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 cass-2003/local-workflow-skillnpx agentmods add plugins/cass-2003/local-workflow-skill/aeogit clone --depth 1 https://github.com/cass-2003/local-workflow-skillGrade A, and why
aeo 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 2d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- aeo — 100% identical, 0 lines differ
What it actually says
{
"name": "aeo",
"description": "Answer Engine Optimization (AEO) skill — optimize content to be cited by AI language models (ChatGPT, Perplexity, Claude, Gemini, Mistral) as authoritative sources. Distinct from SEO (which optimizes for search rankings), AEO optimizes for citation in LLM-generated responses. Ships 3 stdlib Python tools (aeo_audit.py for E-E-A-T + structure scoring, aeo_optimizer.py for content rewriting in conservative/balanced/aggressive modes, citation_tracker.py for local-first citation ledger), 3 references citing 7+ authoritative sources each (E-E-A-T methodology, per-LLM citation patterns, AEO-vs-SEO strategy), and industry-aware thresholds for 8 industries (saas/healthcare/finance/legal/ecommerce/b2b/media/education) with stricter YMYL calibration. Triggers — 'AEO audit', 'optimize for ChatGPT', 'get cited by Perplexity', 'E-E-A-T audit', 'LLM citation strategy', 'answer engine optimization'.",
"version": "2.9.0",
"author": {
"name": "Alireza Rezvani",
"url": "https://alirezarezvani.com"
},
"homepage": "https://github.com/alirezarezvani/claude-skills/tree/main/marketing-skill/skills/aeo",
"repository": "https://github.com/alirezarezvani/claude-skills",
"license": "MIT",
"skills": ["./"],
"source": {
"upstream": "https://github.com/alirezarezvani/aeo-box/tree/main/answer-engine-optimization",
"upstream_version": "1.0.0",
"build_pattern": "Port from aeo-box answer-engine-optimization/ skill (9 modules, 2,464 LOC). Distilled into 3 stdlib CLI tools per claude-skills convention. Preserves E-E-A-T scoring methodology, citation-tracking schema, and industry-aware thresholds. Adds cs-aeo agent + /cs:aeo command + 3 references citing 8 sources each.",
"distinct_from": "marketing-skill/skills/seo-audit (traditional click-through SEO) — AEO and SEO complement, not substitute. Both can run on the same content."
}
}
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.
- 2d ago First seen · 20 lines scan A 350d7eee34c6
aeo is a plugin published in the GitHub repository cass-2003/local-workflow-skill (12 stars, last pushed 1mo 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 2026-08-30.
Other plugins, from other repositories
omnisocials
Manage social media across 11 platforms: create, schedule, and publish posts, stories, and reels, upload media, read and reply to your social inbox, track analytics, and configure webhooks via the OmniSocials API.
gtm-skills
Audit sales call transcripts and CRM exports against GTM rubrics — deal stage, initiative frameworks (MEDDICC, BANT), industry vertical context. Every finding cites a quote. Runs locally, no credentials.
enablement-crm-pack
CRM workflow bundle with reusable context, account planning, deal inspection, forecasting, and renewals.
post-generator
Drafts per-platform copy from a sourced angle in your captured voice, decides how the post breaks into frames, and lists what it refused to claim and why. Never publishes.
pwdev-copy
Framework de copy genérico e treinável — um arquivo de contexto define marca, ICP e voz, e 20 skills cobrem o ciclo completo: pesquisa VOC, brand voice, criação (landing, social, ganchos, reaproveitamento), revisão em 7 sweeps com anti-slop, e camada de análise que fecha o loop (perf-analyzer, perf-patterns…
jobops-ic
Independent contractor toolkit - services, client prospecting, pitch decks, proposals, rate cards, landing pages. Requires jobops.