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 skills add PracticalSwan/agent-skills --skill best-practicesgit clone --depth 1 https://github.com/PracticalSwan/agent-skillsWrote 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/skills/practicalswan/agent-skills/best-practices)<a href="https://agentmods.dev/skills/practicalswan/agent-skills/best-practices"><img src="https://agentmods.dev/badge/skills/practicalswan/agent-skills/best-practices.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Prompt Injection · line 41 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
- high Prompt Injection · line 338 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
- high Prompt Injection · line 426 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
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 | $0.00049 | $0.03607 |
| Opus 5 | $0.00024 | $0.01803 |
| Sonnet 5 | $0.00010 | $0.00721 |
| Haiku 4.5 | $0.00005 | $0.00361 |
Grade A, and why
best-practices scanned grade A with 1 finding 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 today.
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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
const response = await fetch(url); How it starts
The opening of the file, as written. The whole thing — 533 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Best practices
Modern web development standards based on Lighthouse best practices audits. Covers security, browser compatibility, and code quality patterns.
Evidence-led audit workflow
When a rendered page is available:
- Run a live Lighthouse Best Practices audit when that capability is available; with Chrome DevTools MCP, use
lighthouse_audit. Use navigation mode for a normal page load or snapshot mode when the current state must be preserved. - Inspect the listed console and network failures and fetch individual details only when they support a finding.
- Supplement runtime evidence with dependency, header, configuration, and source inspection; Lighthouse is not a complete security assessment.
- Fix the implicated code, re-run the same audit, and keep security findings separate from style preferences.
If live tools are unavailable, use the Lighthouse CLI plus focused dependency and header checks. Never report a high Lighthouse score as proof that the application is secure.
Security
Read the security reference when security is in scope or a live audit surfaces a related failure. It covers HTTPS/HSTS, CSP and Trusted Types, Subresource Integrity, headers, dependencies, sanitization, and cookies.
At minimum:
- Use HTTPS without mixed content. Add HSTS only after confirming every relevant subdomain supports HTTPS.
- Treat a strict CSP as defense in depth. Prefer nonces or hashes and test with report-only before enforcement.
- Sanitize untrusted HTML and protect DOM XSS sinks. Prefer text APIs when markup is not required.
- Pin and review third-party code. Use SRI where the delivery model supports it and keep dependencies patched.
- Verify response headers at runtime. Source configuration alone does not prove what the deployed page sends.
Browser compatibility
Doctype declaration
<!-- ❌ Missing or invalid doctype -->
<HTML>
<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.01//EN">
<!-- ✅ HTML5 doctype -->
<!DOCTYPE html>
<html lang="en">
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- today Changed · +2 lines 4bfc4f31abff
- 2d ago Changed 0f0e52524384
- 4d ago Changed bede5ae0878b
- 8d ago First seen · 531 lines · 49 tokens per session scan A b25bdae96ebe
best-practices is a skill published in the GitHub repository PracticalSwan/agent-skills (13 stars, last pushed today), licensed MIT. It adds 49 tokens to every session and 3,607 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
angular-best-practices-v2
Angular Best Practices workflow skill. Use this skill when the user needs Angular performance optimization and best practices guide. Use when writing, reviewing, or refactoring Angular code for optimal performance, bundle size, and rendering efficiency and the operator should preserve the upstream workflow, copied…
angular-best-practices
Angular Best Practices workflow skill. Use this skill when the user needs Angular performance optimization and best practices guide. Use when writing, reviewing, or refactoring Angular code for optimal performance, bundle size, and rendering efficiency and the operator should preserve the upstream workflow, copied…
airflow-dag-patterns
Apache Airflow DAG Patterns workflow skill. Use this skill when the user needs Build production Apache Airflow DAGs with best practices for operators, sensors, testing, and deployment. Use when creating data pipelines, orchestrating workflows, or scheduling batch jobs and the operator should preserve the upstream…
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ralph with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.