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 Gekkos-tech/agency-os --skill best-practicesgit clone --depth 1 https://github.com/Gekkos-tech/agency-osWrote 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/gekkos-tech/agency-os/best-practices)<a href="https://agentmods.dev/skills/gekkos-tech/agency-os/best-practices"><img src="https://agentmods.dev/badge/skills/gekkos-tech/agency-os/best-practices/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/skills/gekkos-tech/agency-os/best-practices"><img src="https://agentmods.dev/badge/skills/gekkos-tech/agency-os/best-practices.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 | $0.00049 | $0.04063 |
| Opus 5 | $0.00024 | $0.02031 |
| Sonnet 5 | $0.00010 | $0.00813 |
| Haiku 4.5 | $0.00005 | $0.00406 |
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 11d 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.
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 — 642 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.
Security
HTTPS everywhere
Enforce HTTPS:
<!-- ❌ Mixed content -->
<img src="http://example.com/image.jpg">
<script src="http://cdn.example.com/script.js"></script>
<!-- ✅ HTTPS only -->
<img src="https://example.com/image.jpg">
<script src="https://cdn.example.com/script.js"></script>
Avoid protocol-relative URLs (//example.com/...) — they're an HTTP-era pattern with no benefit on HTTPS-only sites and hide the actual scheme from reviewers.
HSTS Header:
Strict-Transport-Security: max-age=31536000; includeSubDomains; preload
Content Security Policy (CSP)
<!-- Basic CSP via meta tag -->
<meta http-equiv="Content-Security-Policy"
content="default-src 'self';
script-src 'self' https://trusted-cdn.com;
style-src 'self' 'unsafe-inline';
img-src 'self' data: https:;
connect-src 'self' https://api.example.com;">
<!-- Better: HTTP header -->
CSP Header (recommended):
Content-Security-Policy:
default-src 'self';
script-src 'self' 'nonce-abc123' https://trusted.com;
style-src 'self' 'nonce-abc123';
img-src 'self' data: https:;
connect-src 'self' https://api.example.com;
frame-ancestors 'self';
base-uri 'self';
form-action 'self';
Using nonces for inline scripts:
<script nonce="abc123">
// This inline script is allowed
</script>
Trusted Types (modern DOM-XSS defense)
A strict CSP blocks loading untrusted script files, but it doesn't stop a string from reaching innerHTML, eval, or other DOM-XSS sinks. Trusted Types — Baseline across all major browsers since early 2026 — closes that hole by making sinks reject raw strings and accept only typed objects produced by a named policy.
Content-Security-Policy: require-trusted-types-for 'script'; trusted-types default;
What ships with it
1 file 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.
- 11d ago First seen · 642 lines · 49 tokens per session scan A 432875ade263
best-practices is a skill published in the GitHub repository Gekkos-tech/agency-os (5 stars, last pushed 2mo ago), licensed MIT. It adds 49 tokens to every session and 4,063 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 2026-08-31.
Other skills, from other repositories
neo-code-review
Use this skill when the user asks to review or audit source code, a PR, diff, commit, or recent changes for bugs, security, performance, tests, compatibility, or maintainability, duplicated code or logic across files, or hard-coded values. Also use it after an AI agent finishes modifying code to inspect the current…
neo-pr
Use this skill when the user asks to create, draft, review, format, or generate a Pull Request (PR) title and description, specify target or source branches for a repository, or convert git branch diffs into concise, high-impact, non-AI-slop PR content.
neo-rust
Use this skill when writing, refactoring, debugging, or auditing Rust code. Trigger for .rs files, Cargo projects, ownership/borrowing/lifetime issues, Result/Option error handling, unnecessary clone/performance work, unsafe code review, or modern Rust architecture.
pr-walkthrough
Generate a static interactive D3 walkthrough of a pull request. Use when the user wants a zoomable PR map, graph/canvas PR orientation, or alternate visualization of PR system components, data flow, code dependencies, and user actions.
respond-to-pr-comments-in-blocklist
Interactively walk a user through PR review comments one at a time, collect a per-comment decision, then post agent-authored replies on GitHub and resolve the review threads once the user approves a preview. Use only when the user wants to reply to or resolve review threads on GitHub. Skip when the user only wants…
review-loop
Iterative worker-reviewer cycle that spawns a critic subagent to score work 1-10 and provide actionable feedback, then revises until a quality gate is met. Use when implementing features, writing specs, reviewing existing code, or completing any task where quality matters more than speed. Trigger phrases: "use…