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 vinta/hal-9000 --skill simple-englishgit 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/simple-english)<a href="https://agentmods.dev/skills/vinta/hal-9000/simple-english"><img src="https://agentmods.dev/badge/skills/vinta/hal-9000/simple-english.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 | $0.00072 | $0.00915 |
| Opus 5 | $0.00036 | $0.00458 |
| Sonnet 5 | $0.00014 | $0.00183 |
| Haiku 4.5 | $0.00007 | $0.00092 |
Grade A, and why
simple-english 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 2d 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 — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Simple English
Write or rewrite the given text in Global English: the global-audience tier that Google, Microsoft, MDN, Red Hat, and GitLab documentation follows. Clear structure, unambiguous words, translation-friendly grammar, no controlled dictionary, no hard word caps. The rewrite must give the same technical facts as the source and still sound like a native speaker wrote it.
Ground rules
- Meaning is untouchable. Every fact, value, condition, and caveat in the source survives the rewrite. Softened obligations stay soft: "should" stays a recommendation unless the source means a requirement.
- Never invent specifics. Keep each fact at its original precision and flag gaps. Do not fabricate values, names, or conditions.
- Quoted text is frozen. Code spans and blocks, commands, config keys, file paths, UI labels, error messages, and identifiers stay exactly as they are. Rewrite the prose around them.
- Voice survives. Clarity edits that flatten prose into staccato fragments are regressions. Filler drops freely ("it should be noted that"), personality stays.
Workflow
-
Load the rules. Read references/writing-rules.md in full: sentence structure, word choice, the clarity helpers, tone, and the substitution table.
-
Collect the source. Take the text from the conversation, or Read the files or sections the user pointed at. When the user wants new text drafted instead of existing text rewritten, collect the facts to convey (from the conversation, code, or files) and treat them as the source for every later step. Done when you hold every passage to rewrite or every fact to state.
-
Sort each passage into procedure (imperative work steps), description (declarative prose), or micro-text (headings, UI labels, error messages). Procedures get imperative mood and condition-first ordering. Micro-text gets a verb when clarity needs one.
-
Map the terminology. List each concept that appears under more than one name, pick one term per concept (prefer the project's established names), and use it everywhere. Done when no concept has two names and no word carries two meanings.
What ships with it
2 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.
- 2d ago Changed · +1 lines · +35 tokens per session d59d63d3762b
- 7d ago First seen · 46 lines · 37 tokens per session scan A d0606f90d99b
simple-english is a skill published in the GitHub repository vinta/hal-9000 (127 stars, last pushed yesterday), licensed MIT. It adds 72 tokens to every session and 915 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
tiny-web-crawler
Crawl from one or more starting web pages, fetch readable content, search within pages, follow relevant links, and stop when the requested information is found or a bounded limit is reached.
live-tutorial
Create an annotated MP4 tutorial from a workflow demonstrated in the owner's actual application. Use when asked for a tutorial video, not merely to watch an action live.
query-snmp-traps
Query SNMP trap logs through Netdata Cloud or directly from a Netdata Agent. Use when the user asks about SNMP traps, trap journal entries, trap severities, trap categories, trap senders, deduplication summaries, decode errors, TRAP fields, TRAPVAR indexed varbind fields, TRAPJSON varbind audit data, or how to inspect…
background-task
Add or modify work that runs outside the request/response cycle — emails, document ingestion, webhooks, cleanups, scheduled jobs. Use when something is slow or fire-and-forget, or when adding a periodic/cron task. This project's queue is {{ cookiecutter.backgroundtasks }}.
rag-knowledge
Work with the RAG knowledge base — ingest documents, run semantic search, manage collections, or add a sync source/connector (Google Drive, S3). Use when populating or debugging the knowledge base, tuning retrieval, or adding a new document source. This project uses {{ cookiecutter.vectorstore }} + {{…
alembic-migration
Create, review, and apply database schema changes with Alembic. Use whenever a SQLAlchemy model is added or changed, a column/index/constraint needs to change, or a data backfill is required — anything that alters the PostgreSQL schema.