Thrifthunter4you/claude-Autopilot-Kit
Autonomous engineering loop for Claude Code: queue a goal, get it researched, designed, planned, built and reported in fresh-context workers. Self-feeding hooks, tiered agent fleet, script toolbox, token & noise-floor measurement, memory/co
ARCHETYPE
Orchestrator
A bench of specialised subagents. The main agent mostly delegates.
Copy this rig
# review before running: this installs third-party code $ npx degit Thrifthunter4you/claude-Autopilot-Kit/agents ./rig-claude-autopilot-kit/agents $ npx degit Thrifthunter4you/claude-Autopilot-Kit/skills ./rig-claude-autopilot-kit/skills $ npx degit Thrifthunter4you/claude-Autopilot-Kit/hooks ./rig-claude-autopilot-kit/hooks
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 Thrifthunter4you/claude-Autopilot-Kit/skills/autopilot .claude/skills/autopilot $ curl -fsSL --create-dirs -o .claude/agents/AGENT_DESIGN.md https://raw.githubusercontent.com/Thrifthunter4you/claude-Autopilot-Kit/main/agents/AGENT_DESIGN.md $ curl -fsSL --create-dirs -o .claude/agents/agent_def_template.md https://raw.githubusercontent.com/Thrifthunter4you/claude-Autopilot-Kit/main/agents/agent_def_template.md $ curl -fsSL --create-dirs -o .claude/agents/scout.md https://raw.githubusercontent.com/Thrifthunter4you/claude-Autopilot-Kit/main/agents/scout.md $ curl -fsSL --create-dirs -o .claude/agents/triage-judge.md https://raw.githubusercontent.com/Thrifthunter4you/claude-Autopilot-Kit/main/agents/triage-judge.md $ curl -fsSL --create-dirs -o .claude/agents/wf-critic.md https://raw.githubusercontent.com/Thrifthunter4you/claude-Autopilot-Kit/main/agents/wf-critic.md $ curl -fsSL --create-dirs -o .claude/agents/wf-dedup.md https://raw.githubusercontent.com/Thrifthunter4you/claude-Autopilot-Kit/main/agents/wf-dedup.md $ curl -fsSL --create-dirs -o .claude/agents/wf-finder.md https://raw.githubusercontent.com/Thrifthunter4you/claude-Autopilot-Kit/main/agents/wf-finder.md $ curl -fsSL --create-dirs -o .claude/agents/wf-fixer.md https://raw.githubusercontent.com/Thrifthunter4you/claude-Autopilot-Kit/main/agents/wf-fixer.md $ curl -fsSL --create-dirs -o .claude/agents/wf-judge.md https://raw.githubusercontent.com/Thrifthunter4you/claude-Autopilot-Kit/main/agents/wf-judge.md $ curl -fsSL --create-dirs -o .claude/agents/wf-synth.md https://raw.githubusercontent.com/Thrifthunter4you/claude-Autopilot-Kit/main/agents/wf-synth.md $ curl -fsSL --create-dirs -o .claude/agents/wf-tester.md https://raw.githubusercontent.com/Thrifthunter4you/claude-Autopilot-Kit/main/agents/wf-tester.md $ curl -fsSL --create-dirs -o .claude/agents/wf-verifier.md https://raw.githubusercontent.com/Thrifthunter4you/claude-Autopilot-Kit/main/agents/wf-verifier.md
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 7,204 rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(rm -rf *)",
"Read(**/*.pem)",
"Bash(rm -rf /)",
"Bash(git push --force:*)",
"Bash(sudo *)",
"Read(.env)",
"Bash(rm -rf /*)",
"Read(./.env.*)",
"Read(~/.aws/**)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Read(**/*.key)",
"Read(**/.env.*)",
"Bash(sudo:*)",
"Bash(git reset --hard*)",
"Bash(git reset --hard:*)",
"Read(.env.*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(rm:*)",
"Bash(git rebase *)",
"Bash(wget *)",
"Bash(npm publish:*)",
"Bash(git commit *)",
"Bash(gh pr merge *)"
]
}
} Skills (1)
Subagents (12)
| AGENT_DESIGN | — |
| {agent_name} model: {model_tier} | |- |
| scout model: haiku | |- |
| triage-judge model: sonnet | |- |
| wf-critic model: sonnet | |- |
| wf-dedup model: haiku | |- |
| wf-finder model: haiku | |- |
| wf-fixer model: sonnet | |- |
| wf-judge model: sonnet | |- |
| wf-synth | |- |
| wf-tester model: haiku | |- |
| wf-verifier model: sonnet | |- |
Similar rigs
leavemagic-cyber/earned-confidence
A behavior contract for AI coding agents — every rule added after a real failure. Ships with a verifier agent that cannot edit what it judges.
Pragmatist 3.6k tok ·
uncoalesced/ArgusCouncil
Provenance locked, three agent research harness for any AI coding agent. A Scout downloads sources, an Archivist hashes and quotes them, an Integrator cites them into your paper, report, or dataset. A stdlib Python engine verifies every quo
Minimalist 1.2k tok ·
frontier-infra/adl
Agent Discipline Layer (ADL) — keep a coding agent honest and make it prove its work: layered guardrails + a /goal contract Warden verifies against reality and signs. Claude Code today; Grok/Codex CLI/Pi planned. (formerly Claude Layers)
Pragmatist 1.2k tok ·
j0yen/dotfiles
The claude-self cluster: machine-personal CLAUDE_SELF.md, its SessionStart hook, and the claude-self CLI.
YOLO Cowboy 4.5k tok ·