wshobson/agents
A multi-harness plugin marketplace of role-specialized subagents (reviewer, architect, security, docs) installable across Claude Code, Codex CLI, Cursor, and other runtimes. Agentiquette scores it 72/100 (A-tier), methodology v1.0, scored 2026-07-07.
Key facts
| Category | Skill collection |
|---|---|
| License | MIT |
| Maintainer | wshobson |
| Compatible agents | claude-code, codex, cursor, copilot, generic |
| File patterns | SKILL.md, plugin-manifest |
| Triggering | manual-reference |
| GitHub metrics | 37,609 stars · 4,035 forks · 11 open issues (fetched 2026-07-07) |
| Last commit | 2026-07-06 |
| Created | 2025-07-24 |
Editorial analysis
Breadth is the product: dozens of role definitions, consistently formatted, portable across harnesses. The best entries are genuinely useful starting points for team standards. The catalog format is also the weakness: role prompts are identity-layer artifacts, thinner than procedural skills, and few define verification steps or failure behavior.
Risks
Quality varies across the catalog; treat each agent definition as needing individual review before team adoption.
Evidence notes: Composability: role agents combine cleanly. Reliability: definitions describe expertise, not workflows with checks. Eval readiness: no per-agent success criteria. Maintenance: active, low open-issue count relative to adoption.
Install and first run
Install individual agents via the marketplace manifest for your runtime.Alternatives in this category
Anthropic's first-party public skill collection: the de facto reference for SKILL.md structure, frontmatter conventions, and…
140 domain skills plus 100+ database connectors that turn a coding agent into a working research assistant for biology, chemistry, medicine,…
A defense-tech company's internally-maintained skill set, published. Notable for governance discipline: explicit boundaries, scripts treated…
Compare with anthropic-skills · Compare with scientific-agent-skills
Embed this badge
Maintainers of scored entries can embed their live badge; it updates when the score does and links back to this page.
[](https://agentiquette.com/index/repos/wshobson-agents)Frequently asked questions
Is wshobson/agents good?
wshobson/agents scores 72/100 (A-tier) on Agentiquette's methodology v1.0, scored 2026-07-07. Strengths and weaknesses are in the editorial analysis; the score is explained dimension by dimension in the scorecard.
What is wshobson/agents for?
A multi-harness plugin marketplace of role-specialized subagents (reviewer, architect, security, docs) installable across Claude Code, Codex CLI, Cursor, and other runtimes.
Is wshobson/agents maintained?
Last commit 2026-07-06, 11 open issues at fetch time (2026-07-07). Maintenance is scored at 88 of 100.
Maintainer of wshobson/agents? Claim this listing and suggest corrections.