~ / rigs / yassine-krichen / claude-code-agentic-setup

yassine-krichen/claude-code-agentic-setup

Personal Claude Code setup — orchestrator/subagent delegation policy, custom agents, and a colored PowerShell statusline (git branch, model+effort, tokens, cost, rate limits).

↗ GitHub ★ 2 NOASSERTION updated 28d ago personal setup Claude Code
stack: PowerShell
share on X
ARCHETYPE
Orchestrator
A bench of specialised subagents. The main agent mostly delegates.
CONTEXT TAX · EVERY TURN
~2.3k tokens
Moderate · median rig: 2.3k · breakdown
GUARDRAILS
1/5
No YOLO mode · details
Quality 23/100 Guardrails v2

Copy this rig

# review before running: this installs third-party code
$ npx degit yassine-krichen/claude-code-agentic-setup/agents ./rig-claude-code-agentic-setup/agents
$ npx degit yassine-krichen/claude-code-agentic-setup/commands ./rig-claude-code-agentic-setup/commands
$ npx degit yassine-krichen/claude-code-agentic-setup/skills ./rig-claude-code-agentic-setup/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 yassine-krichen/claude-code-agentic-setup/skills/jot-note .claude/skills/jot-note
$ npx degit yassine-krichen/claude-code-agentic-setup/skills/ux-design .claude/skills/ux-design
$ npx degit yassine-krichen/claude-code-agentic-setup/skills/vault-ingest .claude/skills/vault-ingest
$ curl -fsSL --create-dirs -o .claude/agents/Explore.md https://raw.githubusercontent.com/yassine-krichen/claude-code-agentic-setup/master/agents/Explore.md
$ curl -fsSL --create-dirs -o .claude/agents/code-reviewer.md https://raw.githubusercontent.com/yassine-krichen/claude-code-agentic-setup/master/agents/code-reviewer.md
$ curl -fsSL --create-dirs -o .claude/agents/committer.md https://raw.githubusercontent.com/yassine-krichen/claude-code-agentic-setup/master/agents/committer.md
$ curl -fsSL --create-dirs -o .claude/agents/debugger.md https://raw.githubusercontent.com/yassine-krichen/claude-code-agentic-setup/master/agents/debugger.md
$ curl -fsSL --create-dirs -o .claude/agents/docs-writer.md https://raw.githubusercontent.com/yassine-krichen/claude-code-agentic-setup/master/agents/docs-writer.md
$ curl -fsSL --create-dirs -o .claude/agents/implementer.md https://raw.githubusercontent.com/yassine-krichen/claude-code-agentic-setup/master/agents/implementer.md
$ curl -fsSL --create-dirs -o .claude/agents/planner.md https://raw.githubusercontent.com/yassine-krichen/claude-code-agentic-setup/master/agents/planner.md
$ curl -fsSL --create-dirs -o .claude/agents/solo-pipeline.md https://raw.githubusercontent.com/yassine-krichen/claude-code-agentic-setup/master/agents/solo-pipeline.md
$ curl -fsSL --create-dirs -o .claude/agents/test-runner.md https://raw.githubusercontent.com/yassine-krichen/claude-code-agentic-setup/master/agents/test-runner.md
$ curl -fsSL --create-dirs -o .claude/agents/test-writer.md https://raw.githubusercontent.com/yassine-krichen/claude-code-agentic-setup/master/agents/test-writer.md

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 (3)

Subagents (10)

Explore
model: sonnet
Searches and reads codebase without changes. Use for "how does X work", "where Y defined", "find usages of Z".
code-reviewer
model: opus
Reviews diff/changed files for correctness, security, and dependency vulnerabilities before commit. Use after implementation and passing tests, before committing. Also the pre-release security-audit p
committer
model: haiku
Stages changes, writes conventional commit message. Use once code-reviewer approves and tests pass — never before.
debugger
model: sonnet
Investigates and fixes a specific failing test, error, or bug report. Use when test-runner reports failure, or given a stack trace/bug description directly.
docs-writer
model: haiku
Updates README, API docs, inline documentation to reflect recent code changes. Use after a feature is implemented and committed, or on request.
implementer
model: sonnet
Writes/edits code to implement a plan or well-specified change. Use once a plan exists, or for small clearly-scoped changes needing no separate planning pass.
planner
model: opus
Investigates feature/bug request, produces implementation plan before code written. Use at start of any non-trivial feature, refactor, or unclear bug.
solo-pipeline
model: sonnet
One-window compact pipeline — plans, implements, self-reviews (correctness + security), and runs/writes tests, all in a single pass. Use for a real, scoped code change where full multi-agent isolation
test-runner
model: haiku
Runs test suites, reports results. Use after any code change to verify nothing broke, or on request.
test-writer
model: sonnet
Writes tests for code that implementer just changed, when none exist yet or coverage is missing. Use after implementer completes, before test-runner, whenever the changed code has no corresponding tes

Slash commands (1)

/handoff

Plugins (4)

caveman@cavemanfrontend-design@claude-plugins-officialplaywright@claude-plugins-officialhumanizer@humanizer

Similar rigs

copied ✓