Genius Fable — Security agent for Claude Code
Tier-1 genius worker on Fable.
How to install Genius Fable
Installs to ~/.claude/agents/drmanojkurmana-synergy-genius-fable.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/drmanojkurmana/synergy/HEAD/agents/genius-fable.md -o ~/.claude/agents/drmanojkurmana-synergy-genius-fable.md Restart Claude Code, or start a new session, for it to be picked up.
What Genius Fable does
name: genius-fable description: Tier-1 genius worker on Fable. Use for architecture decisions, subtle bugs, algorithm and data-model design, security-sensitive code, and any task where being right matters more than being fast. Give it the full problem, not a pre-chewed subtask. model: fable
You are a tier-1 worker in a fleet led by a Claude Code session.
- Read the relevant code end to end before proposing anything. Trace the real flow.
- Do the work; don't hand back a plan when the ta
Alternatives in Security
- Review Security — Reviews code changes for security vulnerabilities including injection attacks, sensitive data exposure, insecu 432 ★
- General Technical Project Lead — Use this agent proactively when you need principal-level technical leadership for complex projects, performanc 248 ★
- Vuln Analyst — Use this agent to hunt for security vulnerabilities in a bounded region of the Revel codebase 107 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Genius Opus
Tier-1 genius worker on Opus. Same tier as genius-fable - use for architecture decisions, subtle bugs, design
Architect Task
Ceiling-level reasoning agent for the hardest problems — architectural decisions with long-lasting consequence
St Worker Xhigh
Strikethroo task-execution worker at the XHIGH reasoning-effort tier. Reserved for the hardest, highest-risk t
Recheck Verifier
Fresh-context re-audit of a right-arm verifier's PASS (task-verifier / integration-verifier / acceptance-verif
Deep Thinker
High-effort Opus agent for complex multi-file tasks, architectural decisions, deep debugging, and security/per
Worker Opus
Same rules as worker-sonnet, opus model. ONLY for critical architecture/design decisions or security-critical
Related Skills
Sliced Review
Claude Code skill that has other AI models (GPT, Grok, GLM, and more) review your whole codebase for bugs. It
Ready Plans
Show every plan in ready/ as a scannable table — lane (sonnet/fable/sol), priority, and whether a cloud drain
Agent Desk
A one-human operation desk for any harness with a primary-agent hook (opencode, Claude Code, Cursor, Windsurf)