# Tools

> Every listed resource, editors’ picks first. The filters below can be combined.

- Search: append `?q=<keywords>` to the URL. Separate several keywords with spaces; all of them must match. Matches name, repository, tags, professions, description and README.
- Filter by type: append `?type=<cli|skill|plugin|mcp>` to the URL.
- Filter by profession: append `?profession=<profession id>` to the URL. Separate several ids with commas; a resource matches when it suits any of them. Ids are listed at https://hebbmind.com/api/v1/professions
- Filter by tag: append `?tag=<tag>` to the URL. Separate several tags with commas; a resource must carry all of them. Tags are listed at https://hebbmind.com/api/v1/tags

Tagged `claude-code`, `dev-workflow`, `subagents`: 4 items.

- [SuperClaude Framework](https://hebbmind.com/ja/plugin/superclaude-framework.md): [Plugin] Adds a structured dev process to Claude Code: 30 /sc slash commands for brainstorming, implementation, testing, troubleshooting and research, 20 domain expert subagents and 7 behavior modes, with optional MCPs like Context7. Installs via pipx; a marketplace version is in progress.
- [GSD Core](https://hebbmind.com/ja/plugin/get-shit-done.md): [Plugin] Spec-driven development and context engineering framework (formerly Get Shit Done): a five-step loop of discuss, plan, execute, verify and ship, handing heavy work to subagents with fresh context to avoid degradation in long sessions. Supports Claude Code, Codex and more.
- [Harness](https://hebbmind.com/ja/plugin/harness.md): [Plugin] Say build a harness for this project and it designs a domain-specific agent team, generating subagent definitions, companion skills and orchestration, validates them and keeps evolving them from feedback. Supports workflow orchestration, persistent agent teams and subagent delegation.
- [Unlazy](https://hebbmind.com/ja/skill/unlazy.md): [Skill] Keeps agents from reporting done too early on substantial work: writes acceptance gates with runnable checks before starting, runs only user-approved commands, splits large jobs into a depth tree of verified leaves, and re-checks evidence before reporting. Optional Claude Code Stop hook.