Security & Testing Agent Skills for Claude Code

Complete security architecture overhaul for claude-flow v3.

A comprehensive verification system for Claude Code sessions.

Comprehensive truth scoring, code quality verification, and automatic rollback system with 0.95 accuracy threshold for ensuring…

Use this when: red-team my optimization metric, find ways to game my metric, metric pre-mortem, adversarial metric evaluation, gaming…

Use ONLY for code review and test write/review guidance in `packages/agent-core-v2` (the DI × Scope agent engine).

Independent local multi-model review for contested, security-sensitive, high-risk, or merge-critical plans and changes.

Harden Kubernetes RBAC to least privilege and detect abuse.

Launch a specific Coval evaluation with explicit cases and execution bounds.

Integrates LazyCat MicroServer authentication systems, including OIDC SSO, HTTP identity headers, public API routing, and API tokens.

Map modernization opportunities in a legacy codebase — identify unsupported dependencies, architecture seams, and migration paths using…

Expert HIPAA compliance assistant for healthcare and software contexts.

Exploits JWT algorithm confusion where the server's verification library trusts the alg named in the token header, by switching RS256 to…

License compliance checking and conflict detection

Use only when the user explicitly asks for TDD, a failing test, or a regression test, OR when the bug has an obvious cheap local test…

Run Lighthouse audits and implement performance, accessibility, and SEO fixes

Use BEFORE declaring victory / shipping / committing, AND proactively for any non-trivial claim, answer, plan, or decision that would…

Report the embedded release marker when testing public Skill installation or marketplace updates.

Confine an LLM agent's actions with tool allowlists, least-privilege credentials, parameter validation, and human-in-the-loop gates.

Run multi-LLM council for adversarial debate and cross-validation.

Poison the data an LLM application trusts — its RAG knowledge base, fine-tuning corpus, or ingestion pipeline — so that later answers…

Abuse an over-privileged LLM agent — excessive tools, permissions, or autonomy — to make it perform actions beyond its intended scope…