skills.rest
Wenbobobo
WenboboboCOMMUNITY
Explore all skills by this author →
GitHub

archon-supervisor

Coordinates supervised AutoArchon runs with fidelity checks and restart-state management.

Updated Apr 11, 2026
Search Tags:#workflow#fidelity#cycles#supervise#autoarchon#log-watching#restart-state
One-click install
npx skills add https://github.com/Wenbobobo/AutoArchon --skill archon-supervisor
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: archon-supervisor
Source: https://github.com/Wenbobobo/AutoArchon/tree/main/skills/archon-supervisor
Command: npx skills add https://github.com/Wenbobobo/AutoArchon --skill archon-supervisor

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This skill helps maintain control over long-running AutoArchon runs, preserving fidelity and restart-state integrity during repeated plan/prover cycles.

Core Features & Use Cases

  • One-cycle supervision with real-time log watching, fidelity checks, and restart-state management.
  • Guardrails and run-lease handling to prevent drift and contamination between runs.
  • Documentation of state transitions in HOT_NOTES.md and LEDGER.md to support reliable recovery and postmortems.

Quick Start

Initiate a supervised cycle by running uv run --directory /path/to/AutoArchon autoarchon-supervised-cycle --workspace /path/to/run-root/workspace --source /path/to/run-root/source.

Frequently Asked Questions about archon-supervisor

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I supervise long-running AutoArchon runs to preserve fidelity?▼

Supervise long-running AutoArchon runs by orchestrating iterative plan/prover cycles via the autoarchon-supervised-cycle command, which enforces run leases and manages restart state to preserve fidelity.

What is the best way to prevent drift and contamination between repeated plan/prover cycles?▼

Prevent drift and contamination by applying guardrails and run-lease handling that enforce boundaries, alongside log watching and artifact hygiene during external supervision of repeated cycles.

How do I restart a failed AutoArchon benchmark slice without losing state?▼

Restart a failed benchmark slice by reading workspace/.archon state files to recover restart state, ensuring fidelity is preserved across the next iterative plan/prover cycle.

Does AutoArchon supervision support soak tests and external log watching?▼

AutoArchon supervision applies to soak tests and any run requiring external supervision, providing real-time log watching, fidelity checks, and restart-state management.

How do I document state transitions for AutoArchon run recovery and postmortems?▼

Document state transitions for recovery and postmortems by writing updates to HOT_NOTES.md and LEDGER.md, which support reliable recovery during repeated plan/prover cycles.

When should I not use external supervision for AutoArchon workflows?▼

Avoid external supervision for AutoArchon workflows when runs are short-lived or do not require iterative plan/prover cycles, as the run-lease handling and state file management add unnecessary overhead.

Related Skills

Explore More Software Engineering Skills→
outfitter-devoutfitter-dev
28

claude-config-management

Configure Claude Desktop and Claude Code settings, MCP servers, and environment variables.

Official
Intermediate
Dorpeer95Dorpeer95

trader-memory-core

Track investment theses through lifecycle transitions and generate postmortems.

Community
Advanced
yiwei79yiwei79

agentic-eval

Evaluate and refine agent outputs through structured reflection loops.

Official
Advanced
ether-moonether-moon

monitors

Manage long-running background monitors for orchestration state and external systems.

Community
Advanced