RepoPilot

panniantong / agent-reach

Search panniantong/agent-reach

GitHub

Code

How panniantong/agent-reach is laid out, and where to start for common changes.

There is no import map for this report yet.

Where to start reading

  1. Repository root
  2. Repository root
  3. Likely public API
  4. Likely public API
  5. Likely start-up file
  6. Suggested starting pointAI
  7. Suggested starting pointAI
  8. Suggested starting pointAI

Find files for a task

AI

Add a new web scraping channel (e.g., a new social media platform)

  • Create a new file in agent_reach/channels/ that extends the Channel base class
  • Implement required methods: async read(), async search(), and platform-specific initialization
  • Add platform credentials and configuration keys to agent_reach/config.py
  • Register the new channel in agent_reach/cli.py argument parser and channel selection logic

Add support for a new LLM provider backend

  • Create new backend module in agent_reach/backends/ implementing the backend interface
  • Add provider configuration keys and credential handling in agent_reach/config.py
  • Integrate backend selection logic in agent_reach/core.py orchestration
  • Update CLI argument parser to expose backend selection option

Expose a new agent skill or capability via MCP

  • Define the skill logic as a new method or channel in the agent_reach/channels/ or agent_reach/core.py layer
  • Register the skill as a callable tool in agent_reach/integrations/mcp_server.py with proper JSON schema
  • Document the skill parameters, usage, and examples in agent_reach/skill/SKILL.md
  • Add reference examples in agent_reach/skill/references/ organized by category (search.md, social.md, etc.)

Change the public API

Trace runtime behavior

Add or update tests

Change build or automation

RepoPilot lists up to 500 files, so a file missing here may still exist.

  • Files marked “likely” are guessed from their names.

Code quality and hotspots

Largest source files

  • Branch points18 per file on average
  • Code issues1 error, 4 warnings
  • Largest file2,400 lines
  • Hotspot load1 high-risk file

Static checks on the 15 largest source files.

Tests, CI and tooling

  • CIGitHub Actions1 workflow
  • Tests37 test filesPytest · 1.0 test files per source file (file count, not coverage)
  • Dependency updatesNo config detected

Test folders: tests · .openteams/specs

Hotspots

Files that change often and branch heavily, highest first. Branch points count if, loop, case, catch, ternary, && and || in the file.