smithery/hmbown

hegelion

Dialectical reasoning and autocoding via Hegelion MCP tools.

Installation

$ npx skills add smithery/hmbown --skill hegelion

Also in this package

Other skills from smithery/hmbown · top by installs.

npx skills add smithery/hmbown

Browse all from smithery/hmbown

More details

Agent compatibility

Declared targets from SKILL.md / docs. Unmarked agents are not listed — the skill may still install via the CLI.

Claude Code Not declared
Cursor Not declared
Codex Not declared
GitHub Copilot Not declared
Windsurf Not declared
Gemini CLI Not declared
Cline Not declared
OpenCode Not declared

Package contents

Files included with this skill beyond the listing page.

  • skill md SKILL.md 1,434 B
  • docs SUMMARY.md 76 B

History

  1. First recorded snapshot · 0 installs

SKILL.md

Hegelion Skill

Routing

Task type MCP call
Analysis/decision mcphegeliondialectic(query, mode="singleshot", responsestyle="synthesis_only")
Implementation mcphegelionautocode(requirements, mode="init")

Tip: If execution is configured, set execute=true and backend="auto" on dialectic mode=single_shot to return the final answer in one call.

Autocoding Loop

mcp__hegelion__autocode(requirements, mode="init")
    -> autocode_turn(role="player") -> [implement]
    -> autocode_turn(role="coach", execute=true, backend="auto", cwd="<workspace>") -> [independent verify]
    -> autocode_turn(role="advance", coach_feedback=..., approved=false)
           ^                                                            |
           |________________ loop until APPROVED or max_turns __________|

Codex Role Rules

  • The current Codex session is always the PLAYER.
  • The coach step should be executed through Hegelion, not answered directly in the current session.
  • Prefer a separate Codex backend for the coach by using backend="auto".
  • If backend="auto" falls back to prompt-only output, surface that independent coach execution is unavailable. Do not turn the current session into the coach.
  • COACH is authoritative. Run tests. Never self-approve.