setup-ollama-local SKILL.md skillB
setup-ollama-local from receptron/mulmoclaude is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add receptron/mulmoclaude/setup-ollama-local@git:20260425.d9b61c8Pins git:20260425.d9b61c8 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- B, 16 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- receptron/mulmoclaude
- Path
.claude/skills/setup-ollama-local/SKILL.md- Versions recorded
- 3
- Latest version
- git:20260425.d9b61c8, committed Apr 25, 2026
- First version recorded
- Apr 24, 2026
- Size
- 7,927 bytes
- Repository stars
- 386
- License
- MIT
Interactively guide setup for connecting the Claude Code CLI to a local Ollama LLM on Mac. NOTE — This is for the standalone Claude Code CLI itself, NOT MulmoClaude (MulmoClaude does not currently support Ollama as a backend). Covers Ollama install, model pull, env switching, and verification. Respond in the user's language.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Setup Claude Code × Ollama (local LLM) > **Scope / 適用範囲** > > This skill sets up the **standalone `claude` CLI** to talk to a local Ollama server. It is **independent of MulmoClaude**; MulmoClaude itself does not currently support Ollama (see `plans/feat-mulmoclaude-ollama-support.md` for a tentative plan). > > このスキルは **`claude` CLI 単体**をローカルの Ollama サーバに接続するセットアップです。**MulmoClaude とは独立**しており、MulmoClaude 本体は現在 Ollama 接続をサポートしていません（実装案は `plans/feat-mulmoclaude-ollama-support.md` を参照）。 For detailed findings and pitfalls, see [`docs/tips/claude-code-ollama.md`](../../../docs/tips/claude-code-ollama.md) (Japanese) / [`docs/tips/claude-code-ollama.en.md`](../../../docs/tips/claude-code-ollama.en.md) (English). ## Prerequisites / 前提知識 - Ollama **v0.14.0 or later** is required (Anthropic Messages API compatibility was added in that version). - Claude Code sends roughly **50,000–57,000 tokens per request**, so the model needs **at least a 64k context window**. - 3B-class small models effectively cannot drive Claude Code (no tool calling, broken templates). …
Read the whole file at its exact version.
How to install
mdr add receptron/mulmoclaude/setup-ollama-local@sha256:683c717726b3811eThe line at the top of this page pins the label git:20260425.d9b61c8, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_3kb5mr7hif6zgs25)
5 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 3 versions of this file, between Apr 24, 2026 and Apr 25, 2026, more than one a day.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260425.d9b61c8 latest | 2026-04-25 | d9b61c8 | 7,927 B | B | view · diff |
| git:20260425.3df6495 | 2026-04-25 | 3df6495 | 7,777 B | B | view · diff |
| git:20260424.bc8597d | 2026-04-24 | bc8597d | 6,258 B | B | view |
Audit of the latest version
- fail: No curl or wget piped into a shell (matched: curl -fsSL https://claude.ai/install.sh | sh)
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (7927 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Starting a new one? Use a template for SKILL.md on mdpantry, which passes every one of these checks and says what to change in it.
Source
receptron/mulmoclaude · 386 stars · license MIT · pushed 2026-11-07 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_3kb5mr7hif6zgs25 GET https://markdownregistry.com/api/v1/resolve?ref=receptron/mulmoclaude/setup-ollama-local GET https://markdownregistry.com/api/v1/blob/683c717726b3811ead33459b35e996b38e86544ab17f52f52e23e89943740382
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.