autowarefoundation/autoware-harness
Autoware expertise, packaged for your coding agent — skills, agents, harness, mcps that turn any AI assistant into an autonomous driving domain expert.
stack: Shell
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
Copy this rig
# review before running: this installs third-party code
$ npx degit autowarefoundation/autoware-harness/.claude ./rig-autoware-harness # inspect, then merge into .claude/ 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 autowarefoundation/autoware-harness/.agents/skills/create-new-skill .claude/skills/create-new-skill $ npx degit autowarefoundation/autoware-harness/.agents/skills/pre-commit .claude/skills/pre-commit $ npx degit autowarefoundation/autoware-harness/.agents/skills/technical-english .claude/skills/technical-english $ npx degit autowarefoundation/autoware-harness/skills/awh-build-colcon .claude/skills/awh-build-colcon $ npx degit autowarefoundation/autoware-harness/skills/awh-build-fix-colcon .claude/skills/awh-build-fix-colcon $ npx degit autowarefoundation/autoware-harness/skills/awh-interface-msg-format .claude/skills/awh-interface-msg-format $ npx degit autowarefoundation/autoware-harness/skills/awh-meta-self-update .claude/skills/awh-meta-self-update
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 (7)
Similar rigs
benyoskovitz/claude-code-workflow
A practical, opinionated Claude Code workflow: a task-rubric loop that makes AI-written code trustworthy, a lean CLAUDE.md pattern, and a lab for versioning your own setup
Pragmatist 127 tok · · Q0
sleepy-panda-srl/portulan
An operating framework for agentic engineering: the tailored context, standards, gates and institutional memory a team needs so any coding agent works their way. Open-core by Sleepy Panda SRL.
Fort Knox 643 tok · · Q52
goulvenclech/dotclaude
Dotfiles for Claude Code : versioned agents, skills, and settings.
YOLO Cowboy 1.3k tok · · Q8
undeadlist/claude-code-agents
Claude Code Agents Prompt templates for Claude Code's subagent system. Run parallel code audits, automate fix cycles, get stuff reviewed. Built for the Claude Code Task tool. Not a framework. Just prompts that work. What This Does Claude Co
Orchestrator 2.2k tok · · Q3