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-final-report-writing-stylegit 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-final-report-writing-style)<a href="https://agentmods.dev/skills/equinor/neqsim-community-skills/neqsim-final-report-writing-style"><img src="https://agentmods.dev/badge/skills/equinor/neqsim-community-skills/neqsim-final-report-writing-style/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-final-report-writing-style"><img src="https://agentmods.dev/badge/skills/equinor/neqsim-community-skills/neqsim-final-report-writing-style.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 | $0.00075 | $0.01449 |
| Opus 5.5 | $0.00030 | $0.00580 |
| Sonnet 5.5 | $0.00015 | $0.00290 |
| Haiku 4.5 | $0.00007 | $0.00145 |
Grade A, and why
neqsim-final-report-writing-style 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 — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Final Report Writing Style
Choose a writing style only after the calculations, evidence review, and technical conclusions are complete. The selected style controls expression, not facts, scope, uncertainty, or validation.
When to Use
- Activate at the final reporting step when generating an HTML, Word, PDF, Markdown, or notebook report, or a durable generated summary.
- Activate when revising an existing final document for style.
- Activate when the user explicitly requests
prose_englishorstandard_engineering_englishfor a generated document. - Do not activate during research, analysis, calculation, source extraction, ordinary chat, interim status messages, code generation, or working notes.
Inputs
document_purpose:interpret,decide,instruct,specify,describe, ormixed.document_sections: the final sections that will be generated.audience: decision-maker, engineer, operator, maintainer, regulator, student, or general reader.user_requested_style: optionalprose_englishorstandard_engineering_english.- Mandatory templates, controlled terminology, safety wording, and accessibility constraints.
Outputs
primary_style:prose_englishorstandard_engineering_english.section_overrides: sections that require the other style, with a short reason.selection_reason: one sentence tied to reader purpose and document type.- Final narrative revised under the selected rules without changing technical content.
When the task uses results.json, record the choice as:
{
"writing_style": {
"primary": "prose_english",
"selection": "automatic",
"reason": "The report interprets evidence for an engineering decision.",
"section_overrides": {
"Operating procedure": "standard_engineering_english"
}
}
}
Engineering Method
- Check for a user request. A valid explicit request sets the primary style.
- If there is no override, select by the reader's task:
- Choose
prose_englishwhen the reader must understand evidence, compare alternatives, interpret uncertainty, or make a decision. - Choose
standard_engineering_englishwhen the reader must perform an action, reproduce a method, identify equipment, follow a limit, or interpret a requirement consistently.
- Choose
- For a mixed engineering report, use
prose_englishas the primary style. Applystandard_engineering_englishto procedures, requirements, equipment descriptions, warnings, cautions, checklists, and tightly controlled method steps. - Mandatory safety, regulatory, contractual, accessibility, and template rules take precedence over either style.
- Apply the selected style only to narrative expression. Do not alter numbers, units, citations, uncertainty, technical terminology, findings, or the direction of a recommendation.
- Record the selection and any section overrides so a reviewer can see which rules were applied.
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 · 142 lines · 75 tokens per session scan A ae6c041646c3
neqsim-final-report-writing-style is a skill published in the GitHub repository equinor/neqsim-community-skills (4 stars, last pushed today), licensed Apache-2.0. It adds 75 tokens to every session and 1,449 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-final-report-writing-style compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| neqsim-final-report-writing-styleequinor/neqsim-community-skills | Skill | 4 | today | Apache-2.0 | A | 75 | 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 |