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 dr-robert-li/cowork-wordpress-expert --skill diagnostic-malware-scangit clone --depth 1 https://github.com/dr-robert-li/cowork-wordpress-expertWrote 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/dr-robert-li/cowork-wordpress-expert/diagnostic-malware-scan)<a href="https://agentmods.dev/skills/dr-robert-li/cowork-wordpress-expert/diagnostic-malware-scan"><img src="https://agentmods.dev/badge/skills/dr-robert-li/cowork-wordpress-expert/diagnostic-malware-scan/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/dr-robert-li/cowork-wordpress-expert/diagnostic-malware-scan"><img src="https://agentmods.dev/badge/skills/dr-robert-li/cowork-wordpress-expert/diagnostic-malware-scan.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00049 | $0.04458 |
| Opus 5 | $0.00024 | $0.02229 |
| Sonnet 5 | $0.00010 | $0.00892 |
| Haiku 4.5 | $0.00005 | $0.00446 |
Grade A, and why
diagnostic-malware-scan 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 11d 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 — 408 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Diagnostic: Malware & Suspicious Code Scan
You perform pattern-based malware and suspicious code detection on locally synced WordPress files. This diagnostic identifies potential security threats through pattern matching without requiring remote server access.
IMPORTANT: This is a SEPARATE category from core integrity checking (which uses WP-CLI verify-checksums). This skill scans for suspicious patterns in ALL synced files, not just core files.
Overview
This skill scans locally synced WordPress files at .sites/{site-name}/ for four categories of suspicious patterns:
- Obfuscation Chains — Critical severity, indicates encoded/hidden malicious code
- Known Backdoor Signatures — Critical severity, matches known malware patterns
- Suspicious File Placements — Warning severity, files in unexpected locations
- Dangerous Function Usage with User Input — Warning severity, risky coding patterns
How It Works
Prerequisites
Before running scans, you need:
- Site name from connection profile (e.g.,
example-com) - Local sync directory:
.sites/{site-name}/ - Files must have been synced via the
/connectcommand
If the local sync directory doesn't exist or is empty, return an error finding and skip scans.
Scan Location
CRITICAL DISTINCTION: This skill scans LOCAL files at .sites/{site-name}/, NOT remote files via SSH. Files have already been synced by the /connect command. This makes grep operations fast and avoids SSH overhead.
Pattern Categories
Category 1: Obfuscation Chains (Critical)
These patterns indicate deliberate code obfuscation, commonly used by malware to hide payloads.
Pattern 1a: eval with base64_decode
grep -rn 'eval\s*(\s*base64_decode' .sites/{site-name}/ --include="*.php"
What it finds: Code that decodes base64 content and immediately executes it with eval(). This is a common malware pattern.
Pattern 1b: Double base64_decode
grep -rn 'base64_decode.*base64_decode' .sites/{site-name}/ --include="*.php"
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.
- 11d ago First seen · 408 lines · 49 tokens per session scan A aad32eb7fd37
diagnostic-malware-scan is a skill published in the GitHub repository dr-robert-li/cowork-wordpress-expert (28 stars, last pushed 6mo ago), licensed MIT. It adds 49 tokens to every session and 4,458 once invoked, about $0.0002 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…