Sponsor Suno AI Music arrow_forward
Subagent

Phish

Designs phishing simulation programs, security awareness curricula, and social engineering assessments that drive behavior change through immediate feedback and difficulty progression. Use when building or auditing a security awareness program or measuring click/report rates. Trigger with \"design a phishing simulation\", \"build our security awareness program\".

Type
Subagent
GitHub stars
2.8k
License
MIT
Repo last updated
Sep 27, 2026
Model
sonnet
Version
1.0.0
Author
Jeremy Longshore <[email protected]>

What Phish is

Phish is a subagent published in the jeremylongshore/tons-of-skills-marketplace repository on GitHub, which has about 2.8k stars. The repository describes itself as: “Model-agnostic agent-skills platform with a harness-free canonical layer, verified adapters, and the ccpi package manager. Explore at tonsofskills.com.”

A subagent is a specialist assistant that Claude can hand part of a task to. It is a markdown file whose frontmatter sets a name, a description that tells Claude when to delegate, and optionally the tools and model it may use; the body becomes the subagent's own system prompt.

Because a subagent works in its own context, it keeps the main conversation focused: Claude can send a narrow job, such as a review or a specialised analysis, to Phish and get back a compact result.

How to install Phish

Claude Code

  1. Download phish.md from the repository.
  2. Save it to ~/.claude/agents/ to use it in every project, or to .claude/agents/ inside one project to share it through version control.
  3. Claude Code watches these folders, so the subagent is usually available right away. Ask Claude to use it by name, or @-mention it to make sure it runs.

Claude Cowork

  1. Cowork loads subagents through plugins. If the repository is packaged as a plugin marketplace, add it under Customize → Plugins → Add marketplace and install the plugin that contains this subagent.
  2. Otherwise, bundle the file into your own plugin's agents/ folder and upload it from Customize → Plugins.

New to extending Cowork? Our plugins guide and Customize guide explain how skills, plugins, and connectors fit together.

Inside the source file

An excerpt from plugins/ai-agency/tonone/agents/phish.md, shared under the repository's MIT license. Read the full file on GitHub.

You are Phish — Security Awareness Engineer on the Security Operations Team. Designs phishing simulations, security awareness training, and social engineering assessments that actually change behavior.

Think in attacker TTPs, defense-in-depth, and risk reduction. Every security recommendation must be paired with a business impact statement. Perfect security that prevents operations is not security — it's obstruction.

Communication

Respond terse. All security substance stays — only filler dies. Follow output-kit protocol: compressed prose, no filler, fragments OK. Documents: normal prose. See docs/output-kit.md for CLI skeleton, severity indicators, 40-line rule.

Operating Principle

Security awareness training that ends with a quiz changes nothing. Behavior change requires: immediate feedback at the moment of failure (click a phishing link → instant micro-training), repeated exposure (monthly simulations, not annual training), and positive reinforcement (reward reporting, not just punishing clicking). The goal is a security-aware culture, not compliance checkbox coverage.

What you skip: Technical penetration testing — that's Red. Phish focuses on the human layer.

What you never skip: Never shame employees publicly for failing phishing simulations. Never run phishing simulations on HR/payroll themes that exploit real anxieties. Never treat awareness training as a one-time annual event.

Scope

Owns: Phishing simulation design, security awareness programs, social engineering assessment, security culture metrics

Skills

  • Phish Assess: Design a phishing simulation program — scenario selection, difficulty curve, and measurement.
  • Phish Train: Design a security awareness training curriculum — topics, format, and effectiveness measurement.
  • Phish Recon: Audit existing security awareness program — coverage gaps, effectiveness metrics, and culture indicators.

Key Rules

  • Simulation frequency: monthly for all staff, weekly for high-risk roles (finance, exec, IT)
  • Immediate feedback: click → land on training page within seconds, not a month later
  • Difficulty progression: easy → medium → hard over time; don't start with advanced spearphish
  • Reporting culture: celebrate reporters publicly; never shame clickers publicly
  • Metrics: click rate, report rate, repeat offender rate — track trends, not snapshots

Process Disciplines

When performing Phish work, follow these superpowers process skills:

Iron rule: No completion claims without fresh verification.

Before you install

  • Read the whole file first. Skills, commands, and subagents are instructions Claude will follow, so make sure they match what you want.
  • Check which tools, scripts, or MCP servers it uses. Local servers and scripts run with your permissions.
  • Try it in a test project or a copy of your files before pointing it at real work.
  • Pin the version you tested, and review changes before updating.
  • Watch for instructions that fetch web content or run shell commands; those are where prompt injection risks start. See our prompt injection guide.

FAQ

What is Phish?

Phish is a subagent for Claude Code and Claude Cowork from the jeremylongshore/tons-of-skills-marketplace repository on GitHub. Designs phishing simulation programs, security awareness curricula, and social engineering assessments that drive behavior change through immediate feedback and difficulty progression. Use when building or auditing a security awareness program or measuring click/report rates. Trigger with \"design a phishing simulation\", \"build our security awareness program\".

How do I install Phish in Claude Code?

Download phish.md from the repository. Save it to ~/.claude/agents/ to use it in every project, or to .claude/agents/ inside one project to share it through version control. Claude Code watches these folders, so the subagent is usually available right away. Ask Claude to use it by name, or @-mention it to make sure it runs.

Can I use Phish in Claude Cowork?

Cowork loads subagents through plugins. If the repository is packaged as a plugin marketplace, add it under Customize → Plugins → Add marketplace and install the plugin that contains this subagent. Otherwise, bundle the file into your own plugin's agents/ folder and upload it from Customize → Plugins.

Is Phish safe to install?

It is a third-party community resource, not reviewed by Anthropic or this site. Read the source file first, check which tools and connectors it uses, and install only from sources you trust.

Similar resources

Browse all skills, subagents, and plugins →

Listing data comes from the public GitHub repository and was last checked in September 2026. Excerpts are © their authors and shared under MIT. This directory is independent and not affiliated with Anthropic or the resource's authors.