agentrigs
+ submit rig
~ / rigs / SchotjeChrisman / agentic-workflow

SchotjeChrisman/agentic-workflow

A self-improving Claude Code setup

↗ GitHub ★ 0 MIT updated 1d ago personal setup Claude Code
share on X
ARCHETYPE
Orchestrator
A bench of specialised subagents. The main agent mostly delegates.
CONTEXT TAX · EVERY TURN
~2.8k tokens
Moderate · median rig: 2.3k · breakdown
GUARDRAILS
3/5
Blocks destructive commands · Pre-tool screening hook · No YOLO mode · details

Copy this rig

# review before running: this installs third-party code
$ npx degit SchotjeChrisman/agentic-workflow/.claude ./rig-agentic-workflow  # 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.

$ curl -fsSL --create-dirs -o .claude/agents/auditor.md https://raw.githubusercontent.com/SchotjeChrisman/agentic-workflow/main/agents/auditor.md
$ curl -fsSL --create-dirs -o .claude/agents/critic.md https://raw.githubusercontent.com/SchotjeChrisman/agentic-workflow/main/agents/critic.md
$ curl -fsSL --create-dirs -o .claude/agents/debugger.md https://raw.githubusercontent.com/SchotjeChrisman/agentic-workflow/main/agents/debugger.md
$ curl -fsSL --create-dirs -o .claude/agents/scraper.md https://raw.githubusercontent.com/SchotjeChrisman/agentic-workflow/main/agents/scraper.md
$ curl -fsSL --create-dirs -o .claude/agents/verifier.md https://raw.githubusercontent.com/SchotjeChrisman/agentic-workflow/main/agents/verifier.md

Merge into .claude/settings.json (project) or ~/.claude/settings.json (user). Hook commands reference scripts in the source repo — copy those too.

{
  "permissions": {
    "deny": [
      "Bash(docker * prune *)",
      "Bash(docker * prune)",
      "Bash(podman * prune *)",
      "Bash(podman * prune)",
      "Bash(podman system reset *)"
    ]
  },
  "hooks": {
    "PreToolUse": [
      {
        "matcher": "Bash",
        "hooks": [
          {
            "type": "command",
            "command": "bash \"${CLAUDE_CONFIG_DIR:-$HOME/.claude}/hooks/rtk.sh\""
          }
        ]
      }
    ]
  }
}

Subagents (5)

auditor
model: sonnet
Checks a document, list or dataset against reality item by item - docs against code, claims against outputs, records against rules. Pass what to audit and the rules to check (or "every checkable claim
criticStress-tests a plan or design before it gets built. Pass the goal, the user's decisions and the full draft. Read-only; returns ranked findings: false claims, failure modes, over- and under-built parts
debuggerFinds and fixes the root cause of a bug, error, failing test or wrong output, in any stack. Pass the symptom as the user reported it, where it shows, and any repro you know. Returns the cause with evi
scraper
model: haiku
Web and docs research on a cheap model, so the pages never fill the caller's context. Pass the question, what the answer is for, and any versions or sources you already know. Read-only; returns each f
verifier
model: sonnet
Cold, independent check of a finished non-trivial change, before saying done, fixed or works. Pass the user's original request verbatim and the diff or changed paths (untracked files included), and no

Hooks (6)

eventmatcherruns
SessionStart*bash "${CLAUDE_CONFIG_DIR:-$HOME/.claude}/hooks/peers.sh"
SessionStart*bash "${CLAUDE_CONFIG_DIR:-$HOME/.claude}/hooks/learn.sh"
PostToolUseWrite|Editbash "${CLAUDE_CONFIG_DIR:-$HOME/.claude}/hooks/learn.sh"
Stop*bash "${CLAUDE_CONFIG_DIR:-$HOME/.claude}/hooks/learn.sh"
SessionEnd*bash "${CLAUDE_CONFIG_DIR:-$HOME/.claude}/hooks/learn.sh"
PreToolUseBashbash "${CLAUDE_CONFIG_DIR:-$HOME/.claude}/hooks/rtk.sh"

Plugins (4)

ponytail@ponytailcontext7@claude-plugins-officialclaude-security@claude-plugins-officialplugin-dev@claude-plugins-official

Permissions

deny (5)
Bash(docker * prune *)
Bash(docker * prune)
Bash(podman * prune *)
Bash(podman * prune)
Bash(podman system reset *)
ask (0)
—
allow (0)
—

Similar rigs

itshig/AGENTS-template
Drop-in AGENTS.md template for Claude Code, Cursor, Codex, and other AI agents — with .agents/ for rules, personas, and workflows.
★ 1 collection Claude CodeCodexGemini CLI 5 agents 1mo ago
Orchestrator 3.0k tok ·
Remus3/Legion-Wallpaper
Self-auditing AI image restoration pipeline (super-resolution, LaMa inpainting, face repair, metric-plus-vision gate ladder), built by a multi-agent Claude Code system with independent verifiers, git-hook gates and headless background lanes
★ 1 project Claude CodeCodexGemini CLI 1 agents 16 hooks today
Automator 5.5k tok ·
IvanKuzyshyn/dotfiles
Dotfiles optimized for speed, coffee, and questionable life choices. 😜
★ 5 setup Claude CodeCodex 2 agents 26d ago
Pragmatist 3.0k tok ·
leavemagic-cyber/earned-confidence
A behavior contract for AI coding agents — every rule added after a real failure. Ships with a verifier agent that cannot edit what it judges.
★ 3 project Claude Code 2 agents 2mo ago
Pragmatist 3.6k tok ·
copied ✓