Borrowing it
Nothing to install: this file belongs to darthzen/ollama-code-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/darthzen/ollama-code-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/darthzen/ollama-code-mcpWrote 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/instructions/darthzen/ollama-code-mcp/claude-md)<a href="https://agentmods.dev/instructions/darthzen/ollama-code-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/darthzen/ollama-code-mcp/claude-md/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/instructions/darthzen/ollama-code-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/darthzen/ollama-code-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00831 | $0.00831 |
| Opus 5.5 | $0.00332 | $0.00332 |
| Sonnet 5.5 | $0.00166 | $0.00166 |
| Haiku 4.5 | $0.00083 | $0.00083 |
Grade A, and why
ollama-code-mcp CLAUDE.md 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 2mo 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Routing guidance: local Ollama vs. cloud Claude
This project exposes coding tools backed by a local/LAN Ollama instance (Qwen3) via MCP. Use this file to decide when to delegate a task to those tools versus doing it yourself.
Delegate to ollama-code-mcp when the task is...
- Mechanical or repetitive. Writing a first-draft test suite, generating
boilerplate (CRUD handlers, DTOs, config parsing), or applying the same
mechanical edit across many files (
batch_refactor). - Context-window-heavy but low-ambiguity. Explaining an unfamiliar file,
reviewing a large diff for obvious issues (
code_review_diff), or reviewing/refactoring a big file you'd otherwise have to paste in full. Usefile_path/diff_file/glob_patterninstead of pasting content so the file never enters your own context window. - A useful first pass before your own review. Run
review_codeorcode_review_diffto surface candidate issues, then apply your own judgment to what it finds rather than trusting it blindly -- local models are meaningfully weaker than you at subtle correctness reasoning. - Not security- or architecture-sensitive. Straightforward fixes, explanations, and tests for code where being wrong is cheap to catch and correct.
Keep in the cloud (do it yourself) when the task is...
- Architecturally significant -- API design, cross-module refactors that require holding the whole system in mind, anything where a subtly wrong answer is expensive to unwind.
- Security-sensitive -- auth, crypto, permission checks, anything touching secrets or user data. Don't delegate generation or fixes here; you can delegate a review pass as a second opinion, but verify its findings yourself.
- Ambiguous or under-specified. If the task needs clarifying questions or multi-turn negotiation with the user, handle it yourself -- the Ollama tools are single-shot, not conversational.
- Small and fast. A one-line fix or a quick rename isn't worth a network round-trip to another host; just make the edit.
- Already failing. If a tool call reports Ollama is unreachable, timed
out, or the model isn't pulled, don't retry it -- handle the task
yourself. Call
ollama_statusonce to confirm before writing off local delegation for the rest of the session.
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.
- 2mo ago First seen · 64 lines · 831 tokens per session scan A 07edf17dab01
ollama-code-mcp CLAUDE.md is an instructions file published in the GitHub repository darthzen/ollama-code-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 831 tokens to every session, about $0.0033 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 2026-08-31.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.