red-team
Offensive security team skill providing methodology guidance for penetration testing and red team engagements. Invoked when users request penetration testing, reconnaissance, vulnerability analysis, exploitation methodology, social engineering, C2 infrastructure, or engagement reporting. Routes to 11 specialized agents covering the full MITRE ATT&CK kill chain. All engagements require red-lead scope authorization before any other agent. Follows PTES, OSSTMM, and ATT&CK methodology frameworks.
What this skill does
# Red Team Skill
> **Version:** 1.0.0
> **Framework:** Jerry Red-Team
> **Constitutional Compliance:** Jerry Constitution v1.0
> **SSOT Reference:** ADR-PROJ010-001 (Agent Team Architecture), ADR-PROJ010-006 (Authorization & Scope Control)
## Document Audience (Triple-Lens)
This SKILL.md serves multiple audiences:
| Level | Audience | Sections to Focus On |
|-------|----------|---------------------|
| **L0 (Stakeholder)** | Engagement managers, leadership | [Purpose](#purpose), [When to Use This Skill](#when-to-use-this-skill), [Routing Disambiguation](#routing-disambiguation), [Mandatory Authorization](#mandatory-authorization), [Quick Reference](#quick-reference) |
| **L1 (Practitioner)** | Security testers invoking agents | [Available Agents](#available-agents), [Invoking an Agent](#invoking-an-agent), [Orchestration Flow](#orchestration-flow), [Cross-Skill Integration Points](#cross-skill-integration-points) |
| **L2 (Architect)** | Framework designers, governance reviewers | [Authorization Architecture](#authorization-architecture), [Circuit Breaker Integration](#circuit-breaker-integration), [Safety Alignment Compatibility](#safety-alignment-compatibility), [Constitutional Compliance](#constitutional-compliance) |
---
## Purpose
The Red Team skill provides **methodology guidance for authorized penetration testing and red team engagements**. It routes to 11 specialized agents that collectively cover the full MITRE ATT&CK kill chain (14/14 tactics at STRONG coverage level), following established professional methodology frameworks: PTES (Penetration Testing Execution Standard), OSSTMM (Open Source Security Testing Methodology Manual), and NIST SP 800-115 (Technical Guide to Information Security Testing and Assessment).
### Key Capabilities
- **Scope & Authorization Management** -- Formal engagement scoping with Rules of Engagement, target allowlists, and technique authorization
- **Full Kill Chain Coverage** -- 11 agents spanning Reconnaissance through Exfiltration with explicit ATT&CK tactic mapping
- **Non-Linear Workflow** -- Iterative phase cycling that mirrors real engagement dynamics, not rigid sequential execution
- **Distributed Defense Evasion** -- TA0005 techniques embedded in each operational agent's phase-specific tradecraft
- **Cross-Skill Integration** -- 4 purple team integration points with /eng-team for adversarial-collaborative hardening
- **Three-Level Degradation** -- All agents function standalone (AD-010); tools augment evidence quality but do not enable reasoning
### What This Skill Is NOT
This skill provides **methodology guidance**, not autonomous exploitation. It does NOT:
- Execute exploits or payloads autonomously
- Access live systems or networks directly
- Generate weaponized exploit code
- Operate without explicit human authorization
- Replace human judgment for novel discovery or legal decisions
This design follows AD-001 (Methodology-First Design Paradigm): LLMs excel at methodology guidance, structured reasoning, and report generation but fundamentally cannot replace tool execution or human judgment for novel discovery (S-001 Convergence 1, D-002).
---
## When to Use This Skill
Activate when:
- Planning or executing a penetration testing engagement
- Performing reconnaissance or attack surface analysis
- Analyzing vulnerabilities and assessing exploit availability
- Developing exploitation methodology or payload crafting guidance
- Conducting privilege escalation, lateral movement, or persistence operations
- Planning data exfiltration testing within authorized scope
- Setting up C2 infrastructure or engagement tooling
- Conducting social engineering assessments (phishing, pretexting, vishing)
- Generating engagement reports with findings, risk scores, and remediation guidance
- Validating /eng-team defenses through adversarial testing (purple team)
NEVER invoke this skill when:
- Task is building secure software (defensive security) -- Consequence: Offensive methodology applied to defensive engineering produces attack narratives instead of hardened code; STRIDE/DREAD threat modeling and OWASP compliance not loaded; use `/eng-team` instead
- Task is adversarial quality review of deliverables -- Consequence: Penetration testing methodology applied to quality assessment produces engagement reports instead of quality scores; S-014 rubric not available; use `/adversary` instead
- Conducting general security research without an engagement context -- Consequence: Red team agents require authorized scope documents; unscoped security research lacks engagement boundaries and authorization controls; use `/problem-solving` instead
- No active scope document exists and no engagement is being planned -- Consequence: Red team operations without scope authorization violate engagement methodology; agents will halt at scope validation
- Target is outside any authorized engagement boundary -- Consequence: Out-of-scope testing violates rules of engagement; red-lead agent enforces scope authority as a hard gate
See [Routing Disambiguation](#routing-disambiguation) for full exclusion conditions with consequences.
---
## Available Agents
| Agent | Role | ATT&CK Tactics | Model | Output Location |
|-------|------|----------------|-------|-----------------|
| `red-lead` | Engagement Lead & Scope Authority | All (oversight) | opus | `projects/${JERRY_PROJECT}/engagements/{engagement-id}/red-lead-{topic-slug}.md` |
| `red-recon` | Reconnaissance Specialist | TA0043 Reconnaissance | sonnet | `projects/${JERRY_PROJECT}/engagements/{engagement-id}/red-recon-{topic-slug}.md` |
| `red-vuln` | Vulnerability Analyst | Analysis support | sonnet | `projects/${JERRY_PROJECT}/engagements/{engagement-id}/red-vuln-{topic-slug}.md` |
| `red-exploit` | Exploitation Specialist | TA0001, TA0002, TA0040 | sonnet | `projects/${JERRY_PROJECT}/engagements/{engagement-id}/red-exploit-{topic-slug}.md` |
| `red-privesc` | Privilege Escalation Specialist | TA0004, TA0006 | sonnet | `projects/${JERRY_PROJECT}/engagements/{engagement-id}/red-privesc-{topic-slug}.md` |
| `red-lateral` | Lateral Movement Specialist | TA0008, TA0007 | sonnet | `projects/${JERRY_PROJECT}/engagements/{engagement-id}/red-lateral-{topic-slug}.md` |
| `red-persist` | Persistence Specialist (RoE-GATED) | TA0003, TA0005 | sonnet | `projects/${JERRY_PROJECT}/engagements/{engagement-id}/red-persist-{topic-slug}.md` |
| `red-exfil` | Data Exfiltration Specialist (RoE-GATED) | TA0009, TA0010 | sonnet | `projects/${JERRY_PROJECT}/engagements/{engagement-id}/red-exfil-{topic-slug}.md` |
| `red-reporter` | Engagement Reporter | TA0040 (documentation) | opus | `projects/${JERRY_PROJECT}/engagements/{engagement-id}/red-reporter-{topic-slug}.md` |
| `red-infra` | Infrastructure & Tooling Specialist | TA0042, TA0011, TA0005 | sonnet | `projects/${JERRY_PROJECT}/engagements/{engagement-id}/red-infra-{topic-slug}.md` |
| `red-social` | Social Engineering Specialist (RoE-GATED) | TA0043, TA0001 | sonnet | `projects/${JERRY_PROJECT}/engagements/{engagement-id}/red-social-{topic-slug}.md` |
---
## Mandatory Authorization
> **ALL engagements MUST start with red-lead.** No other agent can operate without an active scope document.
This is the foundational security constraint for the /red-team skill. The authorization model ensures that offensive operations are structurally bounded -- out-of-scope actions are architecturally impossible, not merely procedurally discouraged.
### Authorization Flow
```
1. User requests engagement --> red-lead creates scope document
2. Scope document defines:
- engagement_id (RED-NNNN format)
- authorized_targets (IP ranges, domains, applications)
- technique_allowlist (ATT&CK technique IDs)
- time_window (start/end timestamps)
- exclusion_list (systems/networks explicitly excluded)
- rules_of_engagement (escalation procedures, communication channels)
- agent_authorizations (which agents are permitted)
- evidence_handling (stRelated in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.