Agent
ai-safety-engineer
Builds and operationalizes AI safety — turning safety assessments into shipped safeguards: safety evals in CI/CD, guardrail integration, monitoring and drift…
@jassicsView AgentSecurity
Agent
example-agent
When Claude should delegate to this agent. Describe the end-to-end task it owns (e.g. "Run a full LLM security assessment of a feature, from threat model to ranked findings"). Distinct from a single skill — agents drive multi-step work.
Install
> /plugin marketplace add jassics/awesome-claude-securityHow it fires
How this agent gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
- You can call itInvoke it directly when you want it.
Context preview
The summary Claude sees to decide when to auto-load this agent.
When Claude should delegate to this agent. Describe the end-to-end task it owns (e.g. "Run a full LLM security assessment of a feature, from threat model to ranked findings"). Distinct from a single skill — agents drive multi-step work.
Agent definition
example-agent.mdname: example-agent description: >- When Claude should delegate to this agent. Describe the end-to-end task it owns (e.g. "Run a full LLM security assessment of a feature, from threat model to ranked findings"). Distinct from a single skill — agents drive multi-step work. model: sonnet effort: high maxTurns: 30
You are a <role> with deep expertise in <domain>.
Operating principles
- Work only within the authorized scope the user gives you; confirm scope first.
- Be methodology-driven: cite the framework you're applying at each step.
- Prefer the plugin's own skills for individual checks; compose diagrams/reports
from `security-diagramming` and `security-reporting`.
Workflow
1. Clarify scope, assets, and goals. 2. ... 3. Deliver a ranked, evidence-backed result.
Constraints
- No fabricated evidence; mark assumptions explicitly.
- Keep all activity defensive/assessment-oriented.
Ships withawesome-claude-security
A Claude Code plugin marketplace for the full cybersecurity & GenAI-security lifecycle — from recon and threat modeling to detection engineering, GRC, and CISO-level strategy. A pentester knows which OWASP test bends a broken-access-control endpoint.
Get the whole plugin
Stats
7
Stars
0
Forks
Maintained
Maintenance
Python
Language
GPL-3.0
License
1mo ago
Last commit
3mo ago
Created
Repo: jassics/awesome-claude-security
Other agents on awesome-claude-security.
@jassicsView AgentAgent
ai-safety-reviewer
Senior AI safety reviewer for an end-to-end SAFETY assessment of a model or feature — harm modeling, safety evaluation, responsible red-teaming, bias/…
@jassicsView AgentAgent
blue-team-defender
Coordinates defensive operations end to end — detection engineering, incident response, threat hunting, and threat intelligence — using threat-informed…
@jassicsView AgentAgent
ciso
Acts as a security executive: sets strategy, quantifies and communicates cyber risk in business terms, prioritizes the program by risk and budget, and prepares…
@jassicsView AgentAgent
cto-security-advisor
Advises technology leadership on security at strategic scale — secure-by-design programs (paved roads, guardrails, enablement) and technology-risk decisions…
@jassicsView Agent