Forcharc/claude-config-shared
Shareable Claude Code setup: skills, custom review agents, path-scoped rules, worktree-safety hook.
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 Forcharc/claude-config-shared/agents ./rig-claude-config-shared/agents $ npx degit Forcharc/claude-config-shared/skills ./rig-claude-config-shared/skills $ npx degit Forcharc/claude-config-shared/hooks ./rig-claude-config-shared/hooks
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 Forcharc/claude-config-shared/skills/agent-core-preamble .claude/skills/agent-core-preamble $ npx degit Forcharc/claude-config-shared/skills/commit .claude/skills/commit $ npx degit Forcharc/claude-config-shared/skills/finalize .claude/skills/finalize $ npx degit Forcharc/claude-config-shared/skills/fork-init .claude/skills/fork-init $ npx degit Forcharc/claude-config-shared/skills/gist .claude/skills/gist $ npx degit Forcharc/claude-config-shared/skills/remind-protocol .claude/skills/remind-protocol $ npx degit Forcharc/claude-config-shared/skills/remind-text-style .claude/skills/remind-text-style $ npx degit Forcharc/claude-config-shared/skills/remind-workflow .claude/skills/remind-workflow $ npx degit Forcharc/claude-config-shared/skills/rethink .claude/skills/rethink $ npx degit Forcharc/claude-config-shared/skills/review-mr .claude/skills/review-mr $ npx degit Forcharc/claude-config-shared/skills/review .claude/skills/review $ npx degit Forcharc/claude-config-shared/skills/reviewer-findings-output .claude/skills/reviewer-findings-output $ npx degit Forcharc/claude-config-shared/skills/rule .claude/skills/rule $ npx degit Forcharc/claude-config-shared/skills/techdebt-init .claude/skills/techdebt-init $ npx degit Forcharc/claude-config-shared/skills/techdebt .claude/skills/techdebt $ npx degit Forcharc/claude-config-shared/skills/tell-the-truth .claude/skills/tell-the-truth $ npx degit Forcharc/claude-config-shared/skills/todo .claude/skills/todo $ npx degit Forcharc/claude-config-shared/skills/txt .claude/skills/txt $ npx degit Forcharc/claude-config-shared/skills/where .claude/skills/where $ npx degit Forcharc/claude-config-shared/skills/workflow-guide .claude/skills/workflow-guide
$ curl -fsSL --create-dirs -o .claude/agents/architecture-reviewer.md https://raw.githubusercontent.com/Forcharc/claude-config-shared/main/agents/architecture-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/clean-code-reviewer.md https://raw.githubusercontent.com/Forcharc/claude-config-shared/main/agents/clean-code-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/docs-reviewer.md https://raw.githubusercontent.com/Forcharc/claude-config-shared/main/agents/docs-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/efficiency-reviewer.md https://raw.githubusercontent.com/Forcharc/claude-config-shared/main/agents/efficiency-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/implementer.md https://raw.githubusercontent.com/Forcharc/claude-config-shared/main/agents/implementer.md $ curl -fsSL --create-dirs -o .claude/agents/logic-reviewer.md https://raw.githubusercontent.com/Forcharc/claude-config-shared/main/agents/logic-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/plan-compliance-reviewer.md https://raw.githubusercontent.com/Forcharc/claude-config-shared/main/agents/plan-compliance-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/plan-factcheck-reviewer.md https://raw.githubusercontent.com/Forcharc/claude-config-shared/main/agents/plan-factcheck-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/plan-standards-reviewer.md https://raw.githubusercontent.com/Forcharc/claude-config-shared/main/agents/plan-standards-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/planner.md https://raw.githubusercontent.com/Forcharc/claude-config-shared/main/agents/planner.md $ curl -fsSL --create-dirs -o .claude/agents/research-writer.md https://raw.githubusercontent.com/Forcharc/claude-config-shared/main/agents/research-writer.md $ curl -fsSL --create-dirs -o .claude/agents/review-judge.md https://raw.githubusercontent.com/Forcharc/claude-config-shared/main/agents/review-judge.md $ curl -fsSL --create-dirs -o .claude/agents/security-reviewer.md https://raw.githubusercontent.com/Forcharc/claude-config-shared/main/agents/security-reviewer.md
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 (20)
agent-core-preamblecommitfinalizefork-initgistremind-protocolremind-text-styleremind-workflowrethinkreview-mrreviewreviewer-findings-outputruletechdebt-inittechdebttell-the-truthtodotxtwhereworkflow-guide
Subagents (13)
| architecture-reviewer model: sonnet | Architecture reviewer. Checks layering, dependencies, abstraction boundaries, public API surface, and breaking changes. |
| clean-code-reviewer model: sonnet | Clean Code reviewer. Checks for YAGNI violations, dead code, speculative abstractions, redundant comments, naming, and DRY. |
| docs-reviewer model: sonnet | Documentation-sync reviewer. Checks that docs match the code after a change — missing docs for new behavior, stale/contradicting docs, and violations of procedural "when you touch A, update B" rules. |
| efficiency-reviewer model: sonnet | Performance and efficiency reviewer. Checks for redundant work, missed concurrency, resource leaks, and premature optimization. |
| implementer model: sonnet | Пишет и правит код проекта на основе переданного плана или задачи. Использовать для крупных задач реализации, рефакторинга, мульти-файловых правок. |
| logic-reviewer model: sonnet | Logic and correctness reviewer. Checks for bugs, edge cases, error handling, races, and deleted side-effects. |
| plan-compliance-reviewer model: sonnet | Plan compliance reviewer. Сверяет коммит с планом реализации: всё ли заявленное сделано (MISSING), нет ли работы вне scope (EXTRA), нет ли отступлений от предписанного подхода (DEVIATION). Спавнится в |
| plan-factcheck-reviewer model: sonnet | Plan fact-check reviewer. Проверяет каждое проверяемое утверждение плана на правоту — код через Read/Grep, внешние факты через WebSearch/WebFetch. Ищет галлюцинации. |
| plan-standards-reviewer model: sonnet | Plan standards reviewer. Проверяет план на соответствие rules проекта, устоявшимся паттернам кодовой базы и одобренному пользователем решению. |
| planner model: sonnet | Пишет детальный план реализации в файл. Спавнится главной сессией по конвейеру планирования (создание и доработка по findings). |
| research-writer model: sonnet | Исследует кодовую базу и записывает подробный отчёт в файл. Использовать для любого делегируемого исследования — агент сам вычисляет правильный путь и возвращает ссылку. |
| review-judge model: opus | Судья код-ревью. Читает файлы находок от ревьюеров, верифицирует каждую по коду, отсеивает false positives, классифицирует FIX/DEBT/DROP, записывает DEBT и выдаёт verdict-файл с готовыми инструкциями |
| security-reviewer model: sonnet | Security reviewer. Checks for secrets in code, sensitive data in logs, missing auth checks, input validation, crypto misuse, and unsafe deserialization. |
Similar rigs
ZaaliMohamed123/evolving-claude
A self-improving global Claude Code setup: 10 subagents, on-demand skills, safety hooks, three-tier memory, and a config feedback loop.
Orchestrator 2.2k tok ·
rafagomes/ai-workflow
AI-assisted development workflow toolkit for Claude Code, Cursor, and Codex — skills, agents, and conventions for the full SDLC
Skill Collector 4.0k tok ·
pahlevikun/levistack
Agent skills for people tired of AI slop. 35 skills, 11 subagents, 41 rules and 5 hooks for Claude Code, Cursor and Codex. Verifies before it says done.
Orchestrator 3.1k tok ·
kapadias/nonna
Your AI agent says done. Nonna makes it prove it: she runs your test suite before a coding agent can stop, and blocks pushes to main and secrets in files. Claude Code plugin, plus git hooks for Codex, Cursor, Copilot, Gemini and more
Fort Knox 3.9k tok ·