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 segunadebayo/design-eng-skills --skill engineering-writinggit clone --depth 1 https://github.com/segunadebayo/design-eng-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/segunadebayo/design-eng-skills/engineering-writing)<a href="https://agentmods.dev/skills/segunadebayo/design-eng-skills/engineering-writing"><img src="https://agentmods.dev/badge/skills/segunadebayo/design-eng-skills/engineering-writing/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/segunadebayo/design-eng-skills/engineering-writing"><img src="https://agentmods.dev/badge/skills/segunadebayo/design-eng-skills/engineering-writing.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 | $0.00051 | $0.00629 |
| Opus 5 | $0.00026 | $0.00315 |
| Sonnet 5 | $0.00010 | $0.00126 |
| Haiku 4.5 | $0.00005 | $0.00063 |
Grade A, and why
engineering-writing 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 12d 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 — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Engineering Writing
Narrative, external-facing technical writing, built from reading real engineering blogs end to end and cross-checking against writing-craft, persuasion, and copywriting research, not from generic advice about "good writing." Every technique in the references below is attributed to where it actually came from.
1. Know which register you're writing
An announcement, a how-we-built-X deep-dive, or a retrospective answer different reader questions and take different shapes. Decide this first. references/REGISTERS.md.
2. Diagnose the reader and find what's actually remarkable
What does the reader already believe, and is there a genuinely surprising fact here, or is this the same generic post everyone already wrote? Don't draft until you have a real answer to both. references/PERSUASION-ETHICS.md and references/METHODOLOGY.md.
3. Draft badly and fast, separate from editing
Write the one small section you understand completely, not the whole piece at once. Cutting happens later, as its own pass. references/METHODOLOGY.md.
4. Choose the opening on purpose
Nine real patterns, cold scene, concrete problem, disarming confession, myth-then-dismantle, reframed word, credentials-then-claim, TL;DR, tension, two-sentence tradeoff, pick the one that fits what you actually have. references/OPENINGS-AND-MOMENTUM.md.
5. Structure for momentum
Every sentence's job is to get the next one read. Reveal iteratively, show the alternatives you rejected, end sections with a reason to keep going. references/OPENINGS-AND-MOMENTUM.md.
6. Write in plain voice, cut the slop
Second person, short sentences, a number or name behind every claim. No em dashes, no decorative emoji, no hype words, no AI-tell phrases. Run the checklist before you ship. references/VOICE-AND-SLOP.md.
What ships with it
6 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.
- 12d ago First seen · 41 lines · 51 tokens per session scan A bdef6fc6e954
engineering-writing is a skill published in the GitHub repository segunadebayo/design-eng-skills (6 stars, last pushed 1mo ago), licensed MIT. It adds 51 tokens to every session and 629 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
ensembl-database
Query Ensembl genome database REST API for 250+ species. Gene lookups, sequence retrieval, variant analysis, comparative genomics, orthologs, VEP predictions, for genomic research.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.
aatmf-t10-confidentiality-breach
AATMF T10 — Integrity & Confidentiality Breach. System prompt extraction, training-data extraction, model-weight leakage, private-key recovery.
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
omh-rust
This is a Hermes-native rust workflow skill.
lazarus-group
Adversary-emulation profile for Lazarus Group (G0032, aka Hidden Cobra / Diamond Sleet / Labyrinth Chollima), a North Korean RGB-linked actor conducting espionage, destructive, and financially motivated operations.