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 equinor/neqsim-community-skills --skill neqsim-standard-engineering-englishgit clone --depth 1 https://github.com/equinor/neqsim-community-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/equinor/neqsim-community-skills/neqsim-standard-engineering-english)<a href="https://agentmods.dev/skills/equinor/neqsim-community-skills/neqsim-standard-engineering-english"><img src="https://agentmods.dev/badge/skills/equinor/neqsim-community-skills/neqsim-standard-engineering-english/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/equinor/neqsim-community-skills/neqsim-standard-engineering-english"><img src="https://agentmods.dev/badge/skills/equinor/neqsim-community-skills/neqsim-standard-engineering-english.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 | $0.00085 | $0.01533 |
| Opus 5.5 | $0.00034 | $0.00613 |
| Sonnet 5.5 | $0.00017 | $0.00307 |
| Haiku 4.5 | $0.00009 | $0.00153 |
Grade A, and why
neqsim-standard-engineering-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 1mo 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 — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Standard Engineering English
standard_engineering_english is the short alias for this style. It is a compact house style
inspired by ASD-STE100. It does not reproduce the ASD-STE100 dictionary and does not establish
ASD-STE100 compliance.
When to Use
- Use during the final reporting step for procedures, operating steps, equipment descriptions, technical requirements, warnings, cautions, limits, checklists, and method summaries.
- Use for generated summaries whose main purpose is repeatable action or unambiguous technical interpretation.
- Use whenever the user explicitly requests
standard_engineering_english. - Do not activate for analysis notes, ordinary chat, source extraction, or code.
Inputs
- Verified technical content, actions, conditions, limits, hazards, units, and terminology.
- The project glossary, approved component names, abbreviations, and spelling convention.
- The document type: procedure, description, requirement, safety instruction, or summary.
- Mandatory regulatory wording and an optional explicit user style choice.
Outputs
- Short, complete sentences with stable terminology and explicit logical relations.
- Procedures with conditions before commands and normally one instruction per sentence.
- Descriptions organized around one subject per sentence and one topic per paragraph.
- A style record of
standard_engineering_englishwhen the reporting workflow records provenance.
Engineering Method
- Build or use the project glossary. Use one preferred term for each concept and one meaning for each term. Do not vary synonyms merely to improve rhythm.
- Use a word in its approved meaning and grammatical role. If a familiar word is ambiguous, rewrite the sentence instead of relying on context.
- Use the project spelling convention consistently. If none exists, use American spelling. Preserve spelling in quotations and official names.
- Keep sentences complete. State the subject and verb, and include articles where normal English requires them. Do not use contractions.
- Prefer active voice. In descriptive text, use passive voice when the agent is unknown or unimportant. Never invent an agent to avoid passive voice.
- Keep noun clusters short. Aim for no more than three consecutive nouns. Expand longer clusters with a preposition, relative clause, or defined short form.
- Put conditions before actions. In a procedure, begin the action with an imperative verb and normally give one instruction per sentence. Combine actions only when they occur at the same time.
- Keep procedural sentences at 20 words or fewer where practical. Keep descriptive sentences and notes at 25 words or fewer where practical. Split a sentence before deleting necessary meaning.
- Give one subject per descriptive sentence, one topic per paragraph, and no more than six sentences per paragraph where practical.
- Use notes only for information. Do not hide actions, requirements, limits, or safety controls in a note.
- For safety text, state the condition or command, the hazard, and the consequence. Use
warningfor risk of injury or death andcautionfor equipment damage only when that distinction matches the governing domain standard. - Use vertical lists when they make complex alternatives or sequences easier to scan. Keep all items grammatically parallel and do not mix procedures with descriptions in one list.
- Follow the project rules for units, numbers, symbols, abbreviations, and typography. This style does not define those conventions.
What ships with it
5 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.
- 1mo ago First seen · 135 lines · 85 tokens per session scan A 3ed68e0b1450
neqsim-standard-engineering-english is a skill published in the GitHub repository equinor/neqsim-community-skills (4 stars, last pushed today), licensed Apache-2.0. It adds 85 tokens to every session and 1,533 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-19.
neqsim-standard-engineering-english compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| neqsim-standard-engineering-englishequinor/neqsim-community-skills | Skill | 4 | today | Apache-2.0 | A | 85 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |