shawnclybor/clybor-claude-tooling
Standardized Claude Code bootstrap — drop-in .claude/ tree with a 19-agent adversarial review team, Ralph Loop, dev-flow skills, and an init script. Agnostic, project-ready.
ARCHETYPE
Orchestrator
A bench of specialised subagents. The main agent mostly delegates.
Copy this rig
# review before running: this installs third-party code
$ npx degit shawnclybor/clybor-claude-tooling/.claude ./rig-clybor-claude-tooling # 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 shawnclybor/clybor-claude-tooling/.claude/skills/adversarial-re-read .claude/skills/adversarial-re-read $ npx degit shawnclybor/clybor-claude-tooling/.claude/skills/adversarial-review .claude/skills/adversarial-review $ npx degit shawnclybor/clybor-claude-tooling/.claude/skills/build-estimate .claude/skills/build-estimate $ npx degit shawnclybor/clybor-claude-tooling/.claude/skills/build-evaluate .claude/skills/build-evaluate $ npx degit shawnclybor/clybor-claude-tooling/.claude/skills/build-execute .claude/skills/build-execute $ npx degit shawnclybor/clybor-claude-tooling/.claude/skills/build-plan .claude/skills/build-plan $ npx degit shawnclybor/clybor-claude-tooling/.claude/skills/build-polish .claude/skills/build-polish $ npx degit shawnclybor/clybor-claude-tooling/.claude/skills/build-prd .claude/skills/build-prd $ npx degit shawnclybor/clybor-claude-tooling/.claude/skills/build-probe .claude/skills/build-probe $ npx degit shawnclybor/clybor-claude-tooling/.claude/skills/build-validate .claude/skills/build-validate $ npx degit shawnclybor/clybor-claude-tooling/.claude/skills/excel-connector-governance .claude/skills/excel-connector-governance $ npx degit shawnclybor/clybor-claude-tooling/.claude/skills/five-whys .claude/skills/five-whys $ npx degit shawnclybor/clybor-claude-tooling/.claude/skills/insight-builder .claude/skills/insight-builder $ npx degit shawnclybor/clybor-claude-tooling/.claude/skills/insight-crystallizer .claude/skills/insight-crystallizer $ npx degit shawnclybor/clybor-claude-tooling/.claude/skills/insight-promotion .claude/skills/insight-promotion $ npx degit shawnclybor/clybor-claude-tooling/.claude/skills/multi-session .claude/skills/multi-session $ npx degit shawnclybor/clybor-claude-tooling/.claude/skills/notion-governance .claude/skills/notion-governance $ npx degit shawnclybor/clybor-claude-tooling/.claude/skills/ooda .claude/skills/ooda $ npx degit shawnclybor/clybor-claude-tooling/.claude/skills/prd-writer .claude/skills/prd-writer $ npx degit shawnclybor/clybor-claude-tooling/.claude/skills/promote-to-tooling .claude/skills/promote-to-tooling $ npx degit shawnclybor/clybor-claude-tooling/.claude/skills/quality-review .claude/skills/quality-review $ npx degit shawnclybor/clybor-claude-tooling/.claude/skills/ralph-implement .claude/skills/ralph-implement $ npx degit shawnclybor/clybor-claude-tooling/.claude/skills/ralph-loop .claude/skills/ralph-loop $ npx degit shawnclybor/clybor-claude-tooling/.claude/skills/search-governance .claude/skills/search-governance $ npx degit shawnclybor/clybor-claude-tooling/.claude/skills/session-output .claude/skills/session-output $ npx degit shawnclybor/clybor-claude-tooling/.claude/skills/skill-validator .claude/skills/skill-validator $ npx degit shawnclybor/clybor-claude-tooling/.claude/skills/task-plan .claude/skills/task-plan $ npx degit shawnclybor/clybor-claude-tooling/.claude/skills/verify .claude/skills/verify $ npx degit shawnclybor/clybor-claude-tooling/.claude/skills/voice-profile-test .claude/skills/voice-profile-test $ npx degit shawnclybor/clybor-claude-tooling/.claude/skills/why-diagnostic .claude/skills/why-diagnostic $ npx degit shawnclybor/clybor-claude-tooling/.claude/skills/writing-quality .claude/skills/writing-quality $ npx degit shawnclybor/clybor-claude-tooling/assets/skills/client-refresh .claude/skills/client-refresh $ npx degit shawnclybor/clybor-claude-tooling/assets/skills/governance-skill-template .claude/skills/governance-skill-template $ npx degit shawnclybor/clybor-claude-tooling/assets/skills/graduate-project .claude/skills/graduate-project $ npx degit shawnclybor/clybor-claude-tooling/assets/skills/meeting-workflow .claude/skills/meeting-workflow $ npx degit shawnclybor/clybor-claude-tooling/assets/skills/project-bootstrap .claude/skills/project-bootstrap $ npx degit shawnclybor/clybor-claude-tooling/assets/skills/yellow-sheet-corpus .claude/skills/yellow-sheet-corpus $ npx degit shawnclybor/clybor-claude-tooling/claude-skills/.claude/skills/plugin-builder .claude/skills/plugin-builder
$ curl -fsSL --create-dirs -o .claude/agents/code-analyzer.md https://raw.githubusercontent.com/shawnclybor/clybor-claude-tooling/main/.claude/agents/code/code-analyzer.md $ curl -fsSL --create-dirs -o .claude/agents/code-reviewer.md https://raw.githubusercontent.com/shawnclybor/clybor-claude-tooling/main/.claude/agents/code/code-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/debugger.md https://raw.githubusercontent.com/shawnclybor/clybor-claude-tooling/main/.claude/agents/code/debugger.md $ curl -fsSL --create-dirs -o .claude/agents/security-auditor.md https://raw.githubusercontent.com/shawnclybor/clybor-claude-tooling/main/.claude/agents/code/security-auditor.md $ curl -fsSL --create-dirs -o .claude/agents/agent-organizer.md https://raw.githubusercontent.com/shawnclybor/clybor-claude-tooling/main/.claude/agents/orchestration/agent-organizer.md $ curl -fsSL --create-dirs -o .claude/agents/context-manager.md https://raw.githubusercontent.com/shawnclybor/clybor-claude-tooling/main/.claude/agents/orchestration/context-manager.md $ curl -fsSL --create-dirs -o .claude/agents/error-coordinator.md https://raw.githubusercontent.com/shawnclybor/clybor-claude-tooling/main/.claude/agents/orchestration/error-coordinator.md $ curl -fsSL --create-dirs -o .claude/agents/knowledge-synthesizer.md https://raw.githubusercontent.com/shawnclybor/clybor-claude-tooling/main/.claude/agents/orchestration/knowledge-synthesizer.md $ curl -fsSL --create-dirs -o .claude/agents/multi-agent-coordinator.md https://raw.githubusercontent.com/shawnclybor/clybor-claude-tooling/main/.claude/agents/orchestration/multi-agent-coordinator.md $ curl -fsSL --create-dirs -o .claude/agents/performance-monitor.md https://raw.githubusercontent.com/shawnclybor/clybor-claude-tooling/main/.claude/agents/orchestration/performance-monitor.md $ curl -fsSL --create-dirs -o .claude/agents/task-distributor.md https://raw.githubusercontent.com/shawnclybor/clybor-claude-tooling/main/.claude/agents/orchestration/task-distributor.md $ curl -fsSL --create-dirs -o .claude/agents/workflow-orchestrator.md https://raw.githubusercontent.com/shawnclybor/clybor-claude-tooling/main/.claude/agents/orchestration/workflow-orchestrator.md $ curl -fsSL --create-dirs -o .claude/agents/adversarial-reviewer.md https://raw.githubusercontent.com/shawnclybor/clybor-claude-tooling/main/.claude/agents/quality/adversarial-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/chaos-engineer.md https://raw.githubusercontent.com/shawnclybor/clybor-claude-tooling/main/.claude/agents/quality/chaos-engineer.md $ curl -fsSL --create-dirs -o .claude/agents/simplifier.md https://raw.githubusercontent.com/shawnclybor/clybor-claude-tooling/main/.claude/agents/quality/simplifier.md $ curl -fsSL --create-dirs -o .claude/agents/evidence-auditor.md https://raw.githubusercontent.com/shawnclybor/clybor-claude-tooling/main/.claude/agents/research/evidence-auditor.md $ curl -fsSL --create-dirs -o .claude/agents/metadata-fetcher.md https://raw.githubusercontent.com/shawnclybor/clybor-claude-tooling/main/.claude/agents/research/metadata-fetcher.md $ curl -fsSL --create-dirs -o .claude/agents/research-analyst.md https://raw.githubusercontent.com/shawnclybor/clybor-claude-tooling/main/.claude/agents/research/research-analyst.md $ curl -fsSL --create-dirs -o .claude/agents/search-specialist.md https://raw.githubusercontent.com/shawnclybor/clybor-claude-tooling/main/.claude/agents/research/search-specialist.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 (38)
adversarial-re-readadversarial-reviewbuild-estimatebuild-evaluatebuild-executebuild-planbuild-polishbuild-prdbuild-probebuild-validateexcel-connector-governancefive-whysinsight-builderinsight-crystallizerinsight-promotionmulti-sessionnotion-governanceoodaprd-writerpromote-to-toolingquality-reviewralph-implementralph-loopsearch-governancesession-outputskill-validatortask-planverifyvoice-profile-testwhy-diagnosticwriting-qualityclient-refreshgovernance-skill-templategraduate-projectmeeting-workflowproject-bootstrapyellow-sheet-corpusplugin-builder
Subagents (19)
| code-analyzer model: sonnet | Deep-dive cross-file analysis. Traces logic flow across files, investigates suspicious behavior, answers "how does this actually work" and "where does this break." Different from code-reviewer (read-o |
| code-reviewer model: sonnet | Read-only review of a code diff or specific file/symbol set. Catches correctness bugs, blast-radius misses, type-safety gaps, observability gaps, security issues, naming and structural issues. Use aft |
| debugger model: sonnet | Diagnose a bug or unexpected behavior. Reproduces the failure, forms hypotheses, narrows the cause with evidence, proposes (and on request implements) a minimal fix, verifies the fix. Complements `fiv |
| security-auditor model: opus | Read-only security audit of a code surface. OWASP-style assessment of input handling, secrets management, auth, authorization, injection risk, dependencies, and crypto practices. Use before shipping a |
| agent-organizer model: sonnet | Picks which agents to spawn for a given task. Reads the task description, maps it to capability profiles, returns a short ranked list with reasoning. Use when the user describes a task and you don't a |
| context-manager model: sonnet | Manages shared context across agents. Prevents context fragmentation when work hands off between agents, and curates what each agent needs to see without overwhelming its window. Use when 3+ agents in |
| error-coordinator model: sonnet | Correlates failures across parallel agents and surfaces the root cause when symptoms are spread across multiple agents' outputs. Use when parallel agents fail in ways that look unrelated but share a r |
| knowledge-synthesizer model: sonnet | Synthesizes findings across multiple agents into a single coherent report. Reads each agent's output, identifies agreements, surfaces disagreements without forcing resolution, and produces a unified n |
| multi-agent-coordinator model: sonnet | Tracks state across parallel agents, handles partial failures, coordinates handoffs. Use when 3+ agents run in parallel and the results need to be combined coherently, or when an agent failure should |
| performance-monitor model: sonnet | Observes agent latency, retry counts, escalation rates, and budget consumption across a workflow. Surfaces hotspots — agents that consistently time out, retry, or escalate. Use when the team has been |
| task-distributor model: sonnet | Splits a task list across parallel agents safely. Identifies which tasks can run concurrently without contended writes, dependencies, or shared resource conflicts. Returns groups suitable for parallel |
| workflow-orchestrator model: sonnet | Sequences multi-step workflows with explicit state transitions, gates between stages, and recovery on partial failure. Use when a task spans 3+ ordered stages, when stages have non-trivial pass criter |
| adversarial-reviewer model: opus | Challenge claims, find weaknesses in reasoning, test whether conclusions are actually supported by evidence. The adversarial reviewer's job is to make the work stronger by finding what's wrong with it |
| chaos-engineer model: sonnet | Stress-test plans, designs, and code for robustness. Find edge cases, failure modes, malformed inputs, scale assumptions, and adversarial use patterns that the happy path never exercises. |
| simplifier model: sonnet | Assess how well KISS/YAGNI principles are being followed. Find over-engineering, unnecessary complexity, premature abstractions, and opportunities to simplify. Keep features, simplify implementation. |
| evidence-auditor model: sonnet | Verifies that quotes, citations, and factual claims in a document trace accurately to their sources. Cross-checks every assertion against original material. Flags unverified, misattributed, or fabrica |
| metadata-fetcher model: haiku | Mechanical metadata lookups — bibliographic data, DOI resolution, package versions, license info, open-access status. Returns structured records. Use when you need accurate metadata for a known source |
| research-analyst model: sonnet | Deep research and multi-source synthesis. Reads across documentation, papers, articles, codebases, and discussion threads to produce a cited, structured answer to a research question. Use when the que |
| search-specialist model: haiku | Quick documentation and reference lookups. Optimized for "find the canonical answer for this specific question" — API signatures, error codes, configuration examples, exact quotes. Returns a short cit |
Slash commands (8)
/adversarial-review/adversarial/chaos/daily-review/five-whys/quality-review/ralph-loop/simplify
Similar rigs
matheus-rib1108/meu-kit-claude-code
Meu kit do Claude Code: skills, agentes, plugins e conectores MCP, em português, que se atualiza sozinho
Orchestrator 19.3k tok · · Q0
nandofarias/dotfiles
Blending some Ghostty + Tmux + Neovim configs 🧨
Orchestrator 3.0k tok · · Q0
Yassinekrn/claude-setup
Personal Claude Code setup — orchestrator/subagent delegation policy, custom agents, and a colored PowerShell statusline (git branch, model+effort, tokens, cost, rate limits).
Orchestrator 1.2k tok · · Q15
urban6/my-harness
새 프로젝트에 적용할 수 있는 Claude Code 기본 세팅
Orchestrator 1.6k tok · · Q0