agentrigs
+ submit rig
~ / rigs / serhii-baksheiev / create-agent-rig

serhii-baksheiev/create-agent-rig

Repo-native workflow layer for Codex and Claude Code: coordination, safety gates, TDD evidence, reviews, continuation, and parallel work.

↗ GitHub ★ 0 MIT updated today project Claude CodeCodex
share on X
ARCHETYPE
Orchestrator
A bench of specialised subagents. The main agent mostly delegates.
CONTEXT TAX · EVERY TURN
~7.1k tokens
Heavy · 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 serhii-baksheiev/create-agent-rig/.claude ./rig-create-agent-rig  # 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.

$ npx degit serhii-baksheiev/create-agent-rig/.agents/skills/check-premises .claude/skills/check-premises
$ npx degit serhii-baksheiev/create-agent-rig/.agents/skills/diagnose .claude/skills/diagnose
$ npx degit serhii-baksheiev/create-agent-rig/.agents/skills/loop .claude/skills/loop
$ npx degit serhii-baksheiev/create-agent-rig/.agents/skills/new-invariant .claude/skills/new-invariant
$ npx degit serhii-baksheiev/create-agent-rig/.agents/skills/plan-slices .claude/skills/plan-slices
$ npx degit serhii-baksheiev/create-agent-rig/.agents/skills/pr-ship .claude/skills/pr-ship
$ npx degit serhii-baksheiev/create-agent-rig/.agents/skills/release-propose .claude/skills/release-propose
$ npx degit serhii-baksheiev/create-agent-rig/.agents/skills/skill-authoring .claude/skills/skill-authoring
$ npx degit serhii-baksheiev/create-agent-rig/.agents/skills/worktree-task .claude/skills/worktree-task
$ curl -fsSL --create-dirs -o .claude/agents/code-reviewer.md https://raw.githubusercontent.com/serhii-baksheiev/create-agent-rig/master/.claude/agents/code-reviewer.md
$ curl -fsSL --create-dirs -o .claude/agents/failure-diagnostician.md https://raw.githubusercontent.com/serhii-baksheiev/create-agent-rig/master/.claude/agents/failure-diagnostician.md
$ curl -fsSL --create-dirs -o .claude/agents/implementation-agent.md https://raw.githubusercontent.com/serhii-baksheiev/create-agent-rig/master/.claude/agents/implementation-agent.md
$ curl -fsSL --create-dirs -o .claude/agents/prose-reviewer.md https://raw.githubusercontent.com/serhii-baksheiev/create-agent-rig/master/.claude/agents/prose-reviewer.md
$ curl -fsSL --create-dirs -o .claude/agents/security-scanner.md https://raw.githubusercontent.com/serhii-baksheiev/create-agent-rig/master/.claude/agents/security-scanner.md
$ curl -fsSL --create-dirs -o .claude/agents/test-writer.md https://raw.githubusercontent.com/serhii-baksheiev/create-agent-rig/master/.claude/agents/test-writer.md
$ curl -fsSL --create-dirs -o .claude/agents/code-reviewer.md https://raw.githubusercontent.com/serhii-baksheiev/create-agent-rig/master/templates/agent-os/universal/.claude/agents/code-reviewer.md
$ curl -fsSL --create-dirs -o .claude/agents/failure-diagnostician.md https://raw.githubusercontent.com/serhii-baksheiev/create-agent-rig/master/templates/agent-os/universal/.claude/agents/failure-diagnostician.md
$ curl -fsSL --create-dirs -o .claude/agents/implementation-agent.md https://raw.githubusercontent.com/serhii-baksheiev/create-agent-rig/master/templates/agent-os/universal/.claude/agents/implementation-agent.md
$ curl -fsSL --create-dirs -o .claude/agents/prose-reviewer.md https://raw.githubusercontent.com/serhii-baksheiev/create-agent-rig/master/templates/agent-os/universal/.claude/agents/prose-reviewer.md
$ curl -fsSL --create-dirs -o .claude/agents/security-scanner.md https://raw.githubusercontent.com/serhii-baksheiev/create-agent-rig/master/templates/agent-os/universal/.claude/agents/security-scanner.md
$ curl -fsSL --create-dirs -o .claude/agents/test-writer.md https://raw.githubusercontent.com/serhii-baksheiev/create-agent-rig/master/templates/agent-os/universal/.claude/agents/test-writer.md

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

{
  "hooks": {
    "PreToolUse": [
      {
        "matcher": "Write|Edit|MultiEdit|NotebookEdit|apply_patch",
        "hooks": [
          {
            "type": "command",
            "command": "node \"$CLAUDE_PROJECT_DIR/.claude/hooks/guard-secret-file.mjs\""
          },
          {
            "type": "command",
            "command": "node \"$CLAUDE_PROJECT_DIR/.claude/hooks/guard-rulebook.mjs\""
          },
          {
            "type": "command",
            "command": "node \"$CLAUDE_PROJECT_DIR/.claude/hooks/probity-gate.mjs\" --harness=claude"
          },
          {
            "type": "command",
            "command": "node \"$CLAUDE_PROJECT_DIR/.claude/hooks/guard-secret-file.mjs\""
          },
          {
            "type": "command",
            "command": "node \"$CLAUDE_PROJECT_DIR/.claude/hooks/guard-rulebook.mjs\""
          },
          {
            "type": "command",
            "command": "node \"$CLAUDE_PROJECT_DIR/.claude/hooks/probity-gate.mjs\" --harness=claude"
          }
        ]
      },
      {
        "matcher": "Bash|PowerShell",
        "hooks": [
          {
            "type": "command",
            "command": "node \"$CLAUDE_PROJECT_DIR/.claude/hooks/block-no-verify.mjs\""
          },
          {
            "type": "command",
            "command": "node \"$CLAUDE_PROJECT_DIR/.claude/hooks/guard-bash.mjs\""
          },
          {
            "type": "command",
            "command": "node \"$CLAUDE_PROJECT_DIR/.claude/hooks/block-no-verify.mjs\""
          },
          {
            "type": "command",
            "command": "node \"$CLAUDE_PROJECT_DIR/.claude/hooks/guard-bash.mjs\""
          }
        ]
      },
      {
        "matcher": "Agent",
        "hooks": [
          {
            "type": "command",
            "command": "node \"$CLAUDE_PROJECT_DIR/.claude/hooks/guard-subagent-model.mjs\""
          },
          {
            "type": "command",
            "command": "node \"$CLAUDE_PROJECT_DIR/.claude/hooks/guard-subagent-model.mjs\""
          }
        ]
      }
    ]
  }
}

Skills (9)

check-premisesdiagnoseloopnew-invariantplan-slicespr-shiprelease-proposeskill-authoringworktree-task

Subagents (12)

code-reviewer
model: claude-opus-5-5
Reviews a completed change against the checklist before a PR is opened or merged. Use after any non-trivial implementation work, and always before opening a PR that reaches the `model` lane — everythi
failure-diagnostician
model: claude-opus-5-5
Use when a check is red or a run crashed and the cause is not obvious, or to reproduce a claimed defect/historical finding on the current default branch before work is planned on it.
implementation-agent
model: claude-sonnet-5
Writes the minimum production code that makes an existing failing test pass — the Green step of TDD, and the Refactor that follows it. Use for ordinary implementation work once test-writer has produce
prose-reviewer
model: claude-sonnet-5
Reviews the documents that instruct agents — rule files, skills, agent specs, AGENTS.md, CLAUDE.md, the README — for claims the code does not support, dead references, and rules that contradict each o
security-scanner
model: claude-opus-5-5
Scans a change for security issues. MUST be used when a change touches authentication, authorization, secrets or configuration, input parsing, file handling, or any new outbound call. Findings gate th
test-writer
model: claude-sonnet-5
Writes the failing test BEFORE any implementation exists. Use at the start of every feature, bug fix, or behavior change — the Red step of TDD. Also use to reproduce a reported bug as a test.
code-reviewer
model: claude-opus-5-5
Reviews a completed change against the checklist before a PR is opened or merged. Use after any non-trivial implementation work, and always before opening a PR that reaches the `model` lane — everythi
failure-diagnostician
model: claude-opus-5-5
Use when a check is red or a run crashed and the cause is not obvious, or to reproduce a claimed defect/historical finding on the current default branch before work is planned on it.
implementation-agent
model: claude-sonnet-5
Writes the minimum production code that makes an existing failing test pass — the Green step of TDD, and the Refactor that follows it. Use for ordinary implementation work once test-writer has produce
prose-reviewer
model: claude-sonnet-5
Reviews the documents that instruct agents — rule files, skills, agent specs, AGENTS.md, CLAUDE.md, the README — for claims the code does not support, dead references, and rules that contradict each o
security-scanner
model: claude-opus-5-5
Scans a change for security issues. MUST be used when a change touches authentication, authorization, secrets or configuration, input parsing, file handling, or any new outbound call. Findings gate th
test-writer
model: claude-sonnet-5
Writes the failing test BEFORE any implementation exists. Use at the start of every feature, bug fix, or behavior change — the Red step of TDD. Also use to reproduce a reported bug as a test.

Hooks (22)

eventmatcherruns
PreToolUseWrite|Edit|MultiEdit|NotebookEdit|apply_patchnode "$CLAUDE_PROJECT_DIR/.claude/hooks/guard-secret-file.mjs"
PreToolUseWrite|Edit|MultiEdit|NotebookEdit|apply_patchnode "$CLAUDE_PROJECT_DIR/.claude/hooks/guard-rulebook.mjs"
PreToolUseWrite|Edit|MultiEdit|NotebookEdit|apply_patchnode "$CLAUDE_PROJECT_DIR/.claude/hooks/probity-gate.mjs" --harness=claude
PreToolUseBash|PowerShellnode "$CLAUDE_PROJECT_DIR/.claude/hooks/block-no-verify.mjs"
PreToolUseBash|PowerShellnode "$CLAUDE_PROJECT_DIR/.claude/hooks/guard-bash.mjs"
PreToolUseAgentnode "$CLAUDE_PROJECT_DIR/.claude/hooks/guard-subagent-model.mjs"
Stop*node "$CLAUDE_PROJECT_DIR/.claude/hooks/gate-stop-dod.mjs"
SessionStart*node "$CLAUDE_PROJECT_DIR/.claude/hooks/inject-rules.mjs"
SessionStart*node "$CLAUDE_PROJECT_DIR/.claude/hooks/warn-subagent-routing.mjs"
SubagentStart*node "$CLAUDE_PROJECT_DIR/.claude/hooks/record-dispatch.mjs" --harness=claude
SubagentStop*node "$CLAUDE_PROJECT_DIR/.claude/hooks/record-dispatch.mjs" --harness=claude
PreToolUseWrite|Edit|MultiEdit|NotebookEdit|apply_patchnode "$CLAUDE_PROJECT_DIR/.claude/hooks/guard-secret-file.mjs"
PreToolUseWrite|Edit|MultiEdit|NotebookEdit|apply_patchnode "$CLAUDE_PROJECT_DIR/.claude/hooks/guard-rulebook.mjs"
PreToolUseWrite|Edit|MultiEdit|NotebookEdit|apply_patchnode "$CLAUDE_PROJECT_DIR/.claude/hooks/probity-gate.mjs" --harness=claude
PreToolUseBash|PowerShellnode "$CLAUDE_PROJECT_DIR/.claude/hooks/block-no-verify.mjs"
PreToolUseBash|PowerShellnode "$CLAUDE_PROJECT_DIR/.claude/hooks/guard-bash.mjs"
PreToolUseAgentnode "$CLAUDE_PROJECT_DIR/.claude/hooks/guard-subagent-model.mjs"
Stop*node "$CLAUDE_PROJECT_DIR/.claude/hooks/gate-stop-dod.mjs"
SessionStart*node "$CLAUDE_PROJECT_DIR/.claude/hooks/inject-rules.mjs"
SessionStart*node "$CLAUDE_PROJECT_DIR/.claude/hooks/warn-subagent-routing.mjs"
SubagentStart*node "$CLAUDE_PROJECT_DIR/.claude/hooks/record-dispatch.mjs" --harness=claude
SubagentStop*node "$CLAUDE_PROJECT_DIR/.claude/hooks/record-dispatch.mjs" --harness=claude

Similar rigs

ameya-vichare/claude-sdd-starter
A platform-agnostic Claude Code setup for engineering teams, using an interactive setup wizard that tailors everything to your project and provides a spec-driven feature development workflow.
★ 7 project Claude Code 5 agents 6mo ago
Orchestrator 2.3k tok ·
Dipen-Dedania/agent-pulse
Know what your agents are doing
★ 11 project Claude CodeCodex 8 agents today
Orchestrator 1.7k tok ·
Caspian-Sun/claude-code-workflow
AI-driven R&D workflow framework: 8-step SDLC, hard gates, @rules traceability chain. Bilingual (EN/ZH).
★ 10 setup Claude Code 5 skills 4 agents 3 hooks 1mo ago
Pragmatist 2.2k tok ·
Caspian-Sun/spider
Tauri 2 + Rust + React desktop tool that visualizes any claude-code-workflow repo as a kanban.
★ 0 project Claude Code 5 skills 4 agents 3 hooks 5mo ago
Pragmatist 2.0k tok ·
copied ✓