by can1357
⌥ AI Coding agent for the terminal — hash-anchored edits, optimized tool harness, LSP, Python, browser, subagents, and more
# Add to your Claude Code skills
git clone https://github.com/can1357/oh-my-piNo comments yet. Be the first to share your thoughts!
AI-powered conventional commit generation with intelligent change analysis:
git-overview, git-file-diff, git-hunk for fine-grained analysisCHANGELOG.md files--legacy flag for deterministic pipeline when preferredomp commit with options: --push, --dry-run, --no-changelog, --contextExecute Python code with a persistent IPython kernel and rich helper prelude:
lines(), insert_at(), delete_lines(), delete_matching() and related helpers for precise editspython.sharedGateway setting).omp/modules/ and ~/.omp/agent/modules/display() for HTML, Markdown, images, and interactive JSON treesomp setup pythonFull IDE-like code intelligence with automatic formatting and diagnostics:
diagnostics, definition, type_definition, implementation, references, hover, symbols, rename, code_actions, status, reloadlsp action diagnostics (without a file)node_modules/.bin/, .venv/bin/, etc.occurrence parameter resolves repeated symbols on the same lineZero context-use rules that inject themselves only when needed:
ttsrTrigger field in rule files (regex pattern)Example: A "don't use deprecated API" rule only activates when the model starts writing deprecated code, saving context for sessions that never touch that API.
Structured code review with priority-based findings:
/review command: Interactive mode selection (branch comparison, uncommitted changes, commit review)report_finding tool with priority levels (P0-P3: critical → nit)Parallel execution framework with specialized agents and real-time streaming:
agent://<id> resources when previews truncateisolated: true runs tasks in git worktrees, Unix fuse-overlay filesystems, or Windows ProjFS (fuse-projfs), with patch or branch merge strategiesawait tool for blocking on results/agents dashboard for managing and creating custom agents~/.omp/agent/agents/) and project-level (.omp/agents/) custom agentsConfigure different models for different purposes with automatic discovery:
default, smol, slow, plan, and commit rolesmodel: pi/smol for cost-effective exploration--smol, --slow, --plan) and env vars (PI_SMOL_MODEL, PI_SLOW_MODEL, PI_PLAN_MODEL)/model selector and persist assignments to settingsStructured task management with phased progress tracking:
replace (setup), add_phase, add_task, update (status changes), remove_taskpending, in_progress, completed, abandoned