Bootgear — AI skill for Claude Code
Agent harness framework - the gear between LLM motors and user skills/tools/configs/docs.
How to install Bootgear
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open vancsj/bootgear and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Bootgear does
Agent harness framework - the gear between LLM motors and user skills/tools/configs/docs.
Alternatives in AI
- Loushang — AI-native agent harness for coding workflows by python: multi-model LLM orchestration, stateful sessions, tool 1.3k ★
- Memtrace Public — Structural memory for AI coding agents 466 ★
- LLM Council Skill — A skill to claude code that enables brainstorming with other LLMs (ChatGPT, Gemini) before presenting the impl 416 ★
README
bootgear
An agent harness framework — the gear between the LLM motor and your skills, tools, configs, and docs.
What is bootgear?
bootgear is a curated collection of general-purpose, extensible **skills**, **agents**, and **hooks** for coding-agent workflows.
Think of an LLM as a motor: raw power, no direction. A motor alone doesn't move anything — it needs a transmission that converts spin into motion, mounted on a chassis you can actually load your cargo onto. bootgear is that layer. It sits between the model and your assets, routes work through an opinionated loop, and lets you bolt on your own gear where it matters.
your skills / tools / configs / docs <- what makes each project different
^
| bootgear: routing, invocation, governance
v
LLM <- the motor
Design principles
**General by design.** Framework-level skills and agents hold no project-specific knowledge. They are reusable across projects, languages, and teams.
**The framework drives (IoC).** Inspired by Spring Boot: you don't call the framework, the framework calls you. Register your skills, agents, and hooks — bootgear owns the lifecycle and invokes them at the right points in the loop.
**Opinionated defaults, explicit overrides.** Every component works out of the box with sensible defaults, and every component declares its customization points. Tune preferences, swap steps, or extend behavior without forking the skill.
**Your workflow stays yours.** bootgear puts you inside a productive loop, not inside a black box. You always see which gear is engaged and can steer at any point.
How is this different from [superpowers](https://github.com/obra/superpowers)?
superpowers proved that a strong, opinionated skill set makes agents dramatically more capable. But its opinions are take-it-or-leave-it: if a skill's assumptions don't fit your project or taste, your options are to live
Related Skills
Integrate External Codebase
Integrate an external codebase for AI-assisted analysis and development. Example - /integrate-external-codebas
Whichmodels
Research the latest Anthropic models (docs, benchmarks, user reports), then propose which model and effort eac
Sth Log
Record a changelog entry. AI auto-infers change type (Feature / Fix / Refactor / Docs / Breaking) and computes
Blueprints Skill
Cross-tool Agent Skill (SKILL.md) that turns any AI coding tool — OpenCode, Claude Code, Codex, Gemini, Cursor
Gdrive Cart
GDrive Context Cart (Context Bridge) — visual context staging between Google Drive and AI agent harnesses (Her
Harness Docs
Düzenek Mühendisliği (Harness Engineering) — AI kod ajanlarını güvenilir kılan çevreyi tasarlayan Türkçe açık
Related Agents
Agentic Auditor
PYA specialist spawned by the /pya orchestrator. Audits AI agent and LLM surfaces in an untrusted repository:
Pack Coder
Use to execute approved implementation plans against pack source — writing/editing scripts, fixtures, configs,
Project Reviewer Adams
Use for reviewing PRs or auditing project consistency across code, configs, docs, and tests, including structu