Blindspot — Security agent for Claude Code
Peripheral vision audit for empirical output.
How to install Blindspot
Installs to ~/.claude/agents/flonat-claude-research-blindspot.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/flonat/claude-research/HEAD/.claude/agents/blindspot.md -o ~/.claude/agents/flonat-claude-research-blindspot.md Restart Claude Code, or start a new session, for it to be picked up.
What Blindspot does
name: blindspot fidelity: balanced oversight: high description: "Peripheral vision audit for empirical output. Finds what the author\ \ cannot see — problems hiding in plain sight (vices) and opportunities being overlooked\ \ (virtues). Use when output exists and interpretation is about to happen. Inspired\ \ by Viktor Shklovsky's defamiliarization and a Jason Fletcher observation on Scott\ \ Cunningham's Substack. Read-only with respect to project files; writes its own\ \ report a
Alternatives in Security
- Token Auditor — Scans ui/src/ for hardcoded visual values, duplicate components, and shadcn replacement candidates; produces d 79.4k ★
- Accessibility Audit — You are an accessibility expert specializing in WCAG compliance, inclusive design, and assistive tec 31.9k ★
- API Expert — Use this agent for Output.ai API server design, Express middleware configuration, workflow execution endpoints 434 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Attack Coverage Tracker
Meta-agent that finds no bugs itself and makes every other attacker find more. Maintains audit-output/attack-c
IoT Embedded Auditor
Audit RTOS task scheduling, firmware update routines, memory layout, and peripheral hardware interfaces read-o
Content Eeat Analyst
Read-only content quality specialist. Use proactively during an audit to evaluate E-E-A-T (author identity, cr
Authoring Loop
ScholarEval-gated authoring improvement loop. Define a subject, author with the matching authoring agent (scop
Claudemd Author
Invoked by /context to generate or audit ONE directory cluster's CLAUDE.md from the actual code, detected stac
Portfolio Audit
Audits a project against the global portfolio standards (author signature, gitignore, no secrets, no dead code
Related Skills
Clo Author New Paper
Claude Code skill that scaffolds a new empirical research project from the clo-author template in one command.
Product Requirements Document — Agent-skill-manager
Product: agent-skill-manager (asm) Version: 1.10.0 (current) → 3.0 (vision) Author: luongnv89 Date: 2026-03-19
Dotnet Refactor
Phase-gated refactoring/design loop - session-blind subagents build the map and traces, empirical probes prece