jakec-dev/jakec-dev-marketplace
Claude Code plugins. agent-setup keeps a repository's Claude Code setup current as Claude Code changes.
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 jakec-dev/jakec-dev-marketplace/.claude ./rig-jakec-dev-marketplace # 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 jakec-dev/jakec-dev-marketplace/.claude/skills/knowledge .claude/skills/knowledge $ npx degit jakec-dev/jakec-dev-marketplace/plugins/agent-setup/evals/content/process-skill-unshown-steps/plugin/skills/add-feature .claude/skills/add-feature $ npx degit jakec-dev/jakec-dev-marketplace/plugins/agent-setup/skills/find-setup-content .claude/skills/find-setup-content $ npx degit jakec-dev/jakec-dev-marketplace/plugins/agent-setup/skills/write-hook .claude/skills/write-hook $ npx degit jakec-dev/jakec-dev-marketplace/plugins/agent-setup/skills/write-rule .claude/skills/write-rule $ npx degit jakec-dev/jakec-dev-marketplace/plugins/agent-setup/skills/write-skill .claude/skills/write-skill $ npx degit jakec-dev/jakec-dev-marketplace/plugins/agent-setup/skills/write-subagent .claude/skills/write-subagent
$ curl -fsSL --create-dirs -o .claude/agents/knowledge-reviewer.md https://raw.githubusercontent.com/jakec-dev/jakec-dev-marketplace/master/.claude/agents/knowledge-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/knowledge-writer.md https://raw.githubusercontent.com/jakec-dev/jakec-dev-marketplace/master/.claude/agents/knowledge-writer.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 (7)
Subagents (2)
| knowledge-reviewer model: sonnet | Checks an agent-setup knowledge file, or a type's excluded sections, against Claude Code's documentation and reports problems without fixing them. Use after knowledge is written or changed. |
| knowledge-writer model: sonnet | Writes one agent-setup knowledge file from the documentation sections it owns, and returns the ledger rows for them. Use when the knowledge skill hands over a topic. |
Similar rigs
The-Urcydo/Agents-Skills-Roles-Oriented
A portable library of agent skills with role charters, validated by standard-library Python tools and CI.
Minimalist 1.0k tok · · Q5
sergioazoc/oxlint-tailwindcss
Tailwind CSS v4 lint rules for oxlint that read your design system: unknown, conflicting and deprecated classes, theme colors and class order, with autofixes.
Pragmatist 21.7k tok · · Q18
Sekers/dev-home-toolkit
Skills, rules, and scripts that give Claude Code and Codex a private home base, shared across your PCs.
Pragmatist 4.5k tok · · Q5
tj-agents/nvim
Neovim learning companion for AI coding agents — teaching method, curriculum and progress tracker over Tommy's nvim config.
Pragmatist 1.3k tok · · Q17