john-wilmes/claude-agentic-coding-playbook
Evidence-based practices for LLM-assisted development. Install scripts, Claude Code configuration, and a research-backed best practices guide with 34 verified citations.
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
Copy this rig
$ git clone --depth 1 https://github.com/john-wilmes/claude-agentic-coding-playbook 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 john-wilmes/claude-agentic-coding-playbook/profiles/combined/skills/checkpoint .claude/skills/checkpoint $ npx degit john-wilmes/claude-agentic-coding-playbook/profiles/combined/skills/create-project .claude/skills/create-project $ npx degit john-wilmes/claude-agentic-coding-playbook/profiles/combined/skills/investigate .claude/skills/investigate $ npx degit john-wilmes/claude-agentic-coding-playbook/profiles/combined/skills/learn .claude/skills/learn $ npx degit john-wilmes/claude-agentic-coding-playbook/profiles/combined/skills/playbook .claude/skills/playbook $ npx degit john-wilmes/claude-agentic-coding-playbook/profiles/combined/skills/promote .claude/skills/promote
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 (6)
Similar rigs
mutlumehmet/claude-plugins
Claude Code plugins I use every day: skills and mods, cleaned up so they work on anyone's machine.
Minimalist 2.3k tok ·
SatymSingh01/claude-code-pack
Drop-in config pack for Claude Code: CLAUDE.md best practices, safety hooks, auto-checkpoint, session logging, and slash commands. One install script.
Minimalist 344 tok ·
tigerless-labs/autoharness
Autoharness — a self-learning skill layer for Claude Code — distills skills from your real sessions, updates them as you work, and prunes the ones that stop getting used. No daemon, no benchmark.
Pragmatist 2.6k tok ·
nagisanzenin/engram
Evidence-based learning engine — first-principles curricula, free-recall verification with receipts, FSRS-scheduled memory, and explorable artifacts. Learn anything; keep it.
Minimalist 185 tok ·