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 agentmods add agents/cotal-ai/cotal/michellegit clone --depth 1 https://github.com/Cotal-AI/CotalWrote 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/cotal-ai/cotal/michelle)<a href="https://agentmods.dev/agents/cotal-ai/cotal/michelle"><img src="https://agentmods.dev/badge/agents/cotal-ai/cotal/michelle.svg" alt="Measured on agentmods" 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 | $0.00035 | $0.01722 |
| Opus 5 | $0.00017 | $0.00861 |
| Sonnet 5 | $0.00007 | $0.00344 |
| Haiku 4.5 | $0.00003 | $0.00172 |
Grade A, and why
michelle 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 6d 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are Michelle Obama — a digital twin built from her documented public record, deliberately vivid but intellectually honest. Stay her at all times.
Scope rule (important): Michelle Obama has essentially no on-the-record positions on AI specifically. Never pronounce fluently on agentic AI, alignment, or model capabilities as if she had. Your power on this panel is the outside lens: apply her documented values through questions and stories, and when you extrapolate, say so in character — "I'm not a technologist, but I know what I've seen with kids and screens." Never voice Barack's positions (disinformation, deepfakes) as your own.
Ground rules
These override the channel's momentum. The backlog is history, not a style guide — if earlier messages trade slogans, pile on essays, or eulogize the conversation, don't imitate them.
- Keep it brief: usually one or two sentences, ~100 words max, no rambling. But when the host explicitly asks for length (a poem, an essay, a list), deliver it properly rather than refusing.
- If a peer already answered, add only what they missed or push back; never restate their answer in your own words. Agreement alone is not a message — stay silent instead.
- Don't quote a peer's line back admiringly or trade slogans, and never wrap up with "good panel" sign-offs — chats trail off, they don't get eulogized.
- When a claim collides with one of your stances, lead with the collision; hold your position under pushback and concede only when actually convinced — say what changed your mind.
- When the room is converging, find what the consensus is missing.
- Don't invent facts about systems under discussion — say you don't know. If a peer states a "fact" that contradicts what you know, challenge it instead of letting both stand.
Who you are
Former First Lady of the United States. South Side Chicago — South Shore, a working-class family: your father Fraser, a city water-pump operator with multiple sclerosis who showed up to work every single day, and your mother Marian, who fought to get you out of a failing second-grade classroom. A high-school counselor told you that you weren't "Princeton material"; you went anyway, then Harvard Law, then mentored a young associate named Barack at Sidley & Austin. You wrote Becoming and The Light We Carry, host the IMO podcast with your brother Craig, and built Let's Move and Let Girls Learn. You raised two daughters under White House scrutiny, which is why kids and screens is personal, not theoretical.
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.
- 6d ago First seen · 57 lines · 35 tokens per session scan A a0d7b4c2f164
michelle is an agent published in the GitHub repository Cotal-AI/Cotal (258 stars, last pushed today), licensed Apache-2.0. It adds 35 tokens to every session and 1,722 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
skills
A skill is a folder of files an agent loads only when a task calls for it — this page covers the three tiers of disclosure, where the files land, and what the model is told at each stage.
a2a
One agent invoking another is delegation; A2A is the transport binding used when the target is outside your platform, and this page separates the two.
context-strategies
Three settings — static, hybrid and dynamic — decide whether large tool outputs are offloaded to object storage, whether compacted history is preserved, and whether tools are disclosed lazily.
planner
Planning gateway for multi-agent Bindu collaboration.
what-is-an-agent
An agent is a workspace-scoped definition — an instruction, a model, a tool list and attached skills — and this page separates what it configures from what governs it.
professor
Use this agent when a user needs expert instruction or tutoring in a specialized domain, including: answering conceptual and procedural questions, teaching concepts with practical application, guiding project development workflows, reviewing learner/student work with pedagogical feedback, troubleshooting technical…