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/jim-schilling/splurge-ai-rulesWrote 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/jim-schilling/splurge-ai-rules/sdlc-standards)<a href="https://agentmods.dev/rules/jim-schilling/splurge-ai-rules/sdlc-standards"><img src="https://agentmods.dev/badge/rules/jim-schilling/splurge-ai-rules/sdlc-standards/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/jim-schilling/splurge-ai-rules/sdlc-standards"><img src="https://agentmods.dev/badge/rules/jim-schilling/splurge-ai-rules/sdlc-standards.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 | $0.00006 | $0.00459 |
| Opus 5 | $0.00003 | $0.00230 |
| Sonnet 5 | $0.00001 | $0.00092 |
| Haiku 4.5 | $0.00001 | $0.00046 |
Grade A, and why
sdlc-standards 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.
What it actually says
- Follow Research, Plan, and Implement lifecycle.
- Document research in docs/research/research-[description]-[yyyy-MM-dd]-[sequence].md.
- Document action plans in docs/plans/plan-[description]-[yyyy-MM-dd]-[sequence].md.
- Document requirements and specifications in docs/specs/spec-[description]-[yyyy-MM-dd]-[sequence].md.
- Document issues/bugs in docs/issues/issue-[description]-[yyyy-MM-dd]-[sequence].md.
- Document apis in docs/apis/api-[description]-[yyyy-MM-dd]-[sequence].md.
- Document notes in docs/notes/note-[description]-[yyyy-MM-dd]-[sequence].md.
- Document configuration in docs/configuration/configuration-[description]-[yyyy-MM-dd]-[sequence].md.
- Research shall include exploration of existing solutions, libraries, and tools.
- Plans shall detail requirements, acceptance criteria, testing strategy (e.g. TDD and BDD), and a step-by-step implementation guide.
- Each action plan shall be sub-divided into stages (e.g. Stage-1, Stage-2), while stages are subdivided into tasks (e.g. Task-[Stage].1, Task-[Stage].2).
- Implementation lifecycle shall always: code failing tests, then implement code, then run tests, then iteratively refactor and run tests until all tests pass.
- Every feature must start as a standalone library before integration:
- Develop features as independent, reusable library components first
- Only integrate into larger applications after proving standalone functionality
- Software tools, primary libraries, data tools, and development tools must expose their functionality through a CLI. Other software functionality may omit a CLI if appropriate.
- If in doubt, prompt user for clarification and mark as [NEEDS CLARIFICATION].
- Always ask for user confirmation before making significant changes.
- Always ask for user confirmation before deleting files or data.
- Always ask for user confirmation before overwriting existing files.
- Use git for version control with feature branches and pull requests.
- Write clear, concise commit messages in the imperative mood (e.g., "Add feature", "Fix bug").
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 · 28 lines · 6 tokens per session scan A d0ad7bde5b85
sdlc-standards is a cursor rule published in the GitHub repository jim-schilling/splurge-ai-rules (3 stars, last pushed 11mo ago), licensed MIT. It adds 6 tokens to every session and 459 once invoked, about $0.0000 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.