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.
git clone --depth 1 https://github.com/Security-Phoenix-demo/security-skills-claude-codeWrote 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/security-phoenix-demo/security-skills-claude-code/phoenix-security-review)<a href="https://agentmods.dev/plugins/security-phoenix-demo/security-skills-claude-code/phoenix-security-review"><img src="https://agentmods.dev/badge/plugins/security-phoenix-demo/security-skills-claude-code/phoenix-security-review/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/plugins/security-phoenix-demo/security-skills-claude-code/phoenix-security-review"><img src="https://agentmods.dev/badge/plugins/security-phoenix-demo/security-skills-claude-code/phoenix-security-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
phoenix-security-review 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 yesterday.
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
{
"$schema": "https://www.schemastore.org/claude-code-plugin-manifest.json",
"name": "phoenix-security-review",
"version": "1.0.0",
"description": "AppSec review suite: multi-language security-reviewer (8-point check, 7 language packs, OWASP/ASVS + endpoint checklists), whole-repo security-assessment, diff-scoped 0day-scanner, STRIDE/DREAD threat-modeling, and two threat-model-driven tiers (tm-quick-security-assessment, tm-security-review). Ships 4 slash commands, a security-reviewer subagent, and 3 opt-in hooks.",
"author": { "name": "Phoenix Security", "email": "[email protected]", "url": "https://phoenix.security" },
"homepage": "https://github.com/Security-Phoenix-demo/security-skills-claude-code",
"repository": "https://github.com/Security-Phoenix-demo/security-skills-claude-code",
"license": "MIT",
"keywords": ["security", "appsec", "owasp", "asvs", "threat-modeling", "stride", "code-review", "sast", "zero-day"]
}
What it installs
The manifest is a name and a version. 6 skills, 4 commands, 1 agent travel with it, and installing the plugin installs all of them — 1,038 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill security-assessment A 152 tokens
- Skill threat-modeling A 97 tokens
- Skill 0day-scanner A 130 tokens
- Skill security-reviewer A 185 tokens
- Skill tm-security-review A 146 tokens
- Skill tm-quick-security-assessment A 125 tokens
- Command security-review A 30 tokens
- Command security-audit A 22 tokens
- Command threatmodel A 19 tokens
- Command security-0day A 24 tokens
- Agent security-reviewer A 108 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.
- yesterday First seen · 12 lines scan A 77a7552dcda9
phoenix-security-review is a plugin published in the GitHub repository Security-Phoenix-demo/security-skills-claude-code (70 stars, last pushed yesterday), 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 2026-09-11.
Other plugins, from other repositories
han-communication
Foundational communication plugin for the Han suite. Owns the canonical readability standard, the writing-voice profile, and the explanation standard for talking to a reader who will not implement the work, plus the readability-guidance skill that surfaces the first two into a calling skill's own context for in-voice…
ai-infra-auto-driven-skills
Agent-ready playbooks for LLM serving benchmarks, SGLang model Day-0 support, capacity planning, profiling, SGLang/vLLM SOTA loops, code review, incidents, and PR-history dossiers.
peer-review
Cross-model peer review of plans, specs, and the decisions a session has just made: a harness-agnostic deliberation protocol (challenge packet with GIVEN-tagged context, challenger findings that each carry their own falsifier, evidence-backed responses at a stable locator, a verbatim ledger, a certification pass the…
git-pr
Committing, PR creation and review triage, and dependency upgrades.
code-quality
OxLint, Biome, and Prettier configuration, linting skills, and pre-commit hooks for consistent code quality.
coderabbit
CodeRabbit integration for Claude Code - local code review and PR comment management.