FlintSH/tinderbox
My agent toolkit, designed to give agents autonomy and hold themselves to a high standard.
stack: JavaScript
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 FlintSH/tinderbox/skills ./rig-tinderbox/skills 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 <redacted> .claude/skills/delivery $ npx degit FlintSH/tinderbox/plugins/tinderbox/skills/pr-follow-through .claude/skills/pr-follow-through $ npx degit <redacted>-qa .claude/skills/render-qa $ npx degit <redacted>-qa .claude/skills/visual-qa $ npx degit FlintSH/tinderbox/skills/fl1nt-design .claude/skills/fl1nt-design $ npx degit FlintSH/tinderbox/skills/ui-content .claude/skills/ui-content $ npx degit FlintSH/tinderbox/skills/visual-polish-loop .claude/skills/visual-polish-loop
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
hieuphung97/dely
Multi-harness control protocol that turns requests into approved design contracts, orchestrating isolated worker sessions for sequential implementation and independent code reviews under Orca supervision for Claude Code, Codex, Cursor, Anti
Minimalist 1.9k tok · · Q0
User-Piotr/agent-config
Config for my AI coding agents
Minimalist 162 tok · · Q0
bohous04/devbox
Self-hosted remote dev environment for AI coding agents — Claude Code, Codex and Grok in disposable containers on your own VPS, driven from a Mac, a web dashboard or your iPhone
Minimalist 336 tok · · Q0
jaysueno/claude-operator-kit
Two Claude Code hooks, six rules and four skills for running several AI coding sessions on one machine and one working tree. Each rule opens with the date of the mistake behind it.
Minimalist 525 tok · · Q3