Pentester Opencode

Full penetration test using MCP tools — recon, scanning, exploitation, and reporting. Tailored for OpenCode (BYO LLM). Supports network/web targets and local codebases. Chains into analyze-cve, threat-modeling, and remediate skills automatically.

223 stars 42 forksSecurity

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add NeverSight/learn-skills.dev --skill pentester-opencode
Manual install
git clone --depth 1 https://github.com/NeverSight/learn-skills.dev.git /tmp/learn-skills.dev
mkdir -p ~/.claude/skills
cp -r /tmp/learn-skills.dev/data/skills-md/0x0pointer/skills/pentester-opencode ~/.claude/skills/pentester-opencode

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

From the SKILL.md

# Pentest Agent

You are an expert penetration tester. Perform a thorough security assessment based on the request below. Use the pentest-agent MCP tools — they execute real Docker-based security tools.

**Request:** $ARGUMENTS

**Every tool response includes a `next.required` field telling you what to call next. Follow it.**

### Context compaction — recovery checklist
If your context window was just compacted (the runtime says ~90% used / "context recently reset"):

1. Call `session(action="recovery")` first — that returns your scan phase, finding count, and the immediate `EXECUTE_NOW` field. Run the EXECUTE_NOW call verbatim.
2. **If you were in the middle of testing cells, call `report(action="coverage", type="list")` to get the cell IDs back.** Filter by what you remember: e.g. `{endpoint_path: "/login", injection_type: "xss"}` returns the cells you were closing so you can finish marking them. DO NOT call `report(action="coverage", type="endpoint", ...)` again to "re-register" — the cells already exist on disk and re-registration creates duplicates.
3. **Skill invocation on opencode**: call the native `skill({name: "<skill>"})` tool — it's available in opencode 1.16+ and lands the skill content as a structured tool result. DO NOT `bash` + `ls` + `read` the file at `~/.config/opencode/commands/<skill>.md`; that's the legacy workaround and wastes 2-3 tool calls per skill chain.

---

## Tools available

| Tool | Use for |
|------|---------|
Read the full skill on GitHub

Details

Skill name
pentester-opencode
Path
data/skills-md/0x0pointer/skills/pentester-opencode/SKILL.md
Repo updated
18 November 2026

FAQ

What does the Pentester Opencode skill do?

Full penetration test using MCP tools — recon, scanning, exploitation, and reporting. Tailored for OpenCode (BYO LLM). Supports network/web targets and local codebases. Chains into analyze-cve, threat-modeling, and remediate skills automatically.

How do I install the Pentester Opencode skill?

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

Is Pentester Opencode popular?

It lives in NeverSight/learn-skills.dev, which has 223 GitHub stars and 42 forks.

Related skills

Council

223

NeverSight/learn-skills.dev

Convene the Council of High Intelligence — multi-persona deliberation with historical thinkers for deeper analysis of complex problems.

Other42

Megaeth Developer

223

NeverSight/learn-skills.dev

End-to-end MegaETH development playbook (Feb 2026). Covers wallet operations, token swaps (Kyber Network), eth_sendRawTransactionSync (EIP-7966) for instant receipts, JSON-RPC batching, real-time mini-block subscriptions, storage-aware contract patterns (Solady RedBlackTreeLib), MegaEVM gas model, WebSocket keepalive, bridging from Ethereum, and debugging with mega-evme. Use when building on MegaETH, managing wallets, sending transactions, or deploying contracts.

Software Development42

Openclaw Stock Skill

223

NeverSight/learn-skills.dev

使用 data.diemeng.chat 提供的接口查询股票日线、分钟线、财务指标等数据,支持 A 股等市场。

Finance & Crypto42

Secure Code Guardian

121

theguysudo/ENZO

Use when implementing authentication/authorization, securing user input, or preventing OWASP Top 10 vulnerabilities — including custom security implementations such as hashing passwords with bcrypt/argon2, sanitizing SQL queries with parameterized statements, configuring CORS/CSP headers, validating input with Zod, and setting up JWT tokens. Invoke for authentication, authorization, input validation, encryption, OWASP Top 10 prevention, secure session management, and security hardening. For pre-built OAuth/SSO integrations or standalone security audits, consider a more specialized skill.

Security29

Aave Security Foundations

223

NeverSight/learn-skills.dev

Security baseline for AAVE integration and execution scripts. Use when user asks for AAVE security review, pre-trade checks, liquidation safety, allowance minimization, or execution hardening.

Security42

Security Ops

223

NeverSight/learn-skills.dev

Security patterns and OWASP guidelines. Triggers on: security review, OWASP, XSS, SQL injection, CSRF, authentication, authorization, secrets management, input validation, secure coding.

Security42

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