vondraysanford/The10XEngineerToolkit
Skills, prompts, templates, and workflows for engineers who build with AI coding agents (Claude Code, Copilot, Cursor). Turns the practices of great engineers into a portable, stack-agnostic system.
ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
Copy this rig
# review before running: this installs third-party code $ npx degit vondraysanford/The10XEngineerToolkit/agents ./rig-the10xengineertoolkit/agents $ npx degit vondraysanford/The10XEngineerToolkit/skills ./rig-the10xengineertoolkit/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>-md .claude/skills/agents-md $ npx degit <redacted>-ai-writing .claude/skills/avoid-ai-writing $ npx degit <redacted>-hygiene .claude/skills/context-hygiene $ npx degit <redacted>-verification .claude/skills/dependency-verification $ npx degit <redacted>-test-diagnosis .claude/skills/flaky-test-diagnosis $ npx degit <redacted>-migration .claude/skills/incremental-migration $ npx degit <redacted>-first .claude/skills/plan-first $ npx degit <redacted>-request-creator .claude/skills/pull-request-creator $ npx degit <redacted>-scrub .claude/skills/spec-scrub $ npx degit <redacted>-mapping .claude/skills/system-mapping $ npx degit <redacted>-check .claude/skills/threat-check $ npx degit <redacted>-loop .claude/skills/verification-loop $ npx degit <redacted>-ticket .claude/skills/write-ticket
$ curl -fsSL --create-dirs -o .claude/agents/devils-advocate.md https://raw.githubusercontent.<redacted>-advocate.md 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 (13)
agents-mdavoid-ai-writingcontext-hygienedependency-verificationflaky-test-diagnosisincremental-migrationplan-firstpull-request-creatorspec-scrubsystem-mappingthreat-checkverification-loopwrite-ticket
Subagents (1)
| devils-advocate model: opus | A read-only challenger for plans, designs, estimates, and "done" claims. Delegate to this agent before committing to an approach, before a risky merge, or when a conclusion feels too comfortable. It a |
Similar rigs
vitaliikapliuk/modelharness
Make every model cheaper or better. Zero-config behavioral harness for Claude Code, with a reproducible 408-run benchmark
Pragmatist 236 tok ·
rlaope/quoted-andrej-karpathy
An harness and behavioral guidelines to enforce reliable execution in AI coding agents.
Minimalist 1.5k tok ·
Lullow/make-skills
A small, cherry-picked set of Claude Code skills for a spec to ticket to done to handover workflow.
Minimalist 343 tok ·
grvermeulen/agent-workflow-template
Personal template for AI-assisted development: AGENTS.md preferences, CodeRabbit config, Cursor rules+skills+hooks, Claude Code loop-on-ci command, husky hooks, and agent-flow GitHub workflows.
Pragmatist 1.7k tok ·