@@ -13,7 +13,7 @@ Codebuff beats Claude Code at 61% vs 53% on [our evals](evals/README.md) across
1313
1414When you ask Codebuff to "add authentication to my API," it might invoke:
1515
16- 1 . A ** File Explorer Agent** to scan your codebase to understand the architecture and find relevant files
16+ 1 . A ** File Picker Agent** to scan your codebase to understand the architecture and find relevant files
17172 . A ** Planner Agent** to plan which files need changes and in what order
18183 . An ** Editor Agent** to make precise edits
19194 . A ** Reviewer Agent** to validate changes
@@ -47,33 +47,6 @@ Then just tell Codebuff what you want and it handles the rest:
4747
4848Codebuff will find the right files, makes changes across your codebase, and runs tests to make sure nothing breaks.
4949
50- ### CLI Options
51-
52- Control how Codebuff runs with these flags:
53-
54- ** Quality & Performance** :
55- - ` --lite ` - Use budget models and fetch fewer files (faster, lower cost)
56- - ` --max ` - Use higher quality models and fetch more files (thorough, slower)
57-
58- ** Modes** :
59- - ` --ask ` - Ask mode, won't change code (safe for exploration)
60- - ` --print, -p ` - Print-only mode, run once and exit (for scripts/CI)
61-
62- ** Agent Control** :
63- - ` --agent <id> ` - Run specific agent (skips loading local ` .agents ` overrides)
64- - ` --spawn <id> ` - Spawn agent directly (e.g., ` --spawn reviewer ` )
65- - ` --params <json> ` - Pass JSON parameters to agent
66-
67- ** Debugging** :
68- - ` --trace ` - Log all subagent activity to ` .agents/traces/*.log `
69- - ` --cwd <dir> ` - Run in specific directory instead of current
70-
71- ** Project Setup** :
72- - ` --init ` - Initialize Codebuff for your project
73- - ` --create <template> ` - Create new project from template
74-
75- Run ` codebuff --help ` for full details and examples.
76-
7750## Create custom agents
7851
7952To get started building your own agents, start Codebuff and run the ` /init ` command:
0 commit comments