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 PHPCraftdream/rust-intelnpx agentmods add plugins/phpcraftdream/rust-intel/marketplacegit clone --depth 1 https://github.com/PHPCraftdream/rust-intelGrade A, and why
rust-intel 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
{
"name": "rust-intel",
"owner": {
"name": "Marat K",
"email": "[email protected]"
},
"description": "Marketplace for the rust-intel plugin — a living specification defending against the systematic mistakes LLMs make when writing Rust.",
"plugins": [
{
"name": "rust-intel",
"source": "./",
"description": "Defense against LLM Rust failure modes: 58 categories of bugs that survive rustc, clippy, and cargo test. Ships the rust-intel skill (auto-activates on Rust tasks) plus /rust-intel:audit, /rust-intel:fix, /rust-intel:plan commands and a fan-out project-audit workflow.",
"category": "development",
"tags": ["rust", "code-review", "audit", "correctness", "security", "performance"],
"license": "MIT OR Apache-2.0",
"repository": "https://github.com/PHPCraftdream/rust-intel"
}
]
}
What ships with it
1 file beside marketplace.json in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 20 lines scan A 733220d73281
rust-intel is a plugin published in the GitHub repository PHPCraftdream/rust-intel (1 stars, last pushed 13d ago), licensed Apache-2.0. 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
radar-suite
Six-skill audit suite for iOS/Swift codebases with 3-axis classification framework.
radar-suite
Six-skill audit suite for iOS/Swift codebases: data models, UI paths, data round-trips, time bombs, visual quality, and capstone grading. As of v2.0 every finding is classified on a 3-axis framework (real bug / scatter / dead code) with mandatory coaching citations to patterns in the audited codebase.
api-authentication
Secure API authentication with JWT, OAuth 2.0, API keys. Use for authentication systems, third-party integrations, service-to-service communication, or encountering token management, security headers, auth flow errors.
wio
Testing workflow skill for high-value test discovery, strategy selection, focused implementation, realistic workload generation, strict review, and suite health diagnostics.
firecrawl-lean
Plugin marketplace listing 1 plugin: firecrawl-lean.
flutter-agentic
Plugin marketplace listing 1 plugin: flutter-agentic.