Local LLMs & agentsProject record · Sep 2026

Local LLM Inference & Agents

Claude Code Autopilot

An installation and activation layer combining upstream coding skills, specialized agents, and hooks into a reusable project toolkit.

ShellPythonTypeScriptClaude CodeHooksCodexSkills
Why it sits here. Useful reusable tooling adaptation; rank below original systems because most skills and agents come from credited upstream projects.
04 / Follow a thought through the machine.STUDY IN SPACE

01 / IMPLEMENTATION & CONTRIBUTION

What the work involves

Donald built the installer and refined session-start and review behavior around upstream obra/superpowers and diet103 skills. Those integrated skills and agents remain credited to their authors.

Technical depth

Prompt hooks select relevant skills, session hooks restore context, installation backs up existing files and installs hook dependencies, and review workflow was revised away from a blocking hook toward a skill-based approach.

The project family

claude-code-autopilot

02 / RESULTS

What came out of it

A reusable setup script backs up existing files, installs hook dependencies, and activates context and review workflows for coding projects.

03 / SUPPORTING EVIDENCE

Follow the source

Implementation notes, project records, and supporting artifacts.

Source context & project scope

Upstream skill counts and production-tested wording belong to the integrated ecosystems, not independent proof of Donald deployment outcomes.

No quantified productivity benefit or broad installation compatibility was established.

Explicit upstream attribution, activation behavior, reusable hooks, installation design.

SOURCE · 2026-09-17

Installer implementation and backup/verification flow.

SOURCE · 2026-09-17

Review integration implementation.

SOURCE · 2026-09-17

Donald installer and review-workflow revisions.

SOURCE · 2026-09-17
CONTINUE IN LOCAL LLM INFERENCE & AGENTS

ZhengMind architecture study