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 code-with-rashid/agent-skillsnpx agentmods add plugins/code-with-rashid/agent-skills/marketplacegit clone --depth 1 https://github.com/code-with-rashid/agent-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/code-with-rashid/agent-skills/marketplace)<a href="https://agentmods.dev/plugins/code-with-rashid/agent-skills/marketplace"><img src="https://agentmods.dev/badge/plugins/code-with-rashid/agent-skills/marketplace.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
codewithrashid-skills marketplace 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 3d 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": "codewithrashid-skills",
"description": "Rashid Mahmood's collection of portable Agent Skills. One catalog, install any skill in Claude Code, Cursor, Codex CLI, or any Agent-Skills-compatible tool.",
"owner": {
"name": "Rashid Mahmood"
},
"plugins": [
{
"name": "mental-model",
"description": "Builds a correct, source-grounded mental model of how code actually works — instead of a confident-sounding guess.",
"source": {
"source": "git-subdir",
"url": "https://github.com/code-with-rashid/mental-model.git",
"path": "skills/mental-model"
}
},
{
"name": "adversarial-qa",
"description": "Drives a repo to measured, resumable test-hardening convergence: coverage, mutation testing, fuzzing, and load/soak, until objective thresholds are met.",
"source": {
"source": "git-subdir",
"url": "https://github.com/code-with-rashid/claude-adversarial-qa-skill.git",
"path": "skills/adversarial-qa"
}
},
{
"name": "manual-qa-loop",
"description": "Runs iterative, manual end-to-end QA on a running app — explore, fix, verify, report — until convergence.",
"source": {
"source": "git-subdir",
"url": "https://github.com/code-with-rashid/manual-qa-loop.git",
"path": "skills/manual-qa-loop"
}
},
{
"name": "understory",
"description": "Turns a codebase into an interactive HTML course the reader can actually defend — territory-mapped, self-verifying, with fieldwork in the real repo and spaced recall.",
"source": {
"source": "git-subdir",
"url": "https://github.com/code-with-rashid/understory.git",
"path": "skills/understory"
}
}
]
}
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.
- 3d ago First seen · 46 lines scan A 5e06880db580
codewithrashid-skills marketplace is a plugin published in the GitHub repository code-with-rashid/agent-skills (1 stars, last pushed 3d 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
llm-wiki
LLM-powered knowledge base from Claude Code and Codex CLI sessions. Follows Karpathy's LLM Wiki pattern.
prompt-pilot
Turns rough, vague prompts into precise, context-enriched prompts. Explores the current codebase read-only, weaves real file paths and symbols into the rewritten prompt, and never implements the task itself.
spec-driven-dev
Parallel-batch spec-driven feature workflow (spec-create, spec-implement, spec-verify, spec-checkpoint, spec-ship) plus a portable SEO/GEO operations skill (generative-seo) for any codebase.
claude-to-codex
Switch from Claude Code to Codex without losing context with one /handoff command.
sync-agents-settings
Sync MCP server configs and instructions from Claude Code to other AI agents (Gemini, Codex, Cursor, Kiro, OpenCode, Kimi, Vibe, Qwen, Amp, Cline, Windsurf).
agent-recall
Persistent memory system for AI coding agents - knows who it is, who you are, and what you were doing.