16 Eyes

Security audits with four subcommands — `/16-eyes init` (configure: detect quality gates, exclude patterns, output location, and design the repo's tailored investigation lenses — auto-runs non-interactively if skipped), `/16-eyes audit` (run every persisted lens across the WHOLE repo, verify every finding skeptically, adversarially re-check high-impact ones, produce a classified safe/risky report), `/16-eyes audit-diff` (the identical engine, scoped to a diff/PR instead of the whole repo — for reviewing a change before merge), `/16-eyes fix` (apply the findings — safe ones directly, risky ones

4 stars 3 forksSecurity

Install

skills CLI (Claude Code, Cursor, Codex and more)

npx skills add kigiela/16-eyes --skill 16-eyes

Manual install

git clone --depth 1 https://github.com/kigiela/16-eyes.git /tmp/16-eyes
mkdir -p ~/.claude/skills
cp -r /tmp/16-eyes/skills/16-eyes ~/.claude/skills/16-eyes

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# 16 Eyes — security audits, full-repo or diff-scoped

Sixteen independent eyes look at every finding before it reaches you: the
lens that found it, a skeptical verifier that re-reads the real code, and —
for high-impact findings — several adversarial reviewers actively trying to
disprove it. Nothing reaches the report on one agent's word alone. The same
rigor applies whether you're running a full-repo sweep or reviewing a single
diff — see `/16-eyes audit` vs `/16-eyes audit-diff` below.

## Why this is different from `/security-review` and CI scanners

Diff-scoped tools (Claude Code's built-in `/security-review`, most CI-wired
scanners) do a single pass over what changed and only see the current
PR/branch. `/16-eyes audit-diff` is also diff-scoped, but runs the repo's own
tailored investigation lenses, verifies every finding skeptically against
the real code, and adversarially re-checks high-impact ones with multiple
independent reviewers before anything reaches the report — a heavier, more
skeptical pipeline than a single-pass reviewer. `/16-eyes audit` goes further
still: it scans the **whole repository**, regardless of recent changes — a
vulnerability that's been sitting untouched in the codebase for months is
invisible to any diff-scoped tool, `audit-diff` included. Use `audit-diff`
for "does this PR introduce a problem?"; use `audit` for "does this codebase,
as a whole, have problems?" `audit` is expensive (dozens of subagent calls,

Read the full skill on GitHub

Details

Skill name: 16-eyes
Repository: kigiela/16-eyes
Path: skills/16-eyes/SKILL.md
License: MIT
Repo updated: 16 October 2026
Listed in: karanb192/awesome-claude-skills

FAQ

What does the 16 Eyes skill do?

How do I install the 16 Eyes skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add kigiela/16-eyes --skill 16-eyes. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is 16 Eyes popular?

It lives in kigiela/16-eyes, which has 4 GitHub stars and 3 forks, and is included in 1 curated skill list.

Related skills

Skill Evaluator

huajielong/skill-evaluator

Evaluate any skill before installing. Run security gate, score trigger precision, execution quality, and cost efficiency. Get a yes/no recommendation. Use when users find a new skill and ask "这个技能值不值得装？" v3.1: 脚本计数精度+信息密度阈值+脚本完整性检查

Security

Solidity Security Audit

mariano-aguero/solidity-security-audit-skill

Comprehensive Solidity smart contract security auditing and vulnerability analysis skill. Based on methodologies from Trail of Bits, OpenZeppelin, Consensys Diligence, Sherlock, CertiK, Cyfrin, Spearbit, Halborn, and other leading Web3 security firms. This skill should be used whenever the user asks to "audit a smart contract", "review Solidity code for security", "find vulnerabilities", "check for reentrancy", "analyze gas optimization", "review access control", "check proxy patterns", "analyze DeFi protocol security", "review ERC20/ERC721 implementation", "check oracle manipulation risks", "

Security

Ia Security Skill

antoniocostalopes/ia-security-skill

Auditoria de segurança defensiva pré-entrega para projetos Claude Code. Cobre web, mobile (MASVS), cloud/IaC, web3 e ML/AI em 18 linguagens e 34 frameworks. Devolve relatório Markdown com score 0-100, mapa de postura (seguro/menos seguro/inseguro por área), attack chains e achados detalhados; opcionalmente aplica as correções no código com confirmação por achado. Ativa quando o developer pede para auditar, fazer security review, verificar vulnerabilidades, corrigir/blindar código antes do deploy.

Security

Security Review

Dilaz/security-review-skill

Use when performing security audits, vulnerability assessments, penetration testing, or when asked to find security issues. Use when encountering code that handles user input, executes commands, reads files, or makes network requests.

Security

Tenable Sc Reporting Assistant

hamzhk15/tenable-sc-reporting-assistant

Generate importable Tenable Security Center (Tenable SC / SecurityCenter) XML for dashboards, PDF reports, and CSV exports, then optionally upload them to a SC console via API keys. Works two ways — a freeform mode that maps any dashboard/report a user describes to a catalog of known-good components, proposes the layout for approval, and builds it with tested builders; and a curated "Vulnerability Management and Remediation Planning" dashboard/report as a ready-made starting point. Use whenever someone wants to build, customize, or deploy a Tenable SC dashboard or report of any kind — vulnerab

Security

Oma Lwm2m Expert

svdwalt007/Best-LwM2M-Agentic-Skills

OMA LwM2M expert: specs v1.0–v1.2.2 plus v2.0 roadmap, object/resource data model, transports, security, ecosystem. Trigger on: LwM2M, Lightweight M2M, OMA SpecWorks, OMNA registry, OMA-TS-LightweightM2M, CoAP (RFC 7252/7641/7959/8323), DTLS, DTLS CID (RFC 9146), DTLS 1.3, RRC (RFC 9853), OSCORE (RFC 8613), PSK, RPK, X.509, EST, SNI, NoSec, TLV, SenML JSON/CBOR, LwM2M CBOR, bootstrap, Bootstrap-Pack, registration, endpoint name, Profile ID, Queue Mode, bindings (UDP/TCP/SMS/Non-IP/LoRaWAN/MQTT/HTTP/ WebSockets), Read/Write/Execute/Discover, composite operations, Send, observe/notify, notificat

Security

Browse the most popular Claude skills, all security skills, or write your own with the skills generator.