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.
npx agentmods add rules/nxt3d/mcp-crm/plan-before-executiongit clone --depth 1 https://github.com/nxt3d/mcp-crmWhat 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 | $0.00000 | $0.00220 |
| Opus 5 | $0.00000 | $0.00110 |
| Sonnet 5 | $0.00000 | $0.00044 |
| Haiku 4.5 | $0.00000 | $0.00022 |
Grade A, and why
plan-before-execution 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 yesterday.
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
For this request, I want you to work up a plan. Provide your findings on how you plan to solve the problem and a step-by-step list of tasks. I don't want you to start changing any existing files or writing any code yet. Instead, conduct any necessary research and define the solution or design you intend to use to complete the task. Once complete, return with a summary of the solution and a clear, step-by-step execution plan.
Save the plan in a document with a relevant name, located appropriately near where the corresponding code will be written or updated. Also, create a second document—a progress file—that we will use to track the implementation of the plan as we build out the feature or solution.
In summary:
Create a detailed plan with your findings and steps.
Save the plan in a clearly named document, in a relevant directory.
Create a second document for tracking progress.
Report back with a summary of the solution and the names/locations of both documents.
Don't forget to save the plan and progress docs!
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.
- yesterday First seen · 20 lines · 0 tokens per session scan A 667a2026b1cf
plan-before-execution is a cursor rule published in the GitHub repository nxt3d/mcp-crm (5 stars, last pushed 1y ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 220 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 2026-08-31.
Other cursor rules, from other repositories
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-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.