메뉴
Third-party Claude Code token/context/code-review tools. Use when choosing or recommending an external tool to reduce token usage, manage context, or review large codebases (caveman, code-review-graph, token-savior, context-mode...).
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Docker & Hadolint validation (2026). Use when working with Docker, containers, or validating Dockerfiles.
Security guidelines and OWASP Top 10. Use when reviewing security, implementing authentication or authorization, hardening code, or discussing vulnerabilities.
Third-party Claude Code token/context/code-review tools. Use when choosing or recommending an external tool to reduce token usage, manage context, or review large codebases.
Testing Flutter 3.44 / BLoC v9 / Riverpod 3 - Stratégie Complète. Use when writing tests, reviewing test coverage, or setting up testing.
Testing React Native 0.85+. Use when writing tests, reviewing test coverage, or setting up testing.
Stratégie de Tests Symfony 8.1 / PHP 8.5. Use when writing tests, reviewing test coverage, or setting up testing.
| name | ecosystem-tools |
| description | Third-party Claude Code token/context/code-review tools. Use when choosing or recommending an external tool to reduce token usage, manage context, or review large codebases (caveman, code-review-graph, token-savior, context-mode...). |
| triggers | {"keywords":["token optimization","reduce tokens","context management","code review tool","caveman","code-review-graph","token-savior","context-mode","claude-context","MCP server","RTK alternative"]} |
| auto_suggest | true |
Curated third-party Claude Code tools that complement Claude Craft's native token/context stack (RTK,
context: fork skills, compaction hooks). None are bundled — they are documented with activation
recipes and license caveats.
See @docs/ECOSYSTEM.md for the full catalogue, licenses, and .mcp.json snippets.
| Tool | License | Use it for | Rec |
|---|---|---|---|
| caveman | MIT | Compress agent output ~65% | ✅ Integrate |
| code-review-graph | MIT | AST graph → read only the blast radius on review | ✅ Integrate |
| token-savior | MIT | Symbol index + Bash output compaction (−80%), RTK alternative | ✅ Integrate |
| claude-token-efficient | MIT | Anti-verbosity CLAUDE.md drop-in | ✅ Integrate |
| context-mode | ELv2 | Output sandboxing — license blocks commercial redistribution | 🔶 Reference |
| claude-context | MIT | Semantic search; needs a Milvus/Zilliz vector DB | 🔶 Reference |
Audit the source and pin a version before enabling any third-party MCP server or skill — see
@.claude/rules/11-security.mdand@docs/MCP.md#security.
