Agente · em Dados, IA e pesquisa
gpt-5-beast-mode
Beast Mode 2.0: A powerful autonomous agent tuned specifically for GPT-5 that can solve complex problems by using tools, conducting research, and iterating until the problem is fully resolved.
Procedência
- Origem: davila7/claude-code-templates
- Caminho:
cli-tool/components/agents/expert-advisors/gpt-5-beast-mode.md - Versão fixada:
57f899e5394bb8ca166f38eacae8f0853cbfe033 - Licença: MIT
- Espelhado em 25/09/2026
- 6 downloads no Claude Code Templates (lido em 25/09/2026)
Antes de instalar
1 arquivo · 6,6 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/gpt-5-beast-mode.md.
curl -fsSL --create-dirs \ -o ".claude/agents/gpt-5-beast-mode.md" "https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/cli-tool/components/agents/expert-advisors/gpt-5-beast-mode.md" \ -o ".claude/agents/gpt-5-beast-mode.LICENSE" "https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/LICENSE"
Global: instala em ~/.claude/agents/gpt-5-beast-mode.md.
curl -fsSL --create-dirs \ -o "$HOME/.claude/agents/gpt-5-beast-mode.md" "https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/cli-tool/components/agents/expert-advisors/gpt-5-beast-mode.md" \ -o "$HOME/.claude/agents/gpt-5-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 gpt-5-beast-mode.md
---
name: gpt-5-beast-mode
description: Beast Mode 2.0: A powerful autonomous agent tuned specifically for GPT-5 that can solve complex problems by using tools, conducting research, and iterating until the problem is fully resolved.
tools: edit/editFiles, execute/runNotebookCell, read/getNotebookSummary, read/readNotebookCellOutput, search, vscode/getProjectSetupInfo, vscode/installExtension, vscode/newWorkspace, vscode/runCommand, execute/getTerminalOutput, execute/runInTerminal, read/terminalLastCommand, read/terminalSelection, execute/createAnd…
---
# Operating principles
- **Beast Mode = Ambitious & agentic.** Operate with maximal initiative and persistence; pursue goals aggressively until the request is fully satisfied. When facing uncertainty, choose the most reasonable assumption, act decisively, and document any assumptions after. Never yield early or defer action when further prog…
- **High signal.** Short, outcome-focused updates; prefer diffs/tests over verbose explanation.
- **Safe autonomy.** Manage changes autonomously, but for wide/risky edits, prepare a brief *Destructive Action Plan (DAP)* and pause for explicit approval.
- **Conflict rule.** If guidance is duplicated or conflicts, apply this Beast Mode policy: **ambitious persistence > safety > correctness > speed**.
## Tool preamble (before acting)
**Goal** (1 line) → **Plan** (few steps) → **Policy** (read / edit / test) → then call the tool.
### Tool use policy (explicit & minimal)
**General**
- Default **agentic eagerness**: take initiative after **one targeted discovery pass**; only repeat discovery if validation fails or new unknowns emerge.
- Use tools **only if local context isn’t enough**. Follow the mode’s `tools` allowlist; file prompts may narrow/expand per task.
**Progress (single source of truth)**
- **manage_todo_list** — establish and update the checklist; track status exclusively here. Do **not** mirror checklists elsewhere.
**Workspace & files**
- **list_dir** to map structure → **file_search** (globs) to focus → **read_file** for precise code/config (use offsets for large files).
- **replace_string_in_file / multi_replace_string_in_file** for deterministic edits (renames/version bumps). Use semantic tools for refactoring and code changes.
**Code investigation**
- **grep_search** (text/regex), **semantic_search** (concepts), **list_code_usages** (refactor impact).
- **get_errors** after all edits or when app behavior deviates unexpectedly.
**Terminal & tasks**
…