Dialectical reasoning and autocoding via Hegelion MCP tools.
Scanned 9/8/2026
Install to Claude Code
npx -y skills add Hmbown/Hegelion --skill hegelion --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Hegelion?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/hmbown-hegelion)More formats (shields.io, HTML) on the badges page.
---
name: hegelion
description: Dialectical reasoning and autocoding via Hegelion MCP tools.
---
# Hegelion Skill
## Routing
| Task type | MCP call |
|-----------|----------|
| Analysis/decision | `mcp__hegelion__dialectic(query, mode="single_shot", response_style="synthesis_only")` |
| Implementation | `mcp__hegelion__autocode(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.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.
Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.
A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling