MCP server Claude CodeCodexCursor +2
One of 2 in .mcp.json
Squad CLI — Command-line interface for the Squad multi-agent runtime. Runs locally from the @bradygaster/squad-cli npm package.
Agent Claude Code
Reviews team work for safety, fairness, and responsible AI compliance. Guardrail, not wall.
Agent Claude Code
Monitors the work queue and backlog, keeps the team progressing, and surfaces blockers.
Agent Claude Code
Maintains session logs, records decisions, and preserves project memory for the Squad team.
Skill Claude CodeCodex
Design agent systems with clear responsibilities, bounded state, and observable control flow.
Skill Claude CodeCodex
Measure agent quality with decision-relevant scenarios, criteria, and reproducible evidence.
Skill Claude CodeCodex
Detect behavior regressions in agent systems using controlled scenarios and observable evidence.
Skill Claude CodeCodex
Specify agent tool interfaces with narrow authority, validated inputs, and auditable outcomes.
Skill Claude CodeCodex
Evaluate AI features for misuse, harmful failure modes, safeguards, and accountable deployment.
Skill Claude CodeCodex
Design APIs and data flows with explicit contracts, validation, privacy, and safe change management.
Skill Claude CodeCodex
Evaluate architecture choices with explicit trade-offs and durable decision records.
Skill Claude CodeCodex
Gather and synthesize customer evidence without overstating confidence or generalizability.
Skill Claude CodeCodex
Plan safe delivery with observable rollouts, rollback criteria, and operational ownership.
Skill Claude CodeCodex
Produce accurate user and operator documentation with concise, evidence-based release notes.
Skill Claude CodeCodex
Define evidence-based product positioning that differentiates without unsupported claims.
Skill Claude CodeCodex
Frame product requirements around outcomes, evidence, constraints, and transparent priorities.
Skill Claude CodeCodex
Create task prompts with explicit goals, constraints, inputs, evaluation, and injection resistance.
Skill Claude CodeCodex
Use prototypes to answer focused usability questions before committing to implementation.
Skill Claude CodeCodex
Assess research sources for provenance, corroboration, recency, and appropriate use.
Skill Claude CodeCodex
Design maintainable systems by making boundaries, failure behavior, and operations explicit.
Skill Claude CodeCodex
Turn reported behavior into reliable repros, risk-based tests, and clear acceptance evidence.
Skill Claude CodeCodex
Identify security threats through assets, trust boundaries, abuse paths, and mitigations.
Skill Claude CodeCodex
Review interface work for accessible interaction, semantics, and resilient responsive behavior.
Skill Claude CodeCodex
Create clear, audience-appropriate writing and distinguish verified facts from claims.
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: