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/FrigateCaptain/ElucidatingYourLLMWrote 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/frigatecaptain/elucidatingyourllm/rules-management)<a href="https://agentmods.dev/rules/frigatecaptain/elucidatingyourllm/rules-management"><img src="https://agentmods.dev/badge/rules/frigatecaptain/elucidatingyourllm/rules-management/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/rules/frigatecaptain/elucidatingyourllm/rules-management"><img src="https://agentmods.dev/badge/rules/frigatecaptain/elucidatingyourllm/rules-management.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 | $0.00000 | $0.01219 |
| Opus 5 | $0.00000 | $0.00609 |
| Sonnet 5 | $0.00000 | $0.00244 |
| Haiku 4.5 | $0.00000 | $0.00122 |
Grade A, and why
rules-management 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 4d 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cursor rule management
Placement
- Base rules (needed in every conversation: AI behavior, safety, git, language, response format) — in the main
.cursorrulesfile. - Domain rules (for specific file types, tools, formats) — in
.cursor/rules/*.mdcwith appropriate globs. - Do not place rules in
rules/*.md— Cursor does not load them automatically.
File naming
- Kebab-case:
technical-documents.mdc,video-editing.mdc. - The name reflects the rule’s purpose.
Frontmatter
Each .mdc file starts with YAML frontmatter. When creating a new rule — open and use the template .cursor/rules/FRONTMATTER_of_rules_TEMPLATE.md.
Rule registry
All rules are registered in .cursor/rules/RULES_REGISTRY.md. When creating, changing, or deleting a rule — update the registry:
- On create — fill the "Creation date" and "Last updated" columns (same values, with time; format: "10 March 2026, 14:30").
- On change — update the "Last updated" column (with time).
- On delete — remove the row from the registry.
Choosing activation type
alwaysApply: true— only if the rule is needed in EVERY conversation. Test: "If the user asks 'what is 2+2?' — is this rule needed in context?" If not — use globs.globs— preferred for domain rules. Specify concrete file patterns.descriptionwithout globs — for rules hard to tie to files; Cursor loads them by semantic relevance.
One rule = one goal
If a rule mixes unrelated topics — split into separate files with their own globs.
Size control
A good target for one rule is up to 50 lines. This is not a hard limit, but a rule that fits in ~50 lines is usually focused and easy to read.
If a rule exceeds ~500 lines — ask the user: "Rule [name] has [N] lines. Consider splitting or shortening. Proceed?" The user decides.
No duplication
Each rule exists in one place. If you find a duplicate — merge into one file, remove from other locations, leave a short pointer.
Separate rules from other artifacts
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.
- 4d ago First seen · 103 lines · 0 tokens per session scan A 4918329f6d32
rules-management is a cursor rule published in the GitHub repository FrigateCaptain/ElucidatingYourLLM (14 stars, last pushed 5d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,219 tokens. 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 2026-09-05.
Other cursor rules, from other repositories
coding-process-rules
A workflow guide for handling coding tasks step by step, finishing one file before moving to the next, and recording unfinished work with TODO comments.
code-output-rules
Code-output guidelines that require complete, usable file contents with imports, declarations, surrounding code, and comments for important changes.
history-and-next-task-rules
A response-formatting guide that requires an assistant to summarize the work, show the source tree, and identify the next task.
general-assistant-rules
A set of general assistant rules for understanding a project's needs and technology choices, handling errors, asking clarifying questions, and suggesting solutions.
kotlin-springboot-rules
A set of coding rules for Kotlin applications built with Spring Boot, a Java-based framework for web services. It covers project layout, naming, Kotlin style, and common design patterns.
mobx-react-lite-usage
A set of rules for connecting MobX to React function components through mobx-react-lite, a library that makes components observe MobX state.