theonly1me/shadowclone
Your engineering taste, in every coding agent. Shadowclone learns your rules and delivers them as skills to Claude Code, Codex, Cursor, Pi, and Antigravity, and as a GitHub cloud bot.
field: unknown workflow: PR / code reviewGit & commitsTesting & TDDDebuggingFrontend & design runs claude in CI
ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
CONTEXT TAX · EVERY TURN
up to ~8.0k tokens
Claude Code loads MCP tools on demand, so the real cost is usually lower.
Heavy · median rig: 2.3k · breakdown
Copy this rig
# review before running: this installs third-party code
$ npx degit theonly1me/shadowclone/.claude ./rig-shadowclone # 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 theonly1me/shadowclone/.agents/skills/choose-by-consequence .claude/skills/choose-by-consequence $ npx degit theonly1me/shadowclone/.agents/skills/design-deep-modules .claude/skills/design-deep-modules $ npx degit theonly1me/shadowclone/.agents/skills/diagnose-before-editing .claude/skills/diagnose-before-editing $ npx degit theonly1me/shadowclone/.agents/skills/plan-with-review-page .claude/skills/plan-with-review-page $ npx degit theonly1me/shadowclone/.agents/skills/research-primary-sources .claude/skills/research-primary-sources $ npx degit theonly1me/shadowclone/.agents/skills/resolve-conflicts-by-intent .claude/skills/resolve-conflicts-by-intent $ npx degit theonly1me/shadowclone/.agents/skills/scope-confirmed-changes .claude/skills/scope-confirmed-changes $ npx degit theonly1me/shadowclone/.agents/skills/shadowclone-build-preferences .claude/skills/shadowclone-build-preferences $ npx degit theonly1me/shadowclone/.agents/skills/shadowclone-review .claude/skills/shadowclone-review $ npx degit theonly1me/shadowclone/.agents/skills/shadowclone-work .claude/skills/shadowclone-work $ npx degit theonly1me/shadowclone/.agents/skills/tests-that-catch-bugs .claude/skills/tests-that-catch-bugs $ npx degit theonly1me/shadowclone/.agents/skills/typescript-type-safety .claude/skills/typescript-type-safety $ npx degit theonly1me/shadowclone/.agents/skills/verify-and-review .claude/skills/verify-and-review $ npx degit theonly1me/shadowclone/.agents/skills/write-plain-english .claude/skills/write-plain-english $ npx degit theonly1me/shadowclone/.claude/skills/data-handling .claude/skills/data-handling $ npx degit <redacted>-clones .claude/skills/setup-clones $ npx degit <redacted>-shadowclone .claude/skills/setup-shadowclone $ npx degit theonly1me/shadowclone/skills/guided-pr-review .claude/skills/guided-pr-review $ npx degit theonly1me/shadowclone/skills/verify-review-findings .claude/skills/verify-review-findings
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 *)"
]
}
} MCP servers (1)
| server | source | est. tokens |
|---|---|---|
| shadowclone | local / custom | 2.5k |
Skills (19)
choose-by-consequencedesign-deep-modulesdiagnose-before-editingplan-with-review-pageresearch-primary-sourcesresolve-conflicts-by-intentscope-confirmed-changesshadowclone-build-preferencesshadowclone-reviewshadowclone-worktests-that-catch-bugstypescript-type-safetyverify-and-reviewwrite-plain-englishdata-handlingsetup-clonessetup-shadowcloneguided-pr-reviewverify-review-findings
Similar rigs
theonly1me/vigilante
See what a pull request lets your code, CI, and AI agents do before you merge it. Vigilante reports new powers, such as exec, network, CI tokens, MCP servers, and install scripts, through dependencies in Go, Rust, JavaScript, TypeScript, Py
Skill Collector 3.2k tok · · Q3
aalokshah-business/AskAi
Make Claude Code, Codex, Antigravity and Cursor subscriptions last longer: one command installs evidence-based token-saving settings, plugins and project files for all four.
Pragmatist 2.5k tok · · Q3
pr-pm/prpm
The universal registry for AI coding tools
Orchestrator 36.8k tok · · Q18
kookr-ai/kookr
A smart attention router for developers running multiple AI coding agents.
Skill Collector 11.1k tok · · Q25