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 skills/vinta/hal-9000/best-practicesnpx skills add vinta/hal-9000 --skill best-practicesgit clone --depth 1 https://github.com/vinta/hal-9000Wrote 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/vinta/hal-9000/best-practices)<a href="https://agentmods.dev/skills/vinta/hal-9000/best-practices"><img src="https://agentmods.dev/badge/skills/vinta/hal-9000/best-practices.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 | $0.00083 | $0.01130 |
| Opus 5 | $0.00042 | $0.00565 |
| Sonnet 5 | $0.00017 | $0.00226 |
| Haiku 4.5 | $0.00008 | $0.00113 |
Grade A, and why
best-practices 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 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.
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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Best Practices
Answer two questions from current sources: what's the recommended way, and what bites people (the gotchas and pitfalls around it). A how-to without its pitfalls is half an answer.
Two-Phase Rule
- Phase 1: Research. Dispatch find-docs and/or WebSearch queries.
- Phase 2: Synthesize and act. Starts only after Phase 1 results arrive.
The user's argument may be a question or an imperative. Imperatives ("refine X", "set up Y") determine what Phase 2 does, not whether Phase 1 happens. Phase 1 always runs.
Rationalizations that precede skipped research:
| Thought | Reality |
|---|---|
| "I already know this" | Training data goes stale. Config keys get renamed, APIs get deprecated. |
| "The user said to act" | The imperative scopes Phase 2, it does not eliminate Phase 1. |
| "This is a simple lookup" | A 30-second search costs nothing. A wrong recommendation costs a debugging round-trip. |
Workflow
1. Identify Research Targets
Break the topic into 2-4 specific queries. Dedicate at least one query to pitfalls ("common mistakes with X", "X gotchas in production"): pitfalls live in issue threads, migration guides, and post-mortems, not in getting-started docs, so a how-to query won't surface them. For design prior-art (the "before proposing a design of your own" trigger), dedicate queries to how existing open source projects implement it — concrete implementations and comparisons, not just advice posts. For single-library lookups, call find-docs or WebSearch directly without subagents.
2. Parallel Research
Dispatch one subagent per query in a single message so they run in parallel, passing model: sonnet on each Agent call so the bulk research stays cheap while orchestration and synthesis keep the session model. Each uses find-docs (Context7) and WebSearch. Be concrete in each subagent prompt: pass library names, version constraints, and the user's specific context. Vague prompts produce vague results.
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 · -7 tokens per session 02df60d1898d
- 5d ago First seen · 90 lines · 90 tokens per session scan A ed9da00dfd24
best-practices is a skill published in the GitHub repository vinta/hal-9000 (126 stars, last pushed today), licensed MIT. It adds 83 tokens to every session and 1,130 once invoked, about $0.0004 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 skills, from other repositories
configure-nightwatch
Configures Laravel Nightwatch data collection, sampling rates, filtering rules, and redaction policies. Use when setting up Nightwatch, managing data volume, protecting sensitive data (PII), or optimizing event collection for production workloads.
laravel-actions
Build, refactor, and troubleshoot Laravel Actions using lorisleiva/laravel-actions. Use when implementing reusable action classes (object/controller/job/listener/command), converting service classes/controllers/jobs into actions, orchestrating workflows via faked actions, or debugging action entrypoints and wiring.
debugging-output-and-previewing-html-using-ray
Use when user says "send to Ray," "show in Ray," "debug in Ray," "log to Ray," "display in Ray," or wants to visualize data, debug output, or show diagrams in the Ray desktop application.
fortify-development
ACTIVATE when the user works on authentication in Laravel. This includes login, registration, password reset, email verification, two-factor authentication (2FA/TOTP/QR codes/recovery codes), passkeys, profile updates, password confirmation, or any auth-related routes and controllers. Activate when the user mentions…
pest-testing
Use this skill for Pest PHP testing in Laravel projects only. Trigger whenever any test is being written, edited, fixed, or refactored — including fixing tests that broke after a code change, adding assertions, converting PHPUnit to Pest, adding datasets, and TDD workflows. Always activate when the user asks how to…
livewire-development
Use for any task or question involving Livewire. Activate if user mentions Livewire, wire: directives, or Livewire-specific concepts like wire:model, wire:click, invoke this skill. Covers building new components, debugging reactivity issues, real-time form validation, loading states, migrating from Livewire 2 to 3…