discover

discover is a command for Claude Code from AgentBR-ia/agentbr-livia. It costs 15 tokens per session (963 once invoked), scanned A, original, MIT.

A command that creates a feature specification through several rounds of delegated investigation. It uses explorer agents to examine code, requirements, dependencies, and risks, then combines their findings into a specification.

In plain words
What is it for?
Use it to explore a proposed feature, create its specification, organize the supporting logs, and prepare the repository for later planning and implementation.
Why use it?
It gives a project a structured starting point before implementation and records the investigation in files and conversation logs. It also requires a feature branch and a supplied feature description.

Command for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: mentions subagents.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the agentbr-livia plugin — 5 commands, 8 agents shipped together

Good fit Use it to explore a proposed feature, create its specification, organize the supporting logs, and prepare the repository for later planning and implementation.

Compare 6 commands from other repositories ↓
Install

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.

Claude Code
/plugin marketplace add AgentBR-ia/agentbr-livia
Claude Code
/plugin install agentbr-livia

Made for: Claude Code.

Or install agentbr-livia, the plugin that ships this one along with the rest of its 5 commands, 8 agents.

Wrote 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.

agentmods badge for discover

README.md
[![agentmods](https://agentmods.dev/badge/commands/agentbr-ia/agentbr-livia/discover.svg)](https://agentmods.dev/commands/agentbr-ia/agentbr-livia/discover)
Your own site
<a href="https://agentmods.dev/commands/agentbr-ia/agentbr-livia/discover"><img src="https://agentmods.dev/badge/commands/agentbr-ia/agentbr-livia/discover.svg" alt="Measured on agentmods" height="20"></a>
Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 963 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00015 $0.00963
Opus 5 $0.00008 $0.00481
Sonnet 5 $0.00003 $0.00193
Haiku 4.5 $0.00002 $0.00096

Measured 8d ago against content hash 90a45c6b68d3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

discover 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.

agentbr-livia/commands/discover.md · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Discover — Orchestrated Feature Discovery

You are the orchestrator of the discovery stage. You do not investigate by yourself: you delegate to the explorer agents from the catalog (${CLAUDE_PLUGIN_ROOT}/AGENTES.md), read their conversation logs, and consolidate the spec. Only you may invoke agents — sub-agents never invoke sub-agents.

User Input

$ARGUMENTS

You MUST consider the user input before proceeding. If empty: ERROR "Nenhuma descrição de feature fornecida" and stop.

The input may be: natural language requirements, a path to a requirements file, or a project-management card reachable via MCP tools. Acquire the content accordingly.

Step 1: Setup

  1. Create a git-branch-friendly <feature_slug> not already present in ./specs/.
  2. Create ./specs/<feature_slug>/ and ./specs/<feature_slug>/conversas/.
  3. Ensure you are on a branch named <feature_slug> (create it if needed; if the folder is not a git repo, offer git init first).

Step 2: Discovery rounds (max 3)

Follow this loop exactly:

round = 1
agents = [livia-explorador-codigo, livia-explorador-requisitos,
          livia-explorador-dependencias, livia-explorador-riscos]  # round 1
while round <= 3:
    invoke the round's agents IN PARALLEL (one Task per agent)
    collect the "Pedidos de delegação" from all returns
    if no requests remain: break
    agents = agents suggested by the requests (typically
             livia-explorador-dependencias), one Task per
             coherent group of requests
    round += 1

Every Task prompt MUST contain (see AGENTES.md → Standard Directives):

  1. GOAL: the specific mission for this invocation (for round 2+, quote the delegation requests being answered)
  2. CONTEXT FILES: paths of previous conversation logs + any referenced requirement files
  3. LOG FILE: specs/<feature_slug>/conversas/NNN-discover-<agente-sem-prefixo>.mdyou assign the sequential NNN; agents never pick their own log name
  4. The STANDARD DIRECTIVES block from ${CLAUDE_PLUGIN_ROOT}/AGENTES.md

Read the full file on GitHub · 88 lines

Changes

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.

  1. 8d ago First seen · 88 lines · 15 tokens per session scan A 90a45c6b68d3

Subscribe to this mod's changes

discover is a command published in the GitHub repository AgentBR-ia/agentbr-livia (9 stars, last pushed 2mo ago), licensed MIT. It adds 15 tokens to every session and 963 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.