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/samilozturk/agentlint/cursor-agentlint-maintenancegit clone --depth 1 https://github.com/samilozturk/agentlintWrote 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/samilozturk/agentlint/cursor-agentlint-maintenance)<a href="https://agentmods.dev/rules/samilozturk/agentlint/cursor-agentlint-maintenance"><img src="https://agentmods.dev/badge/rules/samilozturk/agentlint/cursor-agentlint-maintenance.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 5.1 | $0.00558 | $0.00558 |
| Opus 5 | $0.00279 | $0.00279 |
| Sonnet 5 | $0.00112 | $0.00112 |
| Haiku 4.5 | $0.00056 | $0.00056 |
Grade A, and why
cursor-agentlint-maintenance 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 5d 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 — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scope
- Entire workspace. Apply these rules when the request mentions AGENTS.md, CLAUDE.md, rules, skills, workflows, or plans, or when structure, config, dependency, or CI changes are involved.
Activation
- Always active for this workspace or instruction file when the host client loads it.
Do
- Treat plain-English requests about stale, missing, inconsistent, or low-quality AGENTS.md, CLAUDE.md, rules, skills, workflows, or plans as Agent Lint work even if the user does not name Agent Lint explicitly.
- Treat structural change signals such as new modules, new directories, dependency changes, CI/config updates, environment/security changes, or repository reorganization as triggers to check context artifacts.
- For full workspace review or fix requests, start with
agentlint_plan_workspace_autofix. - For targeted structural changes, call
agentlint_quick_checkwith changed paths and/or a short change description. - Before creating or updating any context artifact, call
agentlint_get_guidelinesfor that artifact type. - When ongoing upkeep is requested, use
agentlint_emit_maintenance_snippetwhere supported or append equivalent maintenance instructions to the main project context file. - Apply recommended context artifact changes directly once Agent Lint has identified what to update, unless the user explicitly asks for a different maintenance outcome.
- Tell the user when an update was triggered or shaped by Agent Lint maintenance guidance.
- Keep context artifact files concise and reference docs instead of duplicating them.
Don't
- Do not edit context artifacts from repo guesses alone; scan the codebase first.
- Do not duplicate README or package README prose inside AGENTS, rules, skills, workflows, or plans.
- Do not leave placeholder sections, TODO text, or stale paths in maintained artifacts.
- Do not expand this maintenance policy to unrelated code or docs outside context artifacts unless the user explicitly asks.
- Do not wait for confirmation after Agent Lint has identified safe context-file fixes unless the user asked for a different outcome or the host approval model requires a gate.
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.
- 5d ago First seen · 46 lines · 558 tokens per session scan A b813ecb92668
cursor-agentlint-maintenance is a cursor rule published in the GitHub repository samilozturk/agentlint (30 stars, last pushed 4mo ago), licensed MIT. It adds 558 tokens to every session, about $0.0028 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 2026-08-30.
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-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.