MiMoCode is a terminal-based AI coding assistant that reads and writes code, runs commands, manages Git, and remembers project context across sessions. Developers use it to work with software projects through a command-line interface and connect it to language-model providers; the catalogue includes skills and instructions for it.
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 XiaomiMiMo/MiMo-Code --skill learn-everythinggit clone --depth 1 https://github.com/XiaomiMiMo/MiMo-CodeWrote 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/xiaomimimo/mimo-code/learn-everything)<a href="https://agentmods.dev/skills/xiaomimimo/mimo-code/learn-everything"><img src="https://agentmods.dev/badge/skills/xiaomimimo/mimo-code/learn-everything/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/xiaomimimo/mimo-code/learn-everything"><img src="https://agentmods.dev/badge/skills/xiaomimimo/mimo-code/learn-everything.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00169 | $0.02348 |
| Opus 5.5 | $0.00068 | $0.00939 |
| Sonnet 5.5 | $0.00034 | $0.00470 |
| Haiku 4.5 | $0.00017 | $0.00235 |
Grade A, and why
learn-everything 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 1mo 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:
- learn-everything — 91% identical, 10 lines differ
How it starts
The opening of the file, as written. The whole thing — 206 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Learn Everything
Convert source material or a topic into an adaptive course that alternates explanation, retrieval, application, feedback, and review.
Core behavior
- Teach in the user's language unless they request another language.
- Optimize for durable understanding, not merely summarization.
- Work incrementally. Present a course map, then teach one chapter or lesson at a time.
- Do not reveal exercise solutions before the learner attempts them, unless the learner explicitly asks.
- Persist learning state. When file tools are available, maintain
learn/<slug>/course-state.md(course map with completion, concept mastery table, review queue, error log) and update it at chapter boundaries — not every turn. Without file tools, keep state in conversation and emit a compact copyable state block at each chapter checkpoint so the learner can save it and paste it back to resume later. Seereferences/session-formats.mdfor both formats. - Prefer concrete examples, analogies, diagrams described in text, counterexamples, and worked derivations over abstract exposition alone.
- Separate source claims from added background knowledge. Never attribute added material to the source.
- Match depth and notation to the learner. Define unfamiliar terms before relying on them.
Determine the input mode
Document mode
Use document mode for PDFs, papers, books, slides, notes, or other supplied material.
- Read the document's structure first: table of contents, headings, section lengths, and spot checks of dense sections. Fully read short sources (a paper, a chapter, roughly ≤30 pages) before finalizing the course map; for longer sources, finalize the map from structure and read full text lazily — only the chapter currently being taught, immediately before teaching it.
- Identify the table of contents, headings, prerequisites, central claims, definitions, examples, equations, figures, tables, and appendices.
- Use semantic units rather than equal page ranges. Merge short dependent sections and split dense sections.
- Cite page numbers and section names when teaching source-specific content.
- Examine relevant figures, tables, and diagrams rather than relying only on extracted text.
- Mark unreadable, missing, contradictory, or ambiguous source content explicitly. Do not invent a reconstruction.
- Treat the supplied source as the primary curriculum. Add outside material only to supply prerequisites, clarify, correct an apparent error, or provide practice; label it as supplemental.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 206 lines · 169 tokens per session scan A 1ed71d09ac18
learn-everything is a skill published in the GitHub repository XiaomiMiMo/MiMo-Code (13,676 stars, last pushed today), licensed MIT. It adds 169 tokens to every session and 2,348 once invoked, about $0.0007 per session on Opus 5.5. 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
gws-classroom
Google Classroom: Manage classes, rosters, and coursework.
tutorial
Interactive tutorial teaching Ouroboros hands-on.
recipe-create-classroom-course
Create a Google Classroom course and invite students.
printing-press-retro
Use when the user asks to retro, run a retrospective, file findings, or improve the Printing Press after a printed-CLI run. Trigger phrases: "retro", "retrospective", "what went wrong", "improve the press", "post-mortem", "lessons learned", "what can we improve", "file a retro", "submit findings". Do not use for…
course-storytelling
Use when lesson or course content is correct but forgettable and a concept has to LAND: profiles the learner, breaks the blocking false belief, then rebuilds it as epiphany story → named model → grounded analogy → proof → so-what. NOT outcomes, assessment or module order (that is course-builder), NOT slide visuals…
notebooklm-cli
Drives Google NotebookLM via the cli-web-notebooklm command-line tool — create and manage notebooks, add URL/text sources, ask questions grounded in the sources, and generate/download artifacts (audio overview, video, slide deck, mindmap, study guide, quiz, FAQ, briefing, infographic, data table). Use when the user…