Stats
Actions
Tags
From agentops
Probes docs, skills, plans, or claims for weaknesses, gaps, or unstated assumptions before shipping. Returns structured verdicts.
How this skill is triggered — by the user, by Claude, or both
Slash command
/agentops:red-teamThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
This skill encodes independent-verdict machinery and now lives with the outer
This skill encodes independent-verdict machinery and now lives with the outer
gate product. Canonical: ~/dev/mt-olympus/.claude/skills/red-team/SKILL.md —
read and follow that file. This stub preserves fleet routing until the
using-agentops catalog closer updates the registry (skill-prune Lane A,
evidence/skill-prune-recon.md).
npx claudepluginhub boshu2/agentops --plugin agentopsAdversarially reviews any artifact (design docs, code, PRs, docs) by dispatching fresh Devil's Advocate subagents iteratively until clean.
Stress-tests plans using red-team/blue-team adversarial review: red team generates grounded what-if questions on gaps and assumptions; blue team delivers verdicts. Ideal before implementation or stakeholder review.
Pre-implementation red-team analysis that stress-tests plans for edge cases, security holes, scalability bottlenecks, error propagation, and integration conflicts before code is written.