
Octocode Research
This is a multi-phase code exploration system that spins up an HTTP server to orchestrate deep repository analysis. It walks through strict gates: server init, context loading, fast-path evaluation (for simple lookups), planning, parallel research execution, and structured output. You get exact file references and line numbers, not assumptions. It supports both HTTP-based tool calls and direct MCP mode if octocode-mcp is available. The prompt selection is task-specific (local research, PR review, implementation planning, or code roasting). Use this when you need planned, multi-step investigation across a codebase. For quick "where is X defined" queries, the lighter octocode-researcher skill is enough. The phase discipline is rigid but keeps complex research from going off the rails.
- skills.sh installs
- 226
- GitHub stars
- 854
- last updated
- Jun 3, 2026
Install
$ npx -y skills add bgauryy/octocode-mcp --skill octocode-research --agent claude-codeInstalls into .claude/skills of the current project.
Files
Octocode Research
Evidence before assertion. Find the anchor, read the exact bytes, prove the claim, then answer or patch.
FRAME → CLASSIFY → MODEL → SEARCH → READ EXACT → PROVE → DECIDE/PATCH → VERIFY
That's the full shape, not a checklist to march through. Scale it to the claim: a small lookup gets a cheap read and an honest confidence label; a delete, a merge verdict, or a root cause earns the whole ladder. Skip stages you can already answer — but say which ones you skipped.
The rules
Sponsors
Details
- Repository
- github.com/bgauryy/octocode-mcp
- Categories
- AI & Agent Building, Data Science & ML
- First seen
- Jun 3, 2026