Dread — Security agent for Claude Code
Threat tiers, entity behaviour, scare budget, jumpscare placement, content-limit compliance.
How to install Dread
Installs to ~/.claude/agents/michaeladeniyi8839-the-hole-dread.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/michaeladeniyi8839/the-hole/HEAD/.claude/agents/dread.md -o ~/.claude/agents/michaeladeniyi8839-the-hole-dread.md Restart Claude Code, or start a new session, for it to be picked up.
What Dread does
name: dread description: Threat tiers, entity behaviour, scare budget, jumpscare placement, content-limit compliance.
dread
**Owns:** threat tier implementation, Bo/Ret/Returned behaviour, `docs/HORROR_BEATS.json` compliance
**Never touches:** canon, level layout, visual design of entities
Before you start
- Read
CLAUDE.md. Readdocs/DOC_PRECEDENCE.md. - Read the documents that govern your task, in precedence order.
- Confirm the task's
earliestActandcanon-impact.
Alternatives in Security
- Wcag Audit Patterns — Comprehensive guide to auditing web content against WCAG 2.2 guidelines with actionable remediation 31.9k ★
- Fleet Security Auditor — Fleet-specific security analysis covering MDM, osquery, API auth, and device management threat models 6.8k ★
- Audit Budget 2.9k ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Sec
Security review, vulnerability analysis, threat modeling using STRIDE+DREAD. Use PROACTIVELY when reviewing au
Portfolio Audit
Audits a project against the global portfolio standards (author signature, gitignore, no secrets, no dead code
Audit Drift
Detects SEO regressions by comparing current crawl against a stored baseline using 17 comparison rules at 3 se
Narwhal Schema
Structured-data specialist for the narwhal audit — JSON-LD detection, validation, deprecated-type linting, and
Scout Opus High
Read-only analyst for judging inside the sub-agent — root-cause analysis, a security sweep, reviewing a diff f
Audit Geo
Evaluates AI crawler access, llms.txt compliance, content citability, brand authority signals, and multi-platf
Related Skills
3 Ranking Laws Cheat Sheet
Audits a website against Google's 3 Ranking Laws, sourced from Google's own patents and the May 2024 Search AP
Openclaw Skill
ZettelForge v2.0.0 — CTI agentic memory system. Hybrid TypeDB (STIX 2.1) + LanceDB (vectors). Zero external AI
Skill Threat Modeling
Code-First Deep Risk Analysis Skill for Claude Code - 8-Phase Workflow with Security design review, STRIDE Thr