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.
A skill your agent uses when working with this machine's local LLM setup (LM Studio + mlx-dspark) -- checking status, changing context window, diagnosing a reasoning hang or dead request…
Install Local LLM
$ npx skills add coco-research/coco --skill local-llm -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install coco-research/coco local-llm --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/coco-research/coco.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/local-llm .claude/skills/local-llm && 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 "local-llm" agent skill from https://github.com/coco-research/coco/tree/main/skills/local-llm into .claude/skills/local-llm/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "local-llm", 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/coco-research/coco/tree/main/skills/local-llmType 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 coco-research/coco --skill local-llm -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install coco-research/coco local-llm --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/coco-research/coco.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/local-llm .agents/skills/local-llm && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "local-llm" agent skill from https://github.com/coco-research/coco/tree/main/skills/local-llm into .agents/skills/local-llm/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "local-llm", 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 coco-research/coco --skill local-llm -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install coco-research/coco local-llm --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/coco-research/coco.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/local-llm .cursor/skills/local-llm && 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 "local-llm" agent skill from https://github.com/coco-research/coco/tree/main/skills/local-llm into .cursor/skills/local-llm/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "local-llm", 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/coco-research/coco.git --path skills/local-llm--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 coco-research/coco --skill local-llm -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install coco-research/coco local-llm --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/coco-research/coco.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/local-llm .gemini/skills/local-llm && 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 "local-llm" agent skill from https://github.com/coco-research/coco/tree/main/skills/local-llm into .gemini/skills/local-llm/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "local-llm", 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 coco-research/coco local-llmInstalls 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 coco-research/coco --skill local-llm -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/coco-research/coco.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/local-llm .github/skills/local-llm && 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 "local-llm" agent skill from https://github.com/coco-research/coco/tree/main/skills/local-llm into .github/skills/local-llm/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "local-llm", 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 coco-research/coco --skill local-llm -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install coco-research/coco local-llm --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/coco-research/coco.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/local-llm .opencode/skills/local-llm && 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 "local-llm" agent skill from https://github.com/coco-research/coco/tree/main/skills/local-llm into .opencode/skills/local-llm/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "local-llm", 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
local-llm- GitHub stars
- 503
- Token cost
- ~7.9k tokens
- SKILL.md length
- 4,255 words
- Files
- 1
- Skills in repo
- 63
- Repo updated
- First seen
- Licence
- Custom licence
At a glance
A skill your agent uses when working with this machine's local LLM setup (LM Studio + mlx-dspark) -- checking status, changing context window, diagnosing a reasoning hang or dead request…
- Works in 5 steps: kv_bits (KV-cache quantization) --… → lookup-drafts -- currently false. A… → Lower weight quantization below 4-bit --… → …
- Working with this machines local LLM setup (LM Studio + mlx-dspark) -- checking status
- SKILL.md covers Announce at start, Architecture, The prefill trick (why this… and Idle-unload (don't keep the…, plus 11 more sections
- Calls curl; needs MLX_DSPARK_API_KEY
What it does
Local LLM is an agent skill from coco-research/coco. Use when working with this machine's local LLM setup (LM Studio + mlx-dspark) -- checking status, changing context window, diagnosing a reasoning hang or dead request, understanding RAM/speed tradeoffs, or wiring a new script to the local inference endpoint.
Its SKILL.md is about 7.9k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Agent Workflows, covering Context engineering. The repository describes itself as: CoCo Super Intelligence is the orchestration layer that turns Claude Code, Cursor, or Codex into an engineering department: a routed advisory board, 226 skills, 386 commands…
When your agent uses it
- Working with this machines local LLM setup (LM Studio + mlx-dspark) -- checking status
- Changing context window
- Diagnosing a reasoning hang
- Understanding RAM/speed tradeoffs
Example prompts
- “/local-llm”
Requirements
- A credential in MLX_DSPARK_API_KEY
Workflow steps
5 steps, taken from the first numbered list in SKILL.md.
- kv_bits (KV-cache quantization) -- currently 0/unused. Helps most at
- lookup-drafts -- currently false. A cheap draft-generation mode
- Lower weight quantization below 4-bit -- diminishing returns, not
- max-batch -- already at 4, matching build_local.py's worker pool;
- Hardware upgrade (M4 Ultra ~= 2x memory bandwidth) -- out of scope, just
What it can do on your machine
Read from SKILL.md and the folder at commit d79d33a. 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
Shell commands in SKILL.md call:
curl
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use curl, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names these keys or tokens, usually read from environment variables:
MLX_DSPARK_API_KEY
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Local LLM loads about 7.9k tokens when it runs. Until then it costs about 67 tokens; SKILL.md has 4,255 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
Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 4,255 words (~7,943 tokens).
“"I'm using the local-llm skill to work with the local inference setup."”
- name
- local-llm
- domain
- ops
Files
Just SKILL.md in skills/local-llm of coco-research/coco.
Open the folder on GitHubat commit d79d33a
Compare with similar skills
Local LLM 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 |
|---|---|---|---|---|---|---|
| Local LLM this skillcoco-research/coco | 503 | — | ~7.9k | Automated safety check: Pass | Custom licence | |
| 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 | |
| ccc Semantic Code Searchcocoindex-io/cocoindex-code | 2.8k | — | ~938 | Automated safety check: Pass | Apache-2.0 | |
| Context Mode for Antigravity CLImksglu/context-mode | 26k | — | ~850 | Automated safety check: Pass | Custom licence |
Similar skills
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.
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.
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.
Token Optimizer
alexgreensh/token-optimizer
Audit a Claude Code or Codex setup for context-window waste, then fix it and measure the savings.
More from coco-research/coco
All 63 skills in this repoCoco Ads
coco-research/coco
Turn the project you just shipped into a short, polished, shareable launch video (an "ad") using HyperFrames.
Arch Index
coco-research/coco
Build and validate .arch/index.json — a committed map from each architectural component of this repository to the real directories and files that implement it, pinned to a git commit, with every…
Openai Agents
coco-research/coco
Build AI applications with OpenAI Agents SDK - text agents, voice agents, multi-agent handoffs, tools with Zod schemas, guardrails, and streaming.
Skill Evolution
coco-research/coco
A skill your agent uses when running, reviewing or changing coco's self-evolution cycle: the 30-day loop that observes how skills are actually used, proposes evidence-backed edits to them as one…
Coco Diagram
coco-research/coco
A skill your agent uses for architecture, current-state, process, data-flow, medallion, or DP diagrams, including redrawing .drawio and Mermaid sources.
API Design Principles
coco-research/coco
A skill your agent uses when designing a new REST or GraphQL API, reviewing an API spec before implementation, setting team API standards, or migrating REST to GraphQL.
Related
Categories
Questions about Local LLM
What does Local LLM do?
A skill your agent uses when working with this machine's local LLM setup (LM Studio + mlx-dspark) -- checking status, changing context window, diagnosing a reasoning hang or dead request…. Local LLM is an agent skill from coco-research/coco. Use when working with this machine's local LLM setup (LM Studio + mlx-dspark) -- checking status, changing context window, diagnosing a reasoning hang or dead request, understanding RAM/speed tradeoffs, or wiring a new script to the local inference endpoint.
When should I use Local LLM?
Local LLM fits situations like: working with this machines local LLM setup (LM Studio + mlx-dspark) -- checking status; changing context window; diagnosing a reasoning hang; understanding RAM/speed tradeoffs.
How do I install Local LLM in Claude Code?
Run `npx skills add coco-research/coco --skill local-llm -a claude-code`. Or copy the skill folder (skills/local-llm in coco-research/coco) into .claude/skills/local-llm in your project. Claude Code loads it when a task matches its description.
How do I install Local LLM in Codex?
Run `npx skills add coco-research/coco --skill local-llm -a codex`. Or copy the skill folder (skills/local-llm in coco-research/coco) into .agents/skills/local-llm in your project. Codex loads it when a task matches its description.
Can I use Local LLM 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 coco-research/coco --skill local-llm -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/local-llm, .gemini/skills/local-llm, .github/skills/local-llm and .opencode/skills/local-llm in your project.
What does Local LLM need to run?
Going by SKILL.md and its folder, Local LLM needs the command-line tools its instructions call (curl) and credentials named MLX_DSPARK_API_KEY. Our summary lists: A credential in MLX_DSPARK_API_KEY.
Does Local LLM access the network?
SKILL.md contains no URLs. Its commands use curl, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Is Local LLM 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 Local LLM use?
Local LLM has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.
How many tokens does Local LLM use?
About 7.9k tokens (SKILL.md is roughly 32k 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 Local LLM?
Skills that share tags, products or a category with Local LLM: Context Mode Output Sandbox (mksglu/context-mode, 26k stars), Memori Long-Term Memory (MemoriLabs/Memori, 17k stars), Picoclaw Skill Creator (sipeed/picoclaw, 30k stars) and ccc Semantic Code Search (cocoindex-io/cocoindex-code, 2.8k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Local LLM?
coco-research (a GitHub user) maintains it in coco-research/coco, which has 503 GitHub stars. The repository holds 63 skills in this directory. The repository was last updated on October 9, 2026.
Source: coco-research/coco on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.