vancsj/bootgear
Agent harness framework - the gear between LLM motors and user skills/tools/configs/docs
field: AI / ML workflow: PR / code reviewPlanning & specsFrontend & designGit & commitsSecurity review
stack: Python
ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
Copy this rig
$ git clone --depth 1 https://github.com/vancsj/bootgear MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.
$ npx degit vancsj/bootgear/codex-plugins/engine/skills/clarify .claude/skills/clarify $ npx degit vancsj/bootgear/codex-plugins/engine/skills/converge .claude/skills/converge $ npx degit vancsj/bootgear/codex-plugins/engine/skills/debate .claude/skills/debate $ npx degit vancsj/bootgear/codex-plugins/engine/skills/execute .claude/skills/execute $ npx degit vancsj/bootgear/codex-plugins/engine/skills/recall .claude/skills/recall $ npx degit vancsj/bootgear/codex-plugins/engine/skills/resolve .claude/skills/resolve $ npx degit vancsj/bootgear/codex-plugins/engine/skills/review .claude/skills/review $ npx degit vancsj/bootgear/codex-plugins/engine/skills/spec-review .claude/skills/spec-review $ npx degit vancsj/bootgear/codex-plugins/engine/skills/spec .claude/skills/spec $ npx degit vancsj/bootgear/codex-plugins/engine/skills/start .claude/skills/start $ npx degit vancsj/bootgear/plugins/advisor/skills/advisor .claude/skills/advisor $ npx degit vancsj/bootgear/plugins/deputy/skills/ask .claude/skills/ask $ npx degit vancsj/bootgear/plugins/deputy/skills/record .claude/skills/record $ npx degit vancsj/bootgear/plugins/memory-ledger/skills/ledger .claude/skills/ledger $ npx degit vancsj/bootgear/plugins/memory-ledger/skills/setup .claude/skills/setup
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 16.2k rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(./.env.*)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(git push --force:*)",
"Read(**/*.pem)",
"Read(.env)",
"Read(~/.aws/**)",
"Read(**/*.key)",
"Read(**/.env.*)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Bash(rm -rf *)",
"Bash(sudo *)",
"Bash(sudo:*)",
"Bash(rm -rf /)",
"Bash(git push -f:*)",
"Read(.env.*)",
"Bash(git reset --hard*)",
"Bash(rm -rf /*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(gh pr merge *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(gh pr merge:*)",
"Bash(gh pr create *)",
"Bash(git reset --hard:*)",
"Bash(npm publish:*)",
"Bash(git rebase *)"
]
}
} Skills (15)
Similar rigs
JuuuuHong/kiro-bridge
Claude Code plugin that bridges to Kiro CLI — structured context handoff, spec-driven delegation, ACP-ready transport
Minimalist 217 tok · · Q0
vegardjorg/ravenseat
Your Claude Code agents keep building. You make the decisions. A local-first work queue that runs parallel agents in isolated worktrees, checks their work with your own gates, and keeps the project moving across sessions.
Skill Collector 1.0k tok · · Q0
machiko/agent-working-agreements
Incident-backed working agreements for AI coding agents
Pragmatist 243 tok · · Q0
JanSzewczyk/spec-driven-development
Spec-Driven Development framework for Claude Code — slash commands take a feature from spec through clarify, plan and tasks, hand each self-contained task to your own implementation flow, and verify the result against the acceptance criteri
Skill Collector 3.8k tok · · Q0