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/saropa/saropa_lints/saropa_lints_instructionsgit clone --depth 1 https://github.com/saropa/saropa_lintsWrote 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/saropa/saropa_lints/saropa_lints_instructions)<a href="https://agentmods.dev/rules/saropa/saropa_lints/saropa_lints_instructions"><img src="https://agentmods.dev/badge/rules/saropa/saropa_lints/saropa_lints_instructions.svg" alt="Measured on agentmods" 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 | $0.00521 | $0.00521 |
| Opus 5 | $0.00260 | $0.00260 |
| Sonnet 5 | $0.00104 | $0.00104 |
| Haiku 4.5 | $0.00052 | $0.00052 |
Grade A, and why
saropa_lints_instructions 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 3d 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 — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Guidelines when working on the saropa_lints codebase (Dart custom lint rules package).
Essential Files to Update
- New rule: Register in lib/src/rules/all_rules.dart and lib/src/tiers.dart. Add entry to ROADMAP.md.
- Structural changes: Update CODEBASE_INDEX.md and CODE_INDEX.md when adding utilities or moving files.
- Before publish: Update CHANGELOG.md.
Workflow
- Adding a rule: Implement in appropriate
lib/src/rules/*_rules.dart, extendDartLintRuleorSaropaLintRule, add DartDoc with Bad/Good examples, register in all_rules.dart and tiers.dart, add ROADMAP entry, add fixture inexample/(mark violations with// LINT) and unit test intest/. - Validation: Run
/analyze,/test,/format. UseSkill(lint-rules)when adding or modifying rules. - Example dirs: All
example*/must be inanalysis_options.yamlunderanalyzer > exclude(they contain intentional violations).
You Must NOT
- Add or support
// ignore:or// ignore_for_file:(no quick fixes that insert ignore; no custom ignore-detection in rules). Fix the rule or the code instead. - Add quick fixes that only insert a
// TODO: ...comment; fixes must make a real code change that resolves the violation. - Add Co-authored-by, AI attribution, or emojis to commit messages.
Principles
- Search first: Check CODE_INDEX.md and lib/src utilities before adding new code.
- ProjectContext: Use for package detection, platform detection, file classification—do not reimplement.
- Type checking over string matching; early returns for simple checks.
- Code quality: Functions ≤50 lines, parameters ≤3, nesting ≤3, files ≤200 lines (self-reviewer enforces).
Commands and Skills
/analyze,/test,/format,/review,/commitas in CLAUDE.md.Skill(lint-rules)for rule work;Skill(publishing)for releasing.
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.
- 3d ago First seen · 38 lines · 521 tokens per session scan A 639e9e261f27
saropa_lints_instructions is a cursor rule published in the GitHub repository saropa/saropa_lints (8 stars, last pushed 4d ago), licensed MIT. It adds 521 tokens to every session, about $0.0026 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
blog-guide
Writing guides for the FlutterInit blogs (Guides category).
validation-harness
Validation harness — interfaces, adapters, cenários E2E.
project-core
Invariantes globais do laboratório Flutter + validation harness.
flutter-app
Convenções do app Flutter (lib/).
testing
Cursor rule "testing" from BlackLeg15/desafio_bloc_1, covering testing and cobertura existente.
codex-premium-website-skills
Apply Codex Skills standards to frontend, website, motion, accessibility, QA, agent reasoning, and handoff work.