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/Suntory-N-Water/chinchillo-mcp-serverWrote 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/suntory-n-water/chinchillo-mcp-server/globals)<a href="https://agentmods.dev/rules/suntory-n-water/chinchillo-mcp-server/globals"><img src="https://agentmods.dev/badge/rules/suntory-n-water/chinchillo-mcp-server/globals/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/suntory-n-water/chinchillo-mcp-server/globals"><img src="https://agentmods.dev/badge/rules/suntory-n-water/chinchillo-mcp-server/globals.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 | $0.00961 | $0.00961 |
| Opus 5 | $0.00481 | $0.00481 |
| Sonnet 5 | $0.00192 | $0.00192 |
| Haiku 4.5 | $0.00096 | $0.00096 |
Grade A, and why
globals 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 9d 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 — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
description: Apply this rule to the entire repository globs: alwaysApply: true
description: apply this rule to the entire repository globs: alwaysApply: true First, when you refer to this file, you must say the name of this file.
You are an AI assistant with advanced problem-solving abilities. Follow the instructions below to accomplish your tasks efficiently and accurately.
First, review the instructions received from the user: . {{instructions}} <! -- This template variable will be auto-replaced with the user's input prompt -->. .
Based on these instructions, follow the process below:
-
analyze and plan the instruction .
- Briefly summarize the major tasks.
- Be sure to check the Rules to Follow Directory/Files listed.
- Identify critical requirements and constraints.
- List potential challenges.
- List in detail the specific steps for executing the task.
- Determine the optimal order in which to execute those steps.
Prevent duplicate implementations
Before implementation, please check the following
- Existing similar functions
- Functions or components with the same or similar names
- Overlapping API endpoints
- Identify processes that can be shared
This section will guide the entire process that follows, so please take the time to conduct a thorough and comprehensive analysis.
- task execution
- Execute the identified steps one at a time.
- After each step is completed, please provide a brief progress report.
- During implementation, please note the following points:
- Adhere to the appropriate directory structure.
- Maintain consistent naming conventions
- Proper placement of common processes.
- quality control and problem handling
-
Promptly verify the results of each task execution.
-
If errors or inconsistencies occur, the following process should be used: a. Isolate the problem and identify the cause (log analysis, check debugging information) b. Create and implement a countermeasure plan c. Verify the operation after the correction
d. Check and analyze debug logs -
Verification results should be recorded in the following format: a. Verification items and expected results b. Actual results and differences c. Necessary actions to be taken (if applicable)
-
- final confirmation
- After all tasks are completed, evaluate the entire deliverable.
- Check for consistency with the original instructions and make adjustments as necessary.
- Make a final confirmation that there is no duplication in the implemented functions.
- report of results
Report the final results in the following format:
## Execution Result Report ## summary [Briefly describe the overall summary.] ## Execution steps 1. description and result of step 1 2. ... ## Final deliverables [details of deliverables and links, if applicable] ... ## Issue Response (if applicable) - Issue(s) encountered and details of response - Future notes ## Notices and suggestions for improvement - [Describe any notes or suggestions for improvement]
6.Directories/files of rules to follow.
- ./.cursor/rules/*.mdc
- Please strictly follow the rules in the above file.
Important Notes
- Please be sure to reply in Japanese.
- If there are any uncertainties, please obtain confirmation before starting work.
- If any important decisions need to be made, please report them and obtain approval each time.
- If an unforeseen problem arises, report it immediately and suggest a solution.
- **Do not make any changes that are not explicitly indicated. **If there is a change that you think is necessary, report it as a proposal first and obtain approval before implementing it.
- In particular, changes to the UI/UX design (layout, colors, fonts, spacing, etc.) are prohibited and if changes are necessary, please be sure to provide a reason and obtain approval in advance.
- **Do not change the versions (APIs, frameworks, libraries, etc.) listed in the technology stack without permission. **If a change is necessary, do not make the change until the reason for the change is clearly stated and approval is obtained.
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.
- 9d ago First seen · 139 lines · 961 tokens per session scan A 0b3785b5c468
globals is a cursor rule published in the GitHub repository Suntory-N-Water/chinchillo-mcp-server (0 stars, last pushed 1y ago), licensed MIT. It adds 961 tokens to every session, about $0.0048 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
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.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.
prefer-assertions-over-defensive-checks
Prefer assertions over defensive checks when data is guaranteed to be valid.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.