agent-capabilities
CommandMatrix of agent capabilities and their specializations.
๐ก๏ธ Security Reviewer - You perform static and dynamic audits to ensure secure code practices. You flag secrets, poor mod...
> /plugin marketplace add ruvnet/agentic-flow> /plugin install agentic-flow@agentic-flow
name: sparc-security-review description: ๐ก๏ธ Security Reviewer - You perform static and dynamic audits to ensure secure code practices. You flag secrets, poor mod...
You perform static and dynamic audits to ensure secure code practices. You flag secrets, poor modular boundaries, and oversized files.
Scan for exposed secrets, env leaks, and monoliths. Recommend mitigations or refactors to reduce risk. Flag files > 500 lines or direct environment coupling. Use `new_task` to assign sub-audits. Finalize findings with `attempt_completion`.
mcp__claude-flow__sparc_mode {
mode: "security-review",
task_description: "audit API security",
options: {
namespace: "security-review",
non_interactive: false
}
}# Use when running from terminal or MCP tools unavailable npx claude-flow sparc run security-review "audit API security" # For alpha features npx claude-flow@alpha sparc run security-review "audit API security" # With namespace npx claude-flow sparc run security-review "your task" --namespace security-review # Non-interactive mode npx claude-flow sparc run security-review "your task" --non-interactive
# If claude-flow is installed locally ./claude-flow sparc run security-review "audit API security"
// Store mode-specific context
mcp__claude-flow__memory_usage {
action: "store",
key: "security-review_context",
value: "important decisions",
namespace: "security-review"
}
// Query previous work
mcp__claude-flow__memory_search {
pattern: "security-review",
namespace: "security-review",
limit: 5
}# Store mode-specific context npx claude-flow memory store "security-review_context" "important decisions" --namespace security-review # Query previous work npx claude-flow memory query "security-review" --limit 5
Production-ready AI agent orchestration with 66 self-learning agents, 213 MCP tools, and autonomous multi-agent swarms.
Matrix of agent capabilities and their specializations.
Complete guide to all 54 available agent types in Claude Flow.
Reviewed all command files in `.claude/commands/analysis/` directory to ensure proper usage of: - `mcp__claude-flow__*` toolsโฆ
Analyze performance bottlenecks in swarm operations and suggest optimizations.
Implement tasks incrementally โ build, test, verify, commit. Add "auto" to run the whole plan in one approved pass.