Skill Claude CodeCodex
Skill "harness" from xwtro0tk1t-cloud/harness, covering harness: project development scaffold meta-skill, workflow (7 steps), step 1: project analysis, step 4: agent team design (interactive) and step 6: planning infrastructure.
Skill Claude CodeCodex
This skill provides three primary modes for Android security testing.
Skill Claude CodeCodex
Dispatch an independent challenger agent to adversarially review a spec or implementation plan against the actual codebase. Catches hallucinated APIs, wrong field names, nonexistent files, and incorrect assumptions. Two modes: (1) spec review — verifies DB model fields, API paths, config attributes, file paths…
Skill Claude CodeCodex
Graph-driven project understanding using code-review-graph (CRG). Query architecture, modules, callers/callees, impact radius, hotspots, execution flows, and search nodes. Use when: (1) brainstorming and need to understand project structure, (2) writing plans and need impact analysis, (3) user says "understand this…
Skill Claude CodeCodex
Manage code knowledge graphs via code-review-graph (CRG). Build, update, and check status of project code graphs stored in .code-review-graph/graph.db. Use when: (1) user says "build graph", "update graph", "graph status", "/graph", (2) Harness init detects CRG, (3) preparing to use /explore commands. Gracefully…
Skill Claude CodeCodex
Skill "harness-audit" from xwtro0tk1t-cloud/harness, covering harness audit — project health check, behavior, checklist, a. infrastructure (max 25 points) and b. skill ecosystem (max 30 points).
Skill Claude CodeCodex
Skill "harness-cleanup" from xwtro0tk1t-cloud/harness, covering harness cleanup — interactive temp file archive, behavior, scan scope & exclusions, scan scope and static exclusion list.
Skill Claude CodeCodex
Skill "harness-guide" from xwtro0tk1t-cloud/harness, covering harness guide — skill recommendation, behavior, matching logic, scenario keywords → skill mapping and output format.
Skill Claude CodeCodex
Skill "harness-handoff" from xwtro0tk1t-cloud/harness, covering harness handoff — deep context transfer, behavior, difference from claude code default behavior, read-tool steps (1-5, deterministic file reads) and step 1: claude.md.
Skill Claude CodeCodex
Skill "harness-help" from xwtro0tk1t-cloud/harness, covering harness help — command index & scenario quick reference, behavior, command index, installed skills inventory and high-frequency scenarios.
Skill Claude CodeCodex
Skill "harness-quality-gate" from xwtro0tk1t-cloud/harness, covering harness quality gate — pre-commit quality check, check levels, check items, 1. tests pass and 2. lint passes.
Skill Claude CodeCodex
Skill "harness-resume" from xwtro0tk1t-cloud/harness, covering harness resume — lightweight context recovery, behavior, steps, step 1: taskplan.md phase anchor and step 2: memory.md best-match.
Skill Claude CodeCodex
An AI-assisted review of software-component vulnerability scans from tools such as Grype, Snyk, and Xray. It groups findings by urgency from P0 to P3 and filters out lower-impact results.
Skill Claude CodeCodex
A generator for security-review skills tailored to a project, programming language, or framework. It can create audit rules from project documentation or reference materials.
Agent
Agent "security_grader" from xwtro0tk1t-cloud/harness, covering security grader, 评估方法, 输入, 评估指标 and 核心指标.
Skill Claude CodeCodex
A security audit for Docker and container deployment files, including Dockerfiles, Docker Compose files, Kubernetes YAML, and Helm charts. It checks for issues such as root or privileged containers, exposed secrets, unsafe mounts, missing resource limits, and risky network settings.
Skill Claude CodeCodex
A security checker for Terraform and related infrastructure-as-code files that describe AWS cloud resources. It looks for unsafe settings in HCL, Terraform JSON, tfvars, and Terragrunt files.
Skill Claude CodeCodex
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, update or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
Agent
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
Agent
Compare two outputs WITHOUT knowing which skill produced them.
Agent
Evaluate expectations against an execution transcript and outputs.
Skill Claude CodeCodex
Audit AI Agent skills for security vulnerabilities including malicious code, remote execution, credential leaks, and supply chain risks. Use when reviewing third-party skills, investigating suspicious behavior, or performing security assessments.
Skill Claude CodeCodex
A supply-chain security checker for detecting malicious changes in software dependencies across several programming languages. A supply-chain attack hides harmful behavior in packages, build steps, or installation scripts.
Skill Claude CodeCodex
Claude Code (你就是 LLM) │ ├─ 简单任务 → 直接处理 │ ├─ HTTP Client → XSS, IDOR 验证 │ └─ Playwright → DOM XSS, CSRF, Open Redirect │ └─ 复杂任务 → CAI Agent │ ├─ 11 Agents (bugbounty, redteam, blueteam...) ├─ MCP Bridge (executecommand → 59 Kali tools) └─ HexStrike Docker (localhost:8888).