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.
git clone --depth 1 https://github.com/davidl71/project-management-automationWrote 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/rules/davidl71/project-management-automation/ollama)<a href="https://agentmods.dev/rules/davidl71/project-management-automation/ollama"><img src="https://agentmods.dev/badge/rules/davidl71/project-management-automation/ollama.svg" alt="Measured on agentmods" 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 | $0.00963 | $0.00963 |
| Opus 5 | $0.00481 | $0.00481 |
| Sonnet 5 | $0.00193 | $0.00193 |
| Haiku 4.5 | $0.00096 | $0.00096 |
Grade A, and why
ollama scanned grade A with 1 finding 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 6d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
3. Test API: `curl http://localhost:11434/api/tags` How it starts
The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ollama MCP Server Usage
When to Use Ollama
ALWAYS use Ollama for:
- Privacy-sensitive code analysis
- Security review of code and risk management
- Documentation generation for proprietary code
- Code review of sensitive calculations
- Analysis of algorithms and strategies
- Any code that should not leave your local machine
Usage Pattern: Use Ollama when:
- Analyzing proprietary code
- Reviewing security implementations
- Generating documentation for sensitive modules
- Debugging complex logic
- Researching with local data
Examples
✅ Good:
- "Use Ollama to analyze this code for security issues"
- "Review this code with Ollama for potential bugs"
- "Generate documentation for this module using Ollama"
- "Explain this calculation using Ollama"
- "Check this code for memory leaks using Ollama"
❌ Avoid:
- General coding questions (use Cursor AI instead)
- Quick lookups (use Context7 or web search)
- Questions that don't involve proprietary code
- Real-time collaboration needs (use Cursor AI)
Benefits
- Privacy: All code stays on your local machine
- Cost Savings: No API costs for frequent analysis
- Offline Capability: Works without internet connection
- Security: Proprietary code never transmitted to cloud
Integration with Other Tools
- Before cloud services: Use Ollama for sensitive code, then Cursor AI for general questions
- With Semgrep: Ollama for code analysis, Semgrep for security scanning
- With Context7: Ollama for proprietary code, Context7 for library documentation
Workflow for Code Review
- Identify sensitive code - Algorithms, calculations, proprietary logic
- Use Ollama - Analyze code locally for bugs, security, documentation
- Review suggestions - Always review Ollama's suggestions before implementing
- Combine with human review - Ollama assists, human decides
Best Practices
Query Optimization
- Be specific: "Review this function for potential bugs, focusing on edge cases and error handling"
- Provide context: Include relevant code or file references
- Break down complex questions: Split large analyses into smaller, focused queries
- Review output: Always review and test Ollama's suggestions
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.
- 6d ago First seen · 134 lines · 963 tokens per session scan A 40029fb92b39
ollama is a cursor rule published in the GitHub repository davidl71/project-management-automation (1 stars, last pushed 6mo ago), licensed MIT. It adds 963 tokens to every session, about $0.0048 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other cursor rules, from other repositories
llm-layer
LLM provider implementation patterns.
tensorflow
TensorFlow: Keras, model training, production deployment.
006_Program_of_Thought_Tutorial
DSPY 3 Program of Thought Tutorial - Production code reasoning system from official DSPy 3.0.1 tutorial.
standards-data-eng
Mandatory standards for Python and SQL data pipelines.
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.