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/starch-uk/agent-docsWrote 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/starch-uk/agent-docs/important)<a href="https://agentmods.dev/rules/starch-uk/agent-docs/important"><img src="https://agentmods.dev/badge/rules/starch-uk/agent-docs/important/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/starch-uk/agent-docs/important"><img src="https://agentmods.dev/badge/rules/starch-uk/agent-docs/important.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 | $0.01398 | $0.01398 |
| Opus 5.5 | $0.00559 | $0.00559 |
| Sonnet 5.5 | $0.00280 | $0.00280 |
| Haiku 4.5 | $0.00140 | $0.00140 |
Grade A, and why
IMPORTANT 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Important Project Guidelines
Documentation Files
-
Use
docs/*.mdfiles: Refer to and use the documentation files in thedocs/directory for project-specific information and guidelines. -
Use
.cursor/plans/*.mdfiles: Refer to and use planning documents in the.cursor/plans/directory for project planning and development guidance.
Updating Existing Documentation - CRITICAL REQUIREMENT
MANDATORY: When updating any file in the docs/ directory, you MUST follow the documented process. This is NON-NEGOTIABLE.
What you MUST do:
- Understand the workflow first - Before making any changes to a doc file, understand the complete workflow
- Extract references - Extract repository URLs, web page URLs, or Salesforce article references from the doc file itself
- Re-research sources - Extract repository URLs, web page URLs, or other references from the doc file itself. CRITICAL: If a repository URL is already present in the existing
docs/*.mdfile, extract the repository URL directly from the doc file and proceed to cloning. - Clone repository - Clone repo using full permissions to system's temporary folder (if applicable)
- Systematic review - Go through every URL on the official page and every file in the repo (verify ALL files inspected)
- Verify all content - All content in markdown file must be verified or removed/changed
- Add missing content - Anything missing should be added
- Cleanup - Delete temporary repository directory after inspection
- Verify ALL todos completed - Before proceeding, verify ALL file inspection todos are completed (count must match file count exactly)
- Optimize - Actually execute the OPTIMISE.md plan after updates (ONLY after ALL todos completed, read it, apply techniques, don't just mark as done)
- Version - Follow VERSIONING.md to determine and update version numbers
What you MUST NOT do:
- ❌ Update doc files without understanding the workflow first
- ❌ Make changes without re-researching sources
- ❌ Skip repository cloning for repository-based docs
- ❌ Skip the verification process
- ❌ Skip file inspection (ALL files must be inspected)
- ❌ Leave temporary directories on the system
- ❌ Mark optimization as "done" without actually executing it
- ❌ Skip optimization or versioning steps
- ❌ Begin optimization before ALL file inspection todos are completed
- ❌ Cancel or skip remaining todos because "essential review is complete"
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 · 98 lines · 1,398 tokens per session scan A 18a5c9e620db
IMPORTANT is a cursor rule published in the GitHub repository starch-uk/agent-docs (6 stars, last pushed 7mo ago), licensed MIT. It adds 1,398 tokens to every session, about $0.0056 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 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.
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.
control-plane-descriptors
Control plane descriptor and instance implementation patterns.
family-instance-domain-actions
Family instance domain action implementation patterns.