15 tagged design-docs, measured the same way as everything else here.
Plugin Claude Code
Asks the questions an architect would ask: problem clarification, decision guidance, and failure analysis, recorded as plain markdown in your repo. Derived from Microsoft's Clarity Agent.
MCP server Claude CodeCodexCursor +2
MCP server "clarity-agent" as configured in danielrmay/claudity. Runs ${CLAUDE_PLUGIN_ROOT}/scripts/mcp_server.py with python3. Needs 3 environment variables to run.
Instructions file
Instructions for danielrmay/claudity, covering claudity — contributor context, invariants, testing and behavioral changes need behavioral evidence.
Agent
Deliberate misuse and attack by adversarial actors: who would attack, why, and how. Launched by Claudity's failure-brainstorming process; not for direct invocation outside it.
Agent
Human and AI error: user mistakes, operator misconfiguration, cognitive biases, information loss. Launched by Claudity's failure-brainstorming process; not for direct invocation outside it.
Agent
Security vulnerabilities: authentication, authorization, data protection, injection, cryptography, and supply chain. Launched by Claudity's failure-brainstorming process; not for direct invocation outside it.
Skill Claude CodeCodex
Work through an important decision with structured guidance.
Skill Claude CodeCodex
Build the project narrative and audience-specific messaging.
Skill Claude CodeCodex
An AI thinking partner that pushes back. Use when the user wants to think through what they're building and why — explore or clarify a problem, requirements, or stakeholders; weigh a solution or architecture; brainstorm risks and failure modes; or work through a consequential decision. Also use proactively at…
At most 3 mods per repository are shown here — the rest are on their repository pages: