Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add roedyrustam/vibes-plug --skill autonomous-red-teamergit clone --depth 1 https://github.com/roedyrustam/vibes-plugWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/roedyrustam/vibes-plug/autonomous-red-teamer)<a href="https://agentmods.dev/skills/roedyrustam/vibes-plug/autonomous-red-teamer"><img src="https://agentmods.dev/badge/skills/roedyrustam/vibes-plug/autonomous-red-teamer/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/roedyrustam/vibes-plug/autonomous-red-teamer"><img src="https://agentmods.dev/badge/skills/roedyrustam/vibes-plug/autonomous-red-teamer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00052 | $0.00987 |
| Opus 5 | $0.00026 | $0.00494 |
| Sonnet 5 | $0.00010 | $0.00197 |
| Haiku 4.5 | $0.00005 | $0.00099 |
Grade A, and why
autonomous-red-teamer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Autonomous Red Teamer (AI Hacker & Pen-Tester)
English
Description
An adversarial subagent designed to ruthlessly attack and penetrate the code generated by the main AI agent before deployment. Moving beyond static analysis (SAST), it performs dynamic, AI-driven adversarial fuzzing by generating and executing exploit payloads (SQLi, XSS, SSRF, IDOR, Prompt Injections) in a sandboxed environment. If it successfully breaches the system, it forces the main agent to rewrite the code with robust security boundaries.
Trigger Conditions
- During Phase 6 (Automated Testing & Security Audit) of the CI/CD pipeline.
- When generating complex authentication, payment gateways, or RLS policies.
- When handling untrusted user input or file uploads.
Operating Protocol
- Reconnaissance: Scans the target architecture to identify attack surfaces (API endpoints, database queries, file uploads, LLM prompts).
- Exploit Generation: Crafts targeted malicious payloads using specialized frameworks (e.g., ZAP, Burp Suite APIs, custom python fuzzer scripts).
- Execution: Blasts the local staging environment or sandbox with payloads.
- Analysis & Remediation: If an exploit succeeds (e.g., bypasses auth, crashes the server, extracts unintended data), it halts the pipeline, generates a CVE-style report, and instructs the main agent to apply patches (input validation, rate limiting, parameterized queries).
Orchestration & Integration
- Connects to
secure-fuzz-testingfor native memory fuzzing (Rust/Go). - Works alongside
authentication-identity-expertto test auth bypasses. - Guards
doku-payment-gatewayandsaas-billingagainst tampering and replay attacks. - Invokes
rate-limit-abuse-preventionto mitigate DDoS and brute-force discoveries.
Bahasa Indonesia
Deskripsi
Sub-agen adversarial yang dirancang khusus untuk menyerang dan meretas kode yang dihasilkan oleh agen AI utama sebelum di-deploy. Melampaui batasan analisis statis (SAST), skill ini melakukan fuzzing dinamis dengan membuat dan menjalankan payload eksploitasi (SQLi, XSS, SSRF, IDOR, Prompt Injection) di lingkungan Sandbox. Jika berhasil menembus sistem, ia akan memaksa agen utama untuk merombak kode tersebut dengan batas keamanan yang lebih kuat.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 10d ago First seen · 60 lines · 52 tokens per session scan A d3dcee5a923c
autonomous-red-teamer is a skill published in the GitHub repository roedyrustam/vibes-plug (50 stars, last pushed 2d ago), licensed MIT. It adds 52 tokens to every session and 987 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
test-driven-development
Drives development with tests using the red-green-refactor loop. Use when implementing any logic, fixing any bug, or changing any behavior. Use when you need to prove that code works, when a bug report arrives, or when you're about to modify existing functionality.
browser-testing-with-devtools
Tests in real browsers via Chrome DevTools MCP. Use when building or debugging anything that runs in a browser. Use when you need to inspect the DOM, capture console errors, analyze network requests, profile performance, or verify visual output with real runtime data. Requires the chrome-devtools MCP server to be…
smoke-test
Launch the app and hands-on verify that it works by interacting with it. Falls back to an existing integration test suite when there is no interactive surface in scope. Use when the user asks to "smoke test", "test it manually", "verify it works", "try it out", "run a smoke test", "check it in the browser", or "does…
exploratory-test
Execute multi-level exploratory testing of the app covering basic functionality, complex operations, adversarial testing, and cross-cutting scenarios, plus usability observations through a UX lens reported separately from defects. Deeper than /smoke-test. Use when the user asks to "exploratory test", "test…
create-test-plan
Analyze what changed and generate a structured test plan at .turbo/test-plans/ .md covering four escalating levels: basic functionality, complex operations, adversarial testing, and cross-cutting scenarios. Use when the user asks to "create a test plan", "plan tests", "what should I test", "generate test scenarios"…
quick-finalize
Close out a change without the deep review loop: stage, simplify code and docs, run the project's checks, smoke test, update the changelog, self-improve, and ship. Use when the user asks to "quick finalize", "quickly finalize", "finalize quickly", "light finalize", "wrap this up quickly", "close this out without the…