polyant-ai/polyant-dev-kit
Skills and templates for building Polyant agents with a coding agent
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 polyant-ai/polyant-dev-kit/.claude ./rig-polyant-dev-kit # 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 polyant-ai/polyant-dev-kit/.agents/skills/agent-configuration .claude/skills/agent-configuration $ npx degit polyant-ai/polyant-dev-kit/.agents/skills/agent-prompt-design .claude/skills/agent-prompt-design $ npx degit polyant-ai/polyant-dev-kit/.agents/skills/agent-prompt-writing .claude/skills/agent-prompt-writing $ npx degit polyant-ai/polyant-dev-kit/.agents/skills/agent-skills .claude/skills/agent-skills $ npx degit polyant-ai/polyant-dev-kit/.agents/skills/cli-workflows .claude/skills/cli-workflows $ npx degit polyant-ai/polyant-dev-kit/.agents/skills/evaluating-agents .claude/skills/evaluating-agents $ npx degit polyant-ai/polyant-dev-kit/.agents/skills/plugin-authoring .claude/skills/plugin-authoring $ npx degit polyant-ai/polyant-dev-kit/.agents/skills/tool-design .claude/skills/tool-design
$ curl -fsSL --create-dirs -o .claude/agents/01-identity.md https://raw.githubusercontent.com/polyant-ai/polyant-dev-kit/main/agents/acme/prompts/01-identity.md $ curl -fsSL --create-dirs -o .claude/agents/04-safety.md https://raw.githubusercontent.com/polyant-ai/polyant-dev-kit/main/agents/acme/prompts/04-safety.md
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 (8)
agent-configurationagent-prompt-designagent-prompt-writingagent-skillscli-workflowsevaluating-agentsplugin-authoringtool-design
Subagents (2)
| 01-identity | — |
| 04-safety | — |
Similar rigs
yiftahb/agsync
Agsync is a repo-native control plane for managing skills, MCP servers, secrets, and agent configs across AI clients like Claude Code and Cursor.
Minimalist 1.2k tok · · Q0
fuleshu/Aworkit
Codex like desktop app with a complete toolset for long running agent tasks for hosted and local models. Visual harness workflow editor, MCP tools, full run inspection. Rust + Tauri.
Pragmatist 1.1k tok · · Q0
zjy-dev/skills
Curated atomic Agent Skills for environment bootstrap, Git worktree organization, academic writing, and frontend design
Pragmatist 370 tok · · Q0
Hyska-Software/ZylaraAi
Zylara is a desktop workspace for coding agents. Plan before it writes, approve what it runs, and review every diff — without leaving your computer.
Skill Collector 11.2k tok · · Q0