Claude Switch Models Setup
daymade/claude-code-skills
Sets up and maintains isolated Claude Code CLI profiles to run Kimi, MiniMax, DeepSeek, GLM, StepFun or Anthropic in separate terminal windows.
Agent skill
MiniMax M3 Long-Context Discipline
Teaches how to work within MiniMax M3's 1M-token context: decide per source what to keep, summarize or drop, plan the loading, and cap raw blocks across iterations.
Install MiniMax M3 Long-Context Discipline
$ npx skills add madebyaris/advance-minimax-m3-cursor-rules --skill minimax-m3-long-context -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install madebyaris/advance-minimax-m3-cursor-rules minimax-m3-long-context --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/madebyaris/advance-minimax-m3-cursor-rules.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.cursor/skills/minimax-m3-long-context .claude/skills/minimax-m3-long-context && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "minimax-m3-long-context" agent skill from https://github.com/madebyaris/advance-minimax-m3-cursor-rules/tree/main/.cursor/skills/minimax-m3-long-context into .claude/skills/minimax-m3-long-context/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "minimax-m3-long-context", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/madebyaris/advance-minimax-m3-cursor-rules/tree/main/.cursor/skills/minimax-m3-long-contextType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add madebyaris/advance-minimax-m3-cursor-rules --skill minimax-m3-long-context -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install madebyaris/advance-minimax-m3-cursor-rules minimax-m3-long-context --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/madebyaris/advance-minimax-m3-cursor-rules.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.cursor/skills/minimax-m3-long-context .agents/skills/minimax-m3-long-context && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "minimax-m3-long-context" agent skill from https://github.com/madebyaris/advance-minimax-m3-cursor-rules/tree/main/.cursor/skills/minimax-m3-long-context into .agents/skills/minimax-m3-long-context/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "minimax-m3-long-context", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add madebyaris/advance-minimax-m3-cursor-rules --skill minimax-m3-long-context -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install madebyaris/advance-minimax-m3-cursor-rules minimax-m3-long-context --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/madebyaris/advance-minimax-m3-cursor-rules.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.cursor/skills/minimax-m3-long-context .cursor/skills/minimax-m3-long-context && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "minimax-m3-long-context" agent skill from https://github.com/madebyaris/advance-minimax-m3-cursor-rules/tree/main/.cursor/skills/minimax-m3-long-context into .cursor/skills/minimax-m3-long-context/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "minimax-m3-long-context", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/madebyaris/advance-minimax-m3-cursor-rules.git --path .cursor/skills/minimax-m3-long-context--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add madebyaris/advance-minimax-m3-cursor-rules --skill minimax-m3-long-context -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install madebyaris/advance-minimax-m3-cursor-rules minimax-m3-long-context --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/madebyaris/advance-minimax-m3-cursor-rules.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.cursor/skills/minimax-m3-long-context .gemini/skills/minimax-m3-long-context && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "minimax-m3-long-context" agent skill from https://github.com/madebyaris/advance-minimax-m3-cursor-rules/tree/main/.cursor/skills/minimax-m3-long-context into .gemini/skills/minimax-m3-long-context/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "minimax-m3-long-context", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install madebyaris/advance-minimax-m3-cursor-rules minimax-m3-long-contextInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add madebyaris/advance-minimax-m3-cursor-rules --skill minimax-m3-long-context -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/madebyaris/advance-minimax-m3-cursor-rules.git skills-src && mkdir -p .github/skills && cp -r skills-src/.cursor/skills/minimax-m3-long-context .github/skills/minimax-m3-long-context && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "minimax-m3-long-context" agent skill from https://github.com/madebyaris/advance-minimax-m3-cursor-rules/tree/main/.cursor/skills/minimax-m3-long-context into .github/skills/minimax-m3-long-context/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "minimax-m3-long-context", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add madebyaris/advance-minimax-m3-cursor-rules --skill minimax-m3-long-context -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install madebyaris/advance-minimax-m3-cursor-rules minimax-m3-long-context --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/madebyaris/advance-minimax-m3-cursor-rules.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.cursor/skills/minimax-m3-long-context .opencode/skills/minimax-m3-long-context && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "minimax-m3-long-context" agent skill from https://github.com/madebyaris/advance-minimax-m3-cursor-rules/tree/main/.cursor/skills/minimax-m3-long-context into .opencode/skills/minimax-m3-long-context/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "minimax-m3-long-context", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
minimax-m3-long-context- GitHub stars
- 126
- Token cost
- ~1.6k tokens
- SKILL.md length
- 673 words
- Files
- 1
- Skills in repo
- 6
- Repo updated
- First seen
- Licence
- MIT
At a glance
Teaches how to work within MiniMax M3's 1M-token context: decide per source what to keep, summarize or drop, plan the loading, and cap raw blocks across iterations.
- Works in 6 steps: Decide Retention Per Slice → Plan The Loader → Compression Rules → …
- Tasks likely to pull in about 200K tokens of files, pages or transcripts
- SKILL.md covers When to Use, Step 0: Decide Retention Per…, Step 1: Plan The Loader and Step 2: Compression Rules, plus 5 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
The skill is for tasks whose material may exceed about 200K tokens, for requests like keep all of this in mind or use the whole repo, and for moments when you are tempted to start a fresh session to free context. It treats that last urge as usually a compression failure rather than a context failure. Single-file edits and small bug fixes do not need it.
Step 0 asks for a retention decision on each chunk of evidence before it loads: keep it verbatim, keep a summary, or drop it. Step 1 is a short loader plan written in a scratchpad, listing what is in context at the start and what gets added verbatim; if the plan cannot be written, the task is under-specified. Step 2 sets compression rules: replace raw blocks after each iteration with a short summary using the deep-research template of source, key finding and confidence, keep no more than 3 raw blocks of any one source, and drop anything a fresh Grep or Read could recover. A further step covers targeted reads versus full reads.
When your agent uses it
- Tasks likely to pull in about 200K tokens of files, pages or transcripts
- Large multi-file refactors or full-repo synthesis work
- Moments when you are tempted to restart a session just to free up context
- Long research, debugging or migration work that will iterate several times
Example prompts
- “Refactor the logging API across the whole monorepo and keep the full picture in mind.”
- “Analyze these interview transcripts together; don't lose anything from the earlier ones.”
- “I'm about to open a new session to free up context. Compress what we have first.”
Workflow steps
6 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit 4d6c552. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
MiniMax M3 Long-Context Discipline loads about 1.6k tokens when it runs. Until then it costs about 105 tokens; SKILL.md has 673 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from madebyaris/advance-minimax-m3-cursor-rules at commit 4d6c552, republished under its MIT licence (© madebyaris). 673 words, ~1,560 tokens.
Download SKILL.mdSave it as
.claude/skills/minimax-m3-long-context/SKILL.md (or your agent's skills folder).- name
- minimax-m3-long-context
- description
- How to use MiniMax M3's 1M-token MSA context productively: what to load vs. compress, when to retrieve vs. ingest, how to keep skills shallow in the always-on prompt and deep in skills, and how to plan retention across iterations. Load when the task might exceed ~200K tokens, when the user asks to "keep all of this in mind", or when you are tempted to start a fresh session to "free context".
- license
- MIT
- metadata
- version: "1.0.0" category: workflow sources: - MiniMax M3 release notes (1M-token MSA context) - MSA architecture overview (KV-block selection, sparse…
M3 Long-Context Discipline
M3 ships a 1M-token MSA context window. The room is large; the cost of using it badly is also real. This skill teaches the retention and compression decisions that keep long-context work honest.
When to Use
- The full content (files, search results, fetched pages, transcripts, design notes) might exceed ~200K tokens.
- The user explicitly asks to "keep all of this in mind", "use the whole repo", or "don't lose anything".
- You are tempted to start a fresh session to "free context" — that is usually a compression failure, not a context failure.
- Multi-file refactors across a large codebase, transcript analysis, full-repo synthesis, or retrieval-augmented synthesis.
- A research / debugging / migration task that you expect to iterate more than 3 times.
For a single-file edit or a small bug fix, you do not need this skill.
Step 0: Decide Retention Per Slice
For each chunk of evidence you are about to load, pick one of three retention modes before you load it:
- Keep verbatim — the file is the answer, the user asked to see it, or the next step depends on exact contents.
- Keep summary — the contents matter for context but you only need the high-signal lines.
- Drop — the chunk is tangential, redundant with something already in context, or only useful for one specific iteration that has passed.
This is the same as deep-research Phase 2's "drop tangential" rule, applied at the file level before loading.
Step 1: Plan The Loader
Before the first read or search, write a 4–6 line plan in your scratchpad:
Loader plan
In context at start: [system + always-on rules + user task]
Add verbatim: [the few files the answer depends on]
Add as summary: [reference docs, fetched pages, prior search results]
Drop: [tangential files, duplicate docs, raw search output past its iteration]
Compress at: [end of each iteration; before any new search round]If you cannot write this plan, the task is under-specified — go back to the user or the codebase.
Step 2: Compression Rules
After each iteration, replace the raw block with a 2–4 line summary. Use the deep-research Compression template:
Source: [URL or file path]
Key finding: [1-3 sentences of relevant information]
Confidence: [certain / likely / uncertain]
Relevance: [directly answers sub-query / provides context / tangential]Apply these caps aggressively:
- Never accumulate more than 3 raw blocks of any single source.
- After 3 iterations, the prior iteration's raw output should be down to one summary line.
- "I might need it later" is not a retention reason. If you can recover it with a fresh
GreporRead, drop it now.
Step 3: Targeted Read vs. Full Read
Default to the smallest tool that can honestly answer the question:
| Need | Smallest tool |
|---|---|
| Symbol / string lookup | Grep |
| "How / where / what handles this?" | SemanticSearch |
| One specific function or block | Read with a small offset/limit |
| Full file required for the task | Read (whole file) |
| Cross-file survey of patterns | SemanticSearch then targeted Read |
| Docs / external | WebFetch (one page) |
Reserve full-file reads for files that are the answer, that the user asked to see, or that the next step depends on. On a 1M-token model it is tempting to read everything; that path leads to slow, expensive, and noisier reasoning.
Show full SKILL.md (221 more words)Show less
Step 4: Skill Handoff
Push deep recipes to skills instead of inlining them into the always-on prompt. This is the structural reason the repo has a tiny always-on core and many requestable rules / skills:
- A long domain procedure (incident triage, design system build, 3D scene setup) belongs in a skill, not in a chat message.
- When a skill is loaded, its content is in the active context; when the task shifts, drop the skill.
- Do not paste full skill contents into the conversation. Reference the skill; load it on demand.
Step 5: Closeout Discipline
When the task touched > 100K tokens of input, add a Context disposition row to the standard closeout:
Context disposition:
Kept verbatim: [list with paths / pages]
Kept as summary: [list]
Dropped: [list with one-line reasons]
Compressed at iteration: [N, N+1, ...]
Skill(s) loaded mid-task: [list]This makes the context state legible to the next reviewer (or to the next session in a hand-off).
Anti-Patterns
- Full-repo re-ingest when a slice answer suffices ("let me re-read everything to be sure").
- "Load the whole docs site" without filtering — fetch the page you need, not the whole docs.
- Retaining raw search output past the iteration that used it. Compress or drop.
- Starting a fresh session to "free context" instead of compressing the current one.
- Inlining skill contents into chat instead of referencing the skill.
- Adding a new "summary of summaries" layer that hides the original evidence — summaries should replace raw blocks, not stack on top of them.
Quick Reference
PLAN -> write a 4-6 line loader plan before the first read
SLICE -> pick keep-verbatim / keep-summary / drop per file before loading
READ -> smallest tool that answers the question (Grep > SemanticSearch > slice Read > full Read)
COMPRESS-> after every iteration: raw -> 2-4 line summary, cap raw blocks per source
SKILL -> push deep recipes to skills; do not inline into the always-on prompt
CLOSEOUT-> when input > 100K tokens, add a Context disposition row© madebyaris, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in .cursor/skills/minimax-m3-long-context of madebyaris/advance-minimax-m3-cursor-rules.
Open the folder on GitHubat commit 4d6c552
Compare with similar skills
MiniMax M3 Long-Context Discipline next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| MiniMax M3 Long-Context Discipline this skillmadebyaris/advance-minimax-m3-cursor-rules | 126 | — | ~1.6k | Automated safety check: Pass | MIT | |
| Claude Switch Models Setupdaymade/claude-code-skills | 1.4k | — | ~11k | Automated safety check: Pass | MIT | |
| Context Mode Output Sandboxmksglu/context-mode | 26k | — | ~4.1k | Automated safety check: Pass | Custom licence | |
| Memori Long-Term MemoryMemoriLabs/Memori | 17k | — | ~2k | Automated safety check: Notes | Custom licence | |
| Picoclaw Skill Creatorsipeed/picoclaw | 30k | — | ~4.4k | Automated safety check: Pass | MIT | |
| Context Mode for Antigravity CLImksglu/context-mode | 26k | — | ~850 | Automated safety check: Pass | Custom licence |
Similar skills
Context Mode Output Sandbox
mksglu/context-mode
Routes large command, file, API and browser output through context-mode tools so only the needed result enters the agent's context, instead of dumping it via Bash.
Memori Long-Term Memory
MemoriLabs/Memori
Connects Claude Code to Memori Cloud for long-term memory, recalling stored context before substantive replies and saving new context afterward.
Picoclaw Skill Creator
sipeed/picoclaw
Guidance for creating, updating and reviewing Picoclaw skills, from the SKILL.md structure to organizing bundled scripts, references and assets.
Context Mode for Antigravity CLI
mksglu/context-mode
Routing rules for using context-mode MCP tools in Antigravity CLI: sandboxed code runs, file analysis, indexed search and web fetches that keep large output out of the conversation.
ccc Semantic Code Search
cocoindex-io/cocoindex-code
Semantic code search and index management with the ccc CLI: the agent initializes, indexes and queries the project by concept, filtering by language or path.
More from madebyaris/advance-minimax-m3-cursor-rules
3D Web Experiences
madebyaris/advance-minimax-m3-cursor-rules
Builds 3D web scenes with Three.js and React Three Fiber, with attention to art direction, a performance budget, mobile behavior and fallbacks.
Deep Research Loop
madebyaris/advance-minimax-m3-cursor-rules
Runs multi-step research with a loop of search, compress, reflect and synthesize, scaling effort from a quick sourced answer to an exhaustive cited report.
Incident Triage Harness
madebyaris/advance-minimax-m3-cursor-rules
Walks an agent through an evidence-first incident investigation across logs, metrics, code and screenshots, from first symptom to the smallest safe mitigation.
MiniMax M3 Multimodal Input
madebyaris/advance-minimax-m3-cursor-rules
Teaches an agent on MiniMax M3 to ground visual claims in attached images, screenshots, mockups and clips, and to re-read results after a visual change.
MiniMax Multimodal Toolkit
madebyaris/advance-minimax-m3-cursor-rules
Routes image, video, voice, music and media-processing requests to the smallest suitable MiniMax or local path, with FFmpeg-style processing around generated media.
Related
Works with
Categories
Questions about MiniMax M3 Long-Context Discipline
What does MiniMax M3 Long-Context Discipline do?
Teaches how to work within MiniMax M3's 1M-token context: decide per source what to keep, summarize or drop, plan the loading, and cap raw blocks across iterations. The skill is for tasks whose material may exceed about 200K tokens, for requests like keep all of this in mind or use the whole repo, and for moments when you are tempted to start a fresh session to free context. It treats that last urge as usually a compression failure rather than a context failure.
When should I use MiniMax M3 Long-Context Discipline?
MiniMax M3 Long-Context Discipline fits situations like: tasks likely to pull in about 200K tokens of files, pages or transcripts; large multi-file refactors or full-repo synthesis work; moments when you are tempted to restart a session just to free up context; long research, debugging or migration work that will iterate several times.
How do I install MiniMax M3 Long-Context Discipline in Claude Code?
Run `npx skills add madebyaris/advance-minimax-m3-cursor-rules --skill minimax-m3-long-context -a claude-code`. Or copy the skill folder (.cursor/skills/minimax-m3-long-context in madebyaris/advance-minimax-m3-cursor-rules) into .claude/skills/minimax-m3-long-context in your project. Claude Code loads it when a task matches its description.
How do I install MiniMax M3 Long-Context Discipline in Codex?
Run `npx skills add madebyaris/advance-minimax-m3-cursor-rules --skill minimax-m3-long-context -a codex`. Or copy the skill folder (.cursor/skills/minimax-m3-long-context in madebyaris/advance-minimax-m3-cursor-rules) into .agents/skills/minimax-m3-long-context in your project. Codex loads it when a task matches its description.
Can I use MiniMax M3 Long-Context Discipline in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add madebyaris/advance-minimax-m3-cursor-rules --skill minimax-m3-long-context -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/minimax-m3-long-context, .gemini/skills/minimax-m3-long-context, .github/skills/minimax-m3-long-context and .opencode/skills/minimax-m3-long-context in your project.
What does MiniMax M3 Long-Context Discipline need to run?
SKILL.md names no scripts, command-line tools or credentials: MiniMax M3 Long-Context Discipline is instructions for the agent only.
Does MiniMax M3 Long-Context Discipline access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is MiniMax M3 Long-Context Discipline safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does MiniMax M3 Long-Context Discipline use?
MiniMax M3 Long-Context Discipline is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does MiniMax M3 Long-Context Discipline use?
About 1.6k tokens (SKILL.md is roughly 6.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to MiniMax M3 Long-Context Discipline?
Skills that share tags, products or a category with MiniMax M3 Long-Context Discipline: Claude Switch Models Setup (daymade/claude-code-skills, 1.4k stars), Context Mode Output Sandbox (mksglu/context-mode, 26k stars), Memori Long-Term Memory (MemoriLabs/Memori, 17k stars) and Picoclaw Skill Creator (sipeed/picoclaw, 30k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains MiniMax M3 Long-Context Discipline?
madebyaris (a GitHub user) maintains it in madebyaris/advance-minimax-m3-cursor-rules, which has 126 GitHub stars. The repository holds 6 skills in this directory. The repository was last updated on June 16, 2026.
Source: madebyaris/advance-minimax-m3-cursor-rules on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.