agentrigs
+ submit rig
~ / rigs / pragmatic-engineer / playbook

pragmatic-engineer/playbook

Personal Claude Code setup: launcher, session hooks, custom system prompt, skills, slash commands, and a statusline. One-line curl install.

↗ GitHub ★ 0 mit updated 3d ago personal setup Claude Code Claude plugin
share on X
ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
CONTEXT TAX · EVERY TURN
~607 tokens
Featherweight · median rig: 2.3k · breakdown
GUARDRAILS
0/5
No committed guardrails · details

Copy this rig

# review before running: this installs third-party code
$ npx degit pragmatic-engineer/playbook/skills ./rig-playbook/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 pragmatic-engineer/playbook/skills/atlassian-cli .claude/skills/atlassian-cli
$ npx degit pragmatic-engineer/playbook/skills/delegating-subagents .claude/skills/delegating-subagents
$ npx degit pragmatic-engineer/playbook/skills/engineering-standards-javascript .claude/skills/engineering-standards-javascript
$ npx degit pragmatic-engineer/playbook/skills/engineering-standards .claude/skills/engineering-standards
$ npx degit pragmatic-engineer/playbook/skills/finish-pull-request .claude/skills/finish-pull-request
$ npx degit pragmatic-engineer/playbook/skills/grounding-research .claude/skills/grounding-research
$ npx degit pragmatic-engineer/playbook/skills/grounding-review .claude/skills/grounding-review
$ npx degit pragmatic-engineer/playbook/skills/playbook-usage .claude/skills/playbook-usage
$ npx degit pragmatic-engineer/playbook/skills/session-handoff .claude/skills/session-handoff
$ npx degit pragmatic-engineer/playbook/skills/systematic-debugging .claude/skills/systematic-debugging
$ npx degit pragmatic-engineer/playbook/skills/writing-style .claude/skills/writing-style

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 (11)

atlassian-clidelegating-subagentsengineering-standards-javascriptengineering-standardsfinish-pull-requestgrounding-researchgrounding-reviewplaybook-usagesession-handoffsystematic-debuggingwriting-style

Similar rigs

antgrid-ai/antgrid
Agentic Development Environment and E2E-encrypted control plane for coding agents
★ 2 project Claude CodeCodex 1 mcp 3 skills 1 hooks today
Pragmatist 28.5k tok ·
kraulerson/solo-orchestrator
AI-assisted software development methodology for solo builders
★ 30 project Claude Code 4 skills 1 agents 5 hooks 9d ago
Automator 10.1k tok ·
benyoskovitz/claude-code-workflow
A practical, opinionated Claude Code workflow: a task-rubric loop that makes AI-written code trustworthy, a lean CLAUDE.md pattern, and a lab for versioning your own setup
★ 8 setup Claude Code 5 skills 15d ago
Pragmatist 127 tok ·
will-pagane/claude-superdev-harness
Minha config pessoal do Claude Code — CLAUDE.md global, statusline custom, stack de plugins/skills
★ 4 setup Claude Code 5 skills 17d ago
Pragmatist 2.0k tok ·
copied ✓