# Tier 2 autonomous mode: file denylist for pre-commit hook. # # One pattern per line. Each pattern is matched as a substring against # the staged file's relative path. Lines starting with `#` and blank # lines are ignored. # # These files are tier-2 sandbox-specific: # - setup_tier2_clone.ps1 modifies opencode.json and mcp_paths.toml # IN the clone (points MCP server at the clone, clears extra_dirs) # - The .opencode/agents/tier2-autonomous.md and # .opencode/commands/tier-2-auto-execute.md files are copied from # conductor/tier2/agents/ and conductor/tier2/commands/ into the # clone by setup_tier2_clone.ps1 # # If any of these end up in a tier-2 commit (via accidental `git add .`), # the main repo would absorb the sandbox's local config drift. # # PATTERN SCOPE: the patterns below are SPECIFIC (not prefix-based) so # they do not match the interactive Tier 2 agent prompt at # .opencode/agents/tier2-tech-lead.md (which legitimately lives in the # main repo). Edit this file when adding new tier-2 sandbox-specific # paths. # Tier-2 autonomous agent prompt (only in clone, canonical source: # conductor/tier2/agents/tier2-autonomous.md) .opencode/agents/tier2-autonomous # Tier-2 autonomous slash command (only in clone, canonical source: # conductor/tier2/commands/tier-2-auto-execute.md) .opencode/commands/tier-2-auto-execute # OpenCode config: setup_tier2_clone.ps1 overrides MCP server path + # default_agent + model in the clone's copy of this file opencode.json # MCP allowed paths: setup_tier2_clone.ps1 clears extra_dirs in the # clone's copy of this file mcp_paths.toml