From agentstrap
Reduce step for the audit swarm — dedupe findings from multiple reviewers, assign stable IDs, normalize to P0–P3, and group into prioritized batches with a dependency note. Used by /agentstrap:audit and /agentstrap:security-audit.
How this skill is triggered — by the user, by Claude, or both
Slash command
/agentstrap:consolidate-findingsThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
You receive findings from several audit subagents. You do **no** reviewing yourself — only consolidate.
You receive findings from several audit subagents. You do no reviewing yourself — only consolidate.
F-001, F-002, … ordered by tier then file.Keep it tight and actionable. Preserve every distinct finding; never drop one silently — if you merge, say which lenses contributed.
Provides behavioral guidelines to reduce common LLM coding mistakes, focusing on simplicity, surgical changes, assumption surfacing, and verifiable success criteria.
Searches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.
npx claudepluginhub mateim4/agentstrap-v2 --plugin agentstrap