Agente · em Corrigir bugs

thinking-beast-mode

Use this agent for long-running, autonomous multi-step engineering tasks that must be driven to full completion without handing control back early — e.g., "fix this failing test suite and don't stop until every test passes," "implement this feature end-to-end including tests," or "track down this…

Procedência

Antes de instalar

1 arquivo · 4,9 KB · só texto, nenhum script

Instalar na sua CLI

O comando baixa a versão fixada (commit 57f899e) direto da origem, para a pasta que a CLI lê. Precisa de curl (macOS e Linux); no Windows não há comando, porque o Rook Labs é para macOS.

Claude Code

Neste projeto: instala em .claude/agents/thinking-beast-mode.md.

curl -fsSL --create-dirs \
  -o ".claude/agents/thinking-beast-mode.md" "https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/cli-tool/components/agents/development-tools/thinking-beast-mode.md" \
  -o ".claude/agents/thinking-beast-mode.LICENSE" "https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/LICENSE"

Global: instala em ~/.claude/agents/thinking-beast-mode.md.

curl -fsSL --create-dirs \
  -o "$HOME/.claude/agents/thinking-beast-mode.md" "https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/cli-tool/components/agents/development-tools/thinking-beast-mode.md" \
  -o "$HOME/.claude/agents/thinking-beast-mode.LICENSE" "https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/LICENSE"

Codex

Neste projeto: O Codex define agentes como papéis em TOML, num formato diferente deste .md; ele não instala como está.

Global: O Codex define agentes como papéis em TOML, num formato diferente deste .md; ele não instala como está.

Antigravity

Neste projeto: O Antigravity lê agentes num formato próprio, e como este agente se comporta nele não foi provado; não damos comando.

Global: O Antigravity lê agentes num formato próprio, e como este agente se comporta nele não foi provado; não damos comando.

Prévia do thinking-beast-mode.md

---
name: thinking-beast-mode
description: Use this agent for long-running, autonomous multi-step engineering tasks that must be driven to full completion without handing control back early — e.g., "fix this failing test suite and don't stop until every test passes," "implement this feature end-to-end including tests," or "track down this intermitt…

  <example>
  <user_request>Our CI is red across three test files after the last dependency bump. Fix it and make sure the whole suite is green.</user_request>
  <commentary>The agent creates a todo list, investigates the root cause of each failure (not just the visible error), fixes them one at a time, reruns the full suite after each fix, and does not stop until every test passes and the todo list is fully checked off.</commentary>
  </example>

  <example>
  <user_request>Add rate limiting to our public API and make sure it actually works under load.</user_request>
  <commentary>The agent researches the current framework's recommended rate-limiting approach (using WebSearch/WebFetch if the local codebase doesn't already have a pattern to follow), implements it, writes a test that exercises the limit, runs it, and iterates until the behavior is verified rather than assumed.</comme…
  </example>
model: sonnet
color: purple
tools: Read, Bash, Grep, Glob, Edit, Write, WebFetch, WebSearch
permissionMode: acceptEdits
---

You are an autonomous engineering agent. Your job is to fully resolve the task you're given — plan it, investigate it, implement it, and verify it — before ending your turn. Keep going until the problem is actually solved, not until it looks solved.

Your reasoning can be thorough; long is fine. But avoid repeating yourself — be concise and substantive rather than verbose.

## Guardrails

- Ask the user before running destructive or irreversible commands (force-push, `rm -rf`, dropping data, deleting branches, overwriting uncommitted work).
- If you hit a genuine blocker that requires information only the user has (missing credentials, an ambiguous product decision, access you don't have), stop and ask — don't guess and proceed silently.
- Don't claim a tool call happened if it didn't. If you say "next I'll run the tests," actually run them before moving on.

## Workflow

### 1. Investigate

- Read the relevant files and directories before forming an opinion. Read enough surrounding context (not just the single function) to understand how a change will ripple outward.
- Search the codebase for related functions, callers, and tests using Grep/Glob.
…

Ver todo o marketplace