DEVfancybear/harness-agents
Terminal coding agent in Rust where the harness, not the model, decides when work is done: approval-gated tools, a persistent Python REPL, project checks plus an independent verifier, background agents, learned skills and prompt caching
ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
Copy this rig
$ git clone --depth 1 https://github.com/DEVfancybear/harness-agents 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 DEVfancybear/harness-agents/.agents/skills/agent-message .claude/skills/agent-message $ npx degit DEVfancybear/harness-agents/.agents/skills/agent-observe .claude/skills/agent-observe $ npx degit DEVfancybear/harness-agents/.agents/skills/attach-image .claude/skills/attach-image $ npx degit DEVfancybear/harness-agents/.agents/skills/compact .claude/skills/compact $ npx degit DEVfancybear/harness-agents/.agents/skills/edit .claude/skills/edit $ npx degit DEVfancybear/harness-agents/.agents/skills/find-skills .claude/skills/find-skills $ npx degit DEVfancybear/harness-agents/.agents/skills/github-deep-research .claude/skills/github-deep-research $ npx degit DEVfancybear/harness-agents/.agents/skills/goal .claude/skills/goal $ npx degit DEVfancybear/harness-agents/.agents/skills/mcp .claude/skills/mcp $ npx degit DEVfancybear/harness-agents/.agents/skills/parallel-task-spark .claude/skills/parallel-task-spark $ npx degit DEVfancybear/harness-agents/.agents/skills/parallel-task .claude/skills/parallel-task $ npx degit DEVfancybear/harness-agents/.agents/skills/refine .claude/skills/refine $ npx degit DEVfancybear/harness-agents/.agents/skills/rlm-heartbeat .claude/skills/rlm-heartbeat $ npx degit DEVfancybear/harness-agents/.agents/skills/skill-creator .claude/skills/skill-creator $ npx degit DEVfancybear/harness-agents/.agents/skills/super-swarm-spark .claude/skills/super-swarm-spark $ npx degit DEVfancybear/harness-agents/.agents/skills/super-swarm .claude/skills/super-swarm $ npx degit DEVfancybear/harness-agents/.agents/skills/swarm-planner .claude/skills/swarm-planner $ npx degit DEVfancybear/harness-agents/.agents/skills/ui-ux-pro-max .claude/skills/ui-ux-pro-max $ npx degit DEVfancybear/harness-agents/.agents/skills/web-artifacts-builder .claude/skills/web-artifacts-builder $ npx degit DEVfancybear/harness-agents/.agents/skills/websearch .claude/skills/websearch
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 (20)
Similar rigs
ControlNet/oma-dotfile
—
Pragmatist 442 tok ·
shikharshikharshikhar/claude-dotfiles
—
Skill Collector 3.2k tok ·
chaohong-ai/ai-auto-work
Automatically completes the full workflow from requirement research → research review → planning → plan review → development → development review using → test AI large language models. Capable of autonomously handling medium to large-scale
Pragmatist 6.0k tok ·
heshengtao/super-agent-party
⭐ All-in-one AI companion! Super Agent Party = Self hosted neuro sama + openclaw! ⭐ 全能AI伴侣！超级智能体派对 = 自托管neuro sama + openclaw!
Minimalist 1.6k tok ·