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/lsampaioweb/ai-instructions/ai-customizationgit clone --depth 1 https://github.com/lsampaioweb/ai-instructionsWrote 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/lsampaioweb/ai-instructions/ai-customization)<a href="https://agentmods.dev/rules/lsampaioweb/ai-instructions/ai-customization"><img src="https://agentmods.dev/badge/rules/lsampaioweb/ai-instructions/ai-customization.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 | $0.00000 | $0.01362 |
| Opus 5 | $0.00000 | $0.00681 |
| Sonnet 5 | $0.00000 | $0.00272 |
| Haiku 4.5 | $0.00000 | $0.00136 |
Grade A, and why
ai-customization 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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Customization Style Contract
Pick the right artifact
| Need | Use | Notes |
|---|---|---|
| Always-on project behavior | Root AGENTS.md |
Plain markdown; no YAML frontmatter |
| Scoped guidance (paths, topics) | .cursor/rules/*.mdc |
globs or alwaysApply; not for duplicating AGENTS.md |
| Repeatable workflow the user invokes | .cursor/skills/**/SKILL.md |
YAML frontmatter + procedural body |
| Domain or stack guidance (path-scoped) | .mdc with globs |
Copilot sources live under .github/instructions/ |
| User-invoked Copilot task template | *.prompt.md |
Frontmatter with description and argument-hint |
| Multi-step Copilot agent persona | *.agent.md |
Copilot sources live under .github/agents/ |
- Do not put global behavior in a rule if it belongs in
AGENTS.md. - Do not duplicate the same rule across
AGENTS.md, rules, and skills.
Rules
- Keep frontmatter discoverable:
descriptionmust state when to use the file. - Remove routing noise: avoid vague descriptors that do not improve file selection.
- Use directive language: write mandatory rules with imperative verbs.
- Keep optional behavior explicit: mark optional rules with an explicit optional tag.
- Use one rule per bullet: each bullet must express one enforceable behavior.
- Split compound bullets: break combined requirements into separate rules.
- Keep sections purpose-specific: section title and rule scope must match.
- Move off-topic rules: relocate unrelated content to a dedicated section.
- Minimize low-signal wording: remove filler that does not change execution.
- Shorten verbose statements: keep the same meaning with fewer words.
- Preserve technical literals: do not alter commands, code, paths, URLs, identifiers, config keys, or versions unless incorrect.
- Resolve duplication deliberately: keep one canonical statement and reference it from secondary files.
- Resolve contradictions explicitly: define precedence or rewrite to remove conflict.
- State each constraint once in the strongest clear polarity; do not restate a Rules bullet as its negation in Safety Guards or in the same bullet.
- Do not append
; never …(or equivalent) inside a Rules bullet when that prohibition is already covered by the Must form or by Safety Guards. - Prefer one canonical file for cross-cutting policy; secondary files use a one-line deferral and must not copy the rule.
- Before adding a preference: search for an existing rule covering the decision; merge or reference instead of appending. Add a rule only when it changes a default decision and does not duplicate an existing rule.
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 · 85 lines · 0 tokens per session scan A ab966d80f272
ai-customization is a cursor rule published in the GitHub repository lsampaioweb/ai-instructions (1 stars, last pushed 11d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,362 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.