slowdini/slow-powers
Eval-backed agent skills for Claude Code, Codex & OpenCode — for developers who hate skills.
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 slowdini/slow-powers/.claude ./rig-slow-powers # 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 slowdini/slow-powers/skills/auditing-slow-powers-usage .claude/skills/auditing-slow-powers-usage $ npx degit slowdini/slow-powers/skills/evaluating-skills .claude/skills/evaluating-skills $ npx degit slowdini/slow-powers/skills/hardening-plans .claude/skills/hardening-plans $ npx degit slowdini/slow-powers/skills/investigating-bugs .claude/skills/investigating-bugs $ npx degit slowdini/slow-powers/skills/verifying-development-work .claude/skills/verifying-development-work $ npx degit slowdini/slow-powers/skills/working-in-isolation .claude/skills/working-in-isolation $ npx degit slowdini/slow-powers/skills/working-with-tdd .claude/skills/working-with-tdd $ npx degit slowdini/slow-powers/skills/writing-skills .claude/skills/writing-skills $ npx degit slowdini/slow-powers/skills/writing-technical-docs .claude/skills/writing-technical-docs
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 (9)
auditing-slow-powers-usageevaluating-skillshardening-plansinvestigating-bugsverifying-development-workworking-in-isolationworking-with-tddwriting-skillswriting-technical-docs
Permissions
deny (0)
—
ask (0)
—
allow (19)
Bash(bun install)
Bash(bun install *)
Bash(bun add *)
Bash(bun pm *)
Bash(bun test *)
Bash(bun run *)
Bash(bun --version)
Bash(bunx biome *)
Bash(git add *)
Bash(git commit *)
Bash(git checkout *)
Bash(git mv *)
Bash(git config *)
Bash(git check-ignore *)
Bash(gh api *)
Bash(gh auth *)
Bash(gh label *)
mcp__plugin_context7_context7__resolve-library-id
mcp__plugin_context7_context7__query-docs
Similar rigs
omril321/claude-code-setup
My collection of skills, commands and more that I use daily for Claude Code
Pragmatist 581 tok ·
jcarlosrodicio/norma
One task loop, one verification gate, one skill library for every coding agent - enforced by git. POSIX sh, no dependencies.
Skill Collector 2.3k tok ·
TechDufus/oh-my-claude
Add ultrawork to any prompt for maximum parallel execution
Skill Collector 3.9k tok ·
RichardBray/dotfiles
My personal configuration files and settings
Skill Collector 671 tok ·