engineering-writing

engineering-writing is a skill for Claude Code, Codex from segunadebayo/design-eng-skills. It costs 51 tokens per session (629 once invoked), scanned A, original, MIT.

A writing guide for public-facing technical articles about how a software project was built, including announcements, deep dives, and retrospectives.

In plain words
What is it for?
Use it for release announcements, engineering blog posts, how-we-built articles, and project retrospectives.
Why use it?
It helps turn engineering work into a clear narrative grounded in the real project, instead of generic technical advice.

Skill for Claude CodeCodex

Written for Claude Code and Codex: shipped in a Claude Code plugin, but also agents/openai.yaml present.

Part of the design-eng-skills plugin — 4 skills shipped together

Good fit Use it for release announcements, engineering blog posts, how-we-built articles, and project retrospectives.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/segunadebayo/design-eng-skills/engineering-writing
Install

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.

Any agent
npx skills add segunadebayo/design-eng-skills --skill engineering-writing
Clone the repo
git clone --depth 1 https://github.com/segunadebayo/design-eng-skills

Made for: Claude Code, Codex.

Or install design-eng-skills, the plugin that ships this one along with the rest of its 4 skills.

Wrote 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.

agentmods badge for engineering-writing

README.md
[![agentmods](https://agentmods.dev/badge/skills/segunadebayo/design-eng-skills/engineering-writing/github.svg)](https://agentmods.dev/skills/segunadebayo/design-eng-skills/engineering-writing)
Your own site
<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.

agentmods 80×15 button for engineering-writing

Your own site · 80×15
<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>
Per session 51 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 629 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 12d ago against content hash bdef6fc6e954, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

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.

skills/engineering-writing/SKILL.md · 41 lines

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.

Read the full file on GitHub · 41 lines

Files

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.

Changes

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.

  1. 12d ago First seen · 41 lines · 51 tokens per session scan A bdef6fc6e954

Subscribe to this mod's changes

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.