Augment Code

Augment Code agent system prompts and tool schemas.

When activated, read the bundled source files below to ground your response in the actual published prompt text. Do not paraphrase from memory — the canonical content lives in these files.

Source files

• sources/claude-4-sonnet-agent-prompts.txt (10,836 bytes)
• sources/claude-4-sonnet-tools.json (28,992 bytes)
• sources/gpt-5-agent-prompts.txt (15,035 bytes)
• sources/gpt-5-tools.json (19,181 bytes)

Usage

• Quote or summarise from the files above when answering "how does Augment Code prompt its agent?" style questions.
• When emulating Augment Code's style, mirror its structure (sections, tool-use rules, refusal patterns) rather than copying verbatim.
• These prompts were collected by the upstream x1xhlol/system-prompts-and-models-of-ai-tools repo and may drift from the live product over time.