
specs/<slug>/conversas/NNN-plan-analista-padroes.md.
Step 2: Generate plan.md
Read the analyst's log and write specs/<feature_slug>/plan.md following ${CLAUDE_PLUGIN_ROOT}/templates/plan.md, in PT-BR:
Phases: Setup → Foundational (only blocking prerequisites — nothing story-specific) → one phase per user story in priority order (P1 first = MVP) → Polish & Validação.
Tasks:
- Format:
- [ ] TNNN [P] [USn] descrição concreta com caminho de arquivo - Granularity: 15–30 minutes each; specific enough for an agent to execute without guessing.
[P]ONLY when tasks touch different files with no logical dependency (use the analyst's collision map).- Include validation tasks per phase using the commands the analyst found.
- Test-writing tasks only if the spec requests them (then tests come before implementation).
Also include: time estimate per phase, dependency graph, user-story independence notes, parallel opportunities, MVP definition.
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 · 56 lines · 20 tokens per session scan A 8fd4f0c10ade
plan is a command published in the GitHub repository AgentBR-ia/agentbr-livia (9 stars, last pushed 2mo ago), licensed MIT. It adds 20 tokens to every session and 647 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.