GPT 5 Beast Mode

GPT 5 Beast Mode is an agent for coding agents from dhar174/custom_github_copilot_agent_builder. It costs 46 tokens per session (1,572 once invoked), scanned A, a copy of GPT 5 Beast Mode, MIT.

An autonomous coding-agent operating mode designed for GPT-5, with instructions for using tools, researching, iterating, and continuing until a task is resolved.

In plain words
What is it for?
Use it for multi-step coding work that may require investigation, tool use, repeated changes, and validation.
Why use it?
It provides a defined way to handle complex tasks with initiative while documenting assumptions and pausing for approval before broad risky edits.

Agent

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/dhar174/custom_github_copilot_agent_builder/gpt-5-beast-mode
Clone the repo
git clone --depth 1 https://github.com/dhar174/custom_github_copilot_agent_builder

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 GPT 5 Beast Mode

README.md
[![agentmods](https://agentmods.dev/badge/agents/dhar174/custom_github_copilot_agent_builder/gpt-5-beast-mode.svg)](https://agentmods.dev/agents/dhar174/custom_github_copilot_agent_builder/gpt-5-beast-mode)
Your own site
<a href="https://agentmods.dev/agents/dhar174/custom_github_copilot_agent_builder/gpt-5-beast-mode"><img src="https://agentmods.dev/badge/agents/dhar174/custom_github_copilot_agent_builder/gpt-5-beast-mode.svg" alt="Measured on agentmods" height="20"></a>
Per session 46 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,572 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 94% copy Near-identical to another mod 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 $0.00046 $0.01572
Opus 5 $0.00023 $0.00786
Sonnet 5 $0.00009 $0.00314
Haiku 4.5 $0.00005 $0.00157

Measured 3d ago against content hash 63a2e86e51f7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

GPT 5 Beast Mode 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 3d 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.

Origin

This is a copy

94% identical to GPT 5 Beast Mode — 57 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.github/agents/gpt-5-beast-mode.agent.md · 143 lines

How it starts

The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.

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 progress is possible.
  • 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

  • run_in_terminal for build/test/lint/CLI; get_terminal_output for long runs; create_and_run_task for recurring commands.

Read the full file on GitHub · 143 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. 3d ago First seen · 143 lines · 46 tokens per session scan A 63a2e86e51f7

Subscribe to this mod's changes

GPT 5 Beast Mode is an agent published in the GitHub repository dhar174/custom_github_copilot_agent_builder (7 stars, last pushed 7mo ago), licensed MIT. It adds 46 tokens to every session and 1,572 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 94% identical to GPT 5 Beast Mode, differing in 57 lines, and is treated as a copy.