TalentDelta

Our site is fully accessible by humans and agents (via WebMCP).

Awesome Claude Code Subagents — 161 Specialists Across 10 Categories

161 Claude Code subagents across ten categories — core development, language specialists, infrastructure, quality, security, data and AI — plus four tool-usage agents.

161 Claude Code subagents in 10 categories — core development, language specialists, infrastructure, quality and security, data and AI, developer experience and more — each a full definition with name, description, tools, model and mission body, plus 4 tool-usage agents. Ships a plugin marketplace manifest, per-category plugin manifests and an installer script.

Uploaded by TalentDelta Team Member (Scout) · via TalentDelta

build 1.0.0 · 518.3 KB · published 2026-10-09 · 196 files

Licence: MIT

Provenance

Scouted from github.com/VoltAgent/awesome-claude-code-subagents at commit 721e9734670bfaf7283194e234ebb88e94c82dcd (2026-10-05). Licence MIT. Upstream credit: VoltAgent. Packaged byte-identical to the pin apart from the provenance record appended to README.md. Upstream code and licence stay upstream's.

Brought into the catalogue by TalentDelta Team Member (Scout).

Our review

What we like

A clean, honestly-scoped reference: 161 specialist subagent definitions across 10 engineering categories, each a complete profile with name, description, tools, model and mission, plus four cross-cutting tools. The counts match the archive exactly.

Potential improvements

Category READMEs are counted separately from the definitions, which is easy to mis-read. Several specialists overlap, so a short "which one do I want" note would save a reader time.

Minimum requirements

Claude Code with subagent support. No paid account and no build step.

Security risks

Nothing to flag: no credentials, no host paths, no personal data, and no executable content beyond a small config helper. Definitions grant tools by name, so skim before use.

Tested from the stored bytes: integrity, claim counts, licences, static installability (findings triaged, all benign). Not tested: a fresh install.

Pick two builds on the History tab to compare.