team-red-team
Skill2 starsChanged 3 months agoMITView on GitHub
Adversarial review team: security, scalability, economic exploits, and behavior-based abuse analysis. Use for pre-launch or high-stakes risk analysis from attacker perspective.
In this repository74 other files it gives its agents.
- .claude/CLAUDE.mdCLAUDE.md
- lead-producerSkill
- role-analytics-engineerSkill
- role-backend-engineerSkill
- role-behavioral-economistSkill
- role-brand-strategistSkill
- role-code-reduction-engineerSkill
- role-community-developerSkill
- role-context-managerSkill
- role-cpp-engineerSkill
- role-ctoSkill
- role-database-engineerSkill
- role-data-engineerSkill
- role-devops-engineerSkill
- role-economistSkill
- role-economy-designerSkill
- role-education-researcherSkill
- role-elementary-math-teacherSkill
- role-elementary-teacherSkill
- role-frontend-engineerSkill
- role-game-balance-designerSkill
- role-game-designerSkill
- role-godot-engineerSkill
- role-go-engineerSkill
- role-icelandic-linguistSkill
- role-icelandic-teacherSkill
- role-java-engineerSkill
- role-kotlin-engineerSkill
- role-level-designerSkill
- role-liveops-engineerSkill
- role-move-sui-developerSkill
- role-narrative-designerSkill
- role-open-source-engineerSkill
- role-principal-software-engineerSkill
- role-product-managerSkill
- role-product-marketing-managerSkill
- role-python-engineerSkill
- role-qa-engineerSkill
- role-railway-deploymentSkill
- role-rust-engineerSkill
- role-scalability-engineerSkill
- role-security-engineerSkill
- role-software-architectSkill
- role-technical-product-managerSkill
- role-technical-writerSkill
- role-typescript-engineerSkill
- role-ui-ux-designerSkill
- role-unity-engineerSkill
- team-architecture-reviewSkill
- team-blue-teamSkill
- team-brand-teamSkill
- team-dev-teamSkill
- team-documentationSkill
- team-economy-teamSkill
- team-elementary-educationSkill
- team-frontend-teamSkill
- team-infrastructureSkill
- team-move-teamSkill
- team-open-sourceSkill
- team-product-teamSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 53
When multiple specialists find the same root cause, merge to highest severity.
- Distinctive: line 57
Do not down-rank severity because a fix is expensive.
- Distinctive: line 58
If exploit path is credible, err conservative on severity.
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Red Team
Purpose
Find failures most likely to hurt users, business, or system under malicious or stressed conditions.
Composition
- role-security-engineer: attack surface, vulnerabilities, abuse cases
- role-scalability-engineer: load-induced failures, resource-exhaustion risk
- role-economy-designer: exploit chains, economy-system abuse
- role-behavioral-economist: scam pressure, manipulation, bias-driven attacks
- Synthesis: deduplicate, severity merge, acceptance
Use When
- Pre-launch or high-stakes risk review
- Checking whether new system can be attacked, manipulated, or broken under stress
- Reviewing incident class for similar undiscovered failures
- System with real financial, reputation, or exploit risk
Do NOT Use When
- Constructive implementation review (use
team-dev-team) - Routine product, UX, or documentation analysis
- Verifying cleanup (use
team-blue-team)
Workflow
- Each specialist attacks from own perspective first.
- Merge duplicates by root cause, keep highest severity.
- Separate exploit blockers from follow-up hardening.
- Produce one severity-ranked adversarial report.
Default Output
RED TEAM REPORT
===============
Critical Risks: must-fix blockers
High Risks: serious attack/stress paths
Shared Root Causes: failures explaining multiple findings
Recommendation: ship / hold / rework, mitigation orderSuccess Criteria
- Findings are adversarial, not generic code review.
- Shared root causes deduplicated cleanly.
- Severity is conservative when exploit path is credible.
Conflict Resolution
- Security Engineer owns severity ranking. Scalability Engineer owns load-failure assessment.
- When multiple specialists find the same root cause, merge to highest severity.
Anti-Drift Rules
- Findings must be adversarial and exploitable, not generic code review comments.
- Do not down-rank severity because a fix is expensive.
- If exploit path is credible, err conservative on severity.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

