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/AgileLuminary/mcp-agile-luminaryWrote 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/agileluminary/mcp-agile-luminary/cursorrule)<a href="https://agentmods.dev/rules/agileluminary/mcp-agile-luminary/cursorrule"><img src="https://agentmods.dev/badge/rules/agileluminary/mcp-agile-luminary/cursorrule.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 | $0.00402 | $0.00402 |
| Opus 5 | $0.00201 | $0.00201 |
| Sonnet 5 | $0.00080 | $0.00080 |
| Haiku 4.5 | $0.00040 | $0.00040 |
Grade A, and why
cursorRule 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 8d 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.
What it actually says
Agile Luminary MCP Rules
-
You have three MCP tools available via Agile Luminary MCP:
getCurrentWorkgetRelatedDocumentsgetPastWork
-
Before performing any user task, always call
getCurrentWorkto know the current user stories or tasks assigned. -
After fetching
getCurrentWork, automatically call:getRelatedDocuments→ Use relevant keywords from the current work to search for related documentation and specifications.getPastWork→ Use relevant keywords from the current work to search for what has been done before on similar tasks.
-
Once all three are retrieved, execute the actual task described in the
getCurrentWorkresponse. -
Do not execute any code or generate content before you have all three responses.
-
When calling
getRelatedDocumentsandgetPastWork, use intelligent search strings based on:- Key terms from the current work description
- Technology stack mentioned
- Feature names or component names
- User story themes or requirements
Example Workflow
User: "Let's work on the next user story."
Agent flow:
- Call
getCurrentWork - Analyze the response to extract key search terms
- Call
getRelatedDocumentswith relevant search string (e.g., "authentication", "payment system", "user dashboard") - Call
getPastWorkwith relevant search string based on the current work context - Then perform the work using all gathered context
Search Strategy Guidelines
- For
getRelatedDocuments: Search for technical specifications, requirements, architecture docs - For
getPastWork: Search for similar features, related user stories, or previous implementations - Use multiple calls with different search terms if the current work spans multiple domains
- Extract meaningful keywords rather than using generic terms
Ensure this sequence is enforced before writing any code or generating content.
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.
- 8d ago First seen · 42 lines · 402 tokens per session scan A 757b291ad214
cursorRule is a cursor rule published in the GitHub repository AgileLuminary/mcp-agile-luminary (3 stars, last pushed 1y ago), licensed MIT. It adds 402 tokens to every session, about $0.0020 per session on Opus 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 cursor rules, from other repositories
dev_workflow
Guide for using Taskmaster to manage task-driven development workflows.
state-memory-mcp
This project tracks workflow state, tasks, design decisions, and blockers using state-memory-mcp with project slug "state-memory-mcp".
tasks
Guidelines for implementing task management operations.
_project
Project-wide conventions and developer environment context (RN monorepo, no-Mac dev).
taskmaster
Comprehensive reference for Taskmaster MCP tools and CLI commands.
monorepo
Monorepo: workspace references, shared packages, boundaries.