Skill Claude CodeCodex
Design agent systems with clear responsibilities, bounded state, and observable control flow.
not rated 7 today A 19 tokens
original MIT
7Stars on the repository
88Mods indexed here, across every type
todayLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown
Skill Claude CodeCodex
Measure agent quality with decision-relevant scenarios, criteria, and reproducible evidence.
not rated 7 today A 20 tokens
original MIT
Skill Claude CodeCodex
Detect behavior regressions in agent systems using controlled scenarios and observable evidence.
not rated 7 today A 18 tokens
original MIT
agent-tools
04Skill Claude CodeCodex
Specify agent tool interfaces with narrow authority, validated inputs, and auditable outcomes.
not rated 7 today A 19 tokens
original MIT
ai-safety
05Skill Claude CodeCodex
Evaluate AI features for misuse, harmful failure modes, safeguards, and accountable deployment.
not rated 7 today A 20 tokens
original MIT
Skill Claude CodeCodex
Design APIs and data flows with explicit contracts, validation, privacy, and safe change management.
not rated 7 today A 23 tokens
original MIT
Skill Claude CodeCodex
Evaluate architecture choices with explicit trade-offs and durable decision records.
not rated 7 today A 16 tokens
original MIT
Skill Claude CodeCodex
Gather and synthesize customer evidence without overstating confidence or generalizability.
not rated 7 today A 21 tokens
original MIT
Skill Claude CodeCodex
Plan safe delivery with observable rollouts, rollback criteria, and operational ownership.
not rated 7 today A 19 tokens
original MIT
Skill Claude CodeCodex
Produce accurate user and operator documentation with concise, evidence-based release notes.
not rated 7 today A 19 tokens
original MIT
positioning
11Skill Claude CodeCodex
Define evidence-based product positioning that differentiates without unsupported claims.
not rated 7 today A 15 tokens
original MIT
Skill Claude CodeCodex
Frame product requirements around outcomes, evidence, constraints, and transparent priorities.
not rated 7 today A 20 tokens
original MIT
Skill Claude CodeCodex
Create task prompts with explicit goals, constraints, inputs, evaluation, and injection resistance.
not rated 7 today A 21 tokens
original MIT
prototype-ux
14Skill Claude CodeCodex
Use prototypes to answer focused usability questions before committing to implementation.
not rated 7 today A 16 tokens
original MIT
Skill Claude CodeCodex
Assess research sources for provenance, corroboration, recency, and appropriate use.
not rated 7 today A 20 tokens
original MIT
Skill Claude CodeCodex
Design maintainable systems by making boundaries, failure behavior, and operations explicit.
not rated 7 today A 18 tokens
original MIT
Skill Claude CodeCodex
Turn reported behavior into reliable repros, risk-based tests, and clear acceptance evidence.
not rated 7 today A 23 tokens
original MIT
Skill Claude CodeCodex
Identify security threats through assets, trust boundaries, abuse paths, and mitigations.
not rated 7 today A 21 tokens
original MIT
Skill Claude CodeCodex
Review interface work for accessible interaction, semantics, and resilient responsive behavior.
not rated 7 today A 18 tokens
original MIT
Skill Claude CodeCodex
Create clear, audience-appropriate writing and distinguish verified facts from claims.
not rated 7 today A 22 tokens
original MIT
api-harness
21Skill Claude CodeCodex
Use the API harness to drive Agentweaver through its REST API, capture the complete request/response evidence, and emit a normalized agentweaver.persona-judge-verdict/v1 JSON verdict. It is for backend/API end-to-end validation; use the UI or MCP harness for those surfaces.
not rated 7
changed 14d ago A 0 tokens
original MIT
mcp-harness
22Skill Claude CodeCodex needs its repo
Use this harness to validate Agentweaver's MCP protocol surface, capture the complete tools/call request/response evidence, and emit a normalized agentweaver.persona-judge-verdict/v1 JSON verdict. It is for MCP end-to-end validation, MCP tool-contract regression checks, and investigation of an MCP-reported issue; use…
not rated 7
changed 1mo ago A 0 tokens
original MIT
Skill Claude CodeCodex needs its repo
Use this contract when you need to discover the current built-in scenario/persona catalog for one harness surface, or generate a reviewed new persona core and surface adapter for a new test intent.
not rated 7
changed 9d ago A 0 tokens
original MIT
Skill Claude CodeCodex needs its repo
Run the Agentweaver persona-driven Playwright UI evidence harness. Use for a specific persona's deployed browser flow, end-to-end UI validation, or investigation of a UI-reported issue.
not rated 7
changed 16d ago A 43 tokens
original MIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: