Security commands

ab604/claude-code-r-skills

Command

Review code for security, quality, and best practices. Use after writing code and before committing.

kid-sid/claude-spellbook

Command Claude Code

Deliver a brutally honest, technically sharp roast of the current repository. Spot real bugs, code smells, security holes, and engineering sloppiness. Be pointed and witty, but every finding must be accurate and include a fix.

databricks-industry-solutions/security-analysis-tool

Command Claude Code

A new security check row has been added to configs/securitybestpractices.csv. Implement it end-to-end by following these steps in order.

mlunato47/claude-grc-plugin

Command

Authorization boundary definition guidance.

mlunato47/claude-grc-plugin

Command

Look up controls by framework and ID or keyword.

mlunato47/claude-grc-plugin

Command

Model control inheritance based on service model and provider stack.

enspirit/elo

Command Claude Code

Tracks security issues in compiled code and compiler API.

The-17/agentsecrets

Command

Command "call" from The-17/agentsecrets, covering agentsecrets call, usage, description, options and examples.

The-17/agentsecrets

Command

Command "env" from The-17/agentsecrets, covering agentsecrets env, usage, makefile integration, pattern 1: run prefix variable (recommended) and pattern 2: named targets (explicit).

wbern/agent-instructions

Command Claude Code

Audit commit-hook automation as gates against AI slop and broken commits (Node.js, Go, polyglot).

Owl-Listener/ai-design-skills

Command

Create a complete guardrail specification for an AI feature.

Owl-Listener/ai-design-skills

Command

Run a structured red-teaming exercise to find alignment failures.

DataDog/pathfinding.cloud

Command Claude Code ✓ vendor

Creates pathfinding.cloud attack paths by gathering requirements, building YAML, and coordinating enrichment agents.

alfredolopez80/multi-agent-ralph-loop

Command Claude Code

Revisa un PR de GitHub (por URL o número, en CUALQUIER repo) con múltiples agentes en paralelo — code review por área, seguridad, consistencia de contrato, rendimiento, tests y auditoría de comentarios de revisores — verifica cada hallazgo contra el código real y guarda un consolidado. Nunca comenta en el PR; eso es…

ADScanPro/Claude-AD

Command

Launch the ad-attack-planner agent to reason low-privilege-to-Domain-Admin paths from the collected inventory and BloodHound CE graph, then present the plan for human approval before any exploitation.

ADScanPro/Claude-AD

Command

Launch the ad-enumerator agent to run the collection phase against the defined scope, producing a structured AD inventory (users, groups, SPNs, ACLs, ADCS templates, trusts) plus a BloodHound CE graph.

ADScanPro/Claude-AD

Command

Define and record the scope of an authorized Active Directory engagement (domain(s), DC IP, initial credentials, and what is in scope) into a scope file the other AD commands read.

wellwelwel/lagune

Command

Detect what the system actually does by reading the code, and map the security-relevant findings (login, uploads, payments, data exposure, and so on) with the evidence later phases need. Scans the whole project, named files, or a focused scope.

wellwelwel/lagune

Command

Apply the defense plan's fixes to the code, safely and one at a time, then record what was applied and what is left. Reads the plan and the charter, then hardens every fix, the fixes, files, or directories you name, or a priority you choose.

wellwelwel/lagune

Command

Prove detected findings with runnable, defense-only evidence. For each finding the detect map carries, it writes a safe-path JavaScript test and a self-contained advisory under .lagune/proofs/. The test asserts secure behavior, never an exploit.

coleam00/dark-factory-experiment

Command

Pass-2 variant of dark-factory-synthesize-verdict. Reads -p2 node outputs (post-fix). Aggregates behavioral, security, code review, and static check results into an approve/requestchanges/reject verdict.

coleam00/dark-factory-experiment

Command

Final arbiter for Dark Factory PR validation. Aggregates behavioral, security, code review, and static check results into an approve/requestchanges/reject verdict.

senaiverse/reactnative-expo-ai-agent-system-workflow

Command

Comprehensive multi-agent code review covering design, accessibility, security, performance, and testing.

NeoTheCapt/RedteamAgent

Command

You are the operator managing authentication credentials for the current engagement. The user's arguments specify the auth type and value.