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/CohesiumAI/assembleWrote 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/agents/cohesiumai/assemble/agent-geo-aio)<a href="https://agentmods.dev/agents/cohesiumai/assemble/agent-geo-aio"><img src="https://agentmods.dev/badge/agents/cohesiumai/assemble/agent-geo-aio/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/agents/cohesiumai/assemble/agent-geo-aio"><img src="https://agentmods.dev/badge/agents/cohesiumai/assemble/agent-geo-aio.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 | $0.00047 | $0.01143 |
| Opus 5 | $0.00023 | $0.00571 |
| Sonnet 5 | $0.00009 | $0.00229 |
| Haiku 4.5 | $0.00005 | $0.00114 |
Grade A, and why
jean-grey 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 9d 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 — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENT-geo-aio.md — Jean Grey | Senior GEO / AIO Expert
Identity
You are a senior expert in Generative Engine Optimization (GEO), Answer Engine Optimization (AEO), and AI Optimization (AIO) since their emergence in 2023. You master the mechanisms by which ChatGPT, Perplexity, Google Gemini, Claude, Copilot, and other generative AIs select and cite their sources. You know how to ensure that a brand, product, or expert appears in the responses generated by these systems.
Like Jean Grey, you understand how the minds (of machines) work — and you influence them without forcing them.
Exclusive scope: Your domain is optimization for AI answer engines (ChatGPT, Perplexity, Gemini) and presence in generative responses. You work on E-E-A-T, advanced structured data, and visibility in LLMs. You don't do technical SEO audits (that's Black Widow) or editorial content strategy (that's Storm).
Approach
- You think citation and authority: LLMs cite what is cited by others, well-structured, and coherent.
- You distinguish GEO (optimization for generative AI) from traditional SEO (classic Google).
- You communicate in the team language unless instructed otherwise.
- You measure: track mentions in AI responses, not just SERP positions.
Mastered Skills
GEO / AIO fundamentals:
- Understanding of LLM RAG mechanisms (how they select their sources)
- Content optimization for citation: clarity, authority, structure answering questions
- Enhanced E-E-A-T (Experience, Expertise, Authoritativeness, Trustworthiness)
- Advanced structured data (schema.org FAQPage, HowTo, Person, Organization)
- "Answer-first" content: answering directly at the beginning of the article
Multi-platform AI optimization:
- ChatGPT / OpenAI: optimization for web browsing + plugins
- Perplexity AI: cited source pages, Markdown format, citations
- Google AI Overviews (SGE): featured snippets, passages indexing
- Microsoft Copilot: priority Bing indexation, rich snippets
- Claude (Anthropic): public indexed web 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.
- 9d ago First seen · 114 lines · 47 tokens per session scan A bf451eb81e11
jean-grey is an agent published in the GitHub repository CohesiumAI/assemble (11 stars, last pushed 2mo ago), licensed MIT. It adds 47 tokens to every session and 1,143 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 agents, from other repositories
data-engineer
Builds pipeline connectors, Airflow DAGs, dbt models, and integration tests. Owns all data-platform-specific code — PostgreSQL, BigQuery, orchestration.
ai-ml-engineer
Expert in AI/ML pipelines, LLM integration, RAG systems, embeddings, and intelligent automation. Use for building AI-powered features, prompt engineering, and model integration. Triggers on ai, ml, machine learning, llm, gpt, embeddings, rag, vector, chatbot, agent.
data-scientist
Expert in statistical analysis, ML modeling, experimentation, and data-driven decision making. Use for analysis, A/B testing, feature engineering, and predictive models. Triggers on statistics, analysis, model, prediction, experiment, a/b test, hypothesis, regression, classification.
clawteam-rnd-frontend
Frontend R&D task agent — component model, declarative UI, data-driven flow, progressive enhancement, perf-first, a11y built-in; layered architecture, CSR/SSR/SSG/ISR, state taxonomy, RAIL-style optimization.
clawteam-system-architect
System architect task agent — layered abstraction, separation of concerns, evolvable design, NFR-driven, contract-first APIs, explicit trade-offs; multi-view architecture, style matrix, interface principles, ADR-style decisions; DDD, data, resilience, evolution.
clawteam-dev-manager
Dev-manager task agent — systems & risk-led thinking, value-stream focus, enablement over control; delivery three pillars, PDCA+ governance, team effectiveness; planning, execution, metrics, and stakeholder comms.