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.
/plugin marketplace add morodomi/redteam-skillsnpx agentmods add plugins/morodomi/redteam-skills/redteam-coregit clone --depth 1 https://github.com/morodomi/redteam-skillsWrote 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/plugins/morodomi/redteam-skills/redteam-core)<a href="https://agentmods.dev/plugins/morodomi/redteam-skills/redteam-core"><img src="https://agentmods.dev/badge/plugins/morodomi/redteam-skills/redteam-core.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
redteam-core 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 4d 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.
What it actually says
{
"name": "redteam-core",
"description": "Security audit automation. RECON → SCAN → ATTACK → REPORT",
"author": {
"name": "morodomi"
},
"repository": "https://github.com/morodomi/redteam-skills",
"license": "MIT"
}
What it installs
The manifest is a name and a version. 4 skills, 18 agents travel with it, and installing the plugin installs all of them — 695 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill context-review A 35 tokens
- Skill security-scan A 33 tokens
- Skill generate-e2e A 22 tokens
- Skill attack-report A 20 tokens
- Agent attack-scenario A 35 tokens
- Agent wordpress-attacker A 36 tokens
- Agent csrf-attacker A 35 tokens
- Agent dast-crawler A 32 tokens
- Agent xxe-attacker A 30 tokens
- Agent error-attacker A 28 tokens
- Agent injection-attacker A 32 tokens
- Agent sca-attacker A 31 tokens
- Agent ssti-attacker A 32 tokens
- Agent xss-attacker A 34 tokens
- Agent api-attacker A 33 tokens
- Agent auth-attacker A 37 tokens
- Agent crypto-attacker A 32 tokens
- Agent file-attacker A 28 tokens
- Agent recon-agent A 34 tokens
- Agent false-positive-filter A 27 tokens
- Agent dynamic-verifier C 36 tokens
- Agent ssrf-attacker C 33 tokens
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.
- 4d ago First seen · 10 lines scan A ced87ff4e20e
redteam-core is a plugin published in the GitHub repository morodomi/redteam-skills (2 stars, last pushed 6mo ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-08-31.
Other plugins, from other repositories
websec
Web application security review skills: architecture recon, 33 vulnerability-class detectors, and a consolidated severity-ranked report.
airtight
Secure-coding gates for AI-written code. 70 numbered gates mapped to OWASP Top 10 and CWE, plus a pre-write guard that denies the failures it can prove: open routes, IDOR, missing CSRF tokens, interpolated queries and shell commands, raw HTML sinks, unverified webhooks, any-origin CORS with credentials, passwords…
secure-coding
OWASP Top 10:2025 rules for writing and reviewing backend/API code in any language, plus /api-secure-report — a full security inventory of every HTTP route in a project.
vuln-scout
Claude Code plugin for whitebox security review. Stable: deterministic offline quick scan, shared findings.json with stable keys and hotspot-aware findings, SARIF/Markdown/HTML/bundle reports, suppressions, CI fail-on gate, Kuzushi parity. Beta: deep profile with Joern/CodeQL/Slither/Trivy/Checkov when installed.…
vantage
Artifact-driven, plugin-based multi-agent SAST pipeline for web and mobile app repositories. Web agents cover the OWASP Top 10; mobile agents cover the OWASP Mobile Top 10 (2024, M1-M10). Both share global validation/PoC/reporting agents. Run /vantage:scan-web or /vantage:scan-mobile to scan, then /vantage:fix-issue…
deep-security-audit
Multi-agent security audit that reads and understands code, adversarially verifies every finding, and scores honest CVSS 3.1. Read-only by default.