technical-writing

technical-writing is a skill for Claude Code from kouroshez/coding-os. It costs 174 tokens per session (1,438 once invoked), scanned A, original, Apache-2.0.

A writing guide for documentation, project decisions, runbooks, API references, release notes, and code comments. It helps match the amount of detail to what the reader needs to decide or do.

In plain words
What is it for?
Use it when writing or reviewing developer documentation, specifications, migration notes, playbooks, and comments.
Why use it?
It makes technical prose easier to scan and act on, while reducing vague, misplaced, or repetitive explanations.

Skill for Claude Code

Written for Claude Code: paths in frontmatter.

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is [docs/governance/docs-system.md](../../../docs/governance/docs-system.md) (SSOT).**.

Good fit Use it when writing or reviewing developer documentation, specifications, migration notes, playbooks, and comments.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/kouroshez/coding-os
agentmods
npx agentmods add skills/kouroshez/coding-os/technical-writing

Made for: Claude Code.

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 technical-writing

README.md
[![agentmods](https://agentmods.dev/badge/skills/kouroshez/coding-os/technical-writing.svg)](https://agentmods.dev/skills/kouroshez/coding-os/technical-writing)
Your own site
<a href="https://agentmods.dev/skills/kouroshez/coding-os/technical-writing"><img src="https://agentmods.dev/badge/skills/kouroshez/coding-os/technical-writing.svg" alt="Measured on agentmods" height="20"></a>
Per session 174 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,438 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 $0.00174 $0.01438
Opus 5 $0.00087 $0.00719
Sonnet 5 $0.00035 $0.00288
Haiku 4.5 $0.00017 $0.00144

Measured 4d ago against content hash fdb939c94fa8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

technical-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 4d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/new_doc.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

src/core/skills/technical-writing/SKILL.md · 86 lines

How it starts

The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Technical Writing

Docs are the contract (Rule 0/19) — code follows prose, not the reverse. A doc that buries its point, mixes altitudes, or restates the code is worse than no doc: it costs every future reader the time to discover it's useless. This skill makes "a reader acts on it the first time" the bar.

Scaffold a doc with the house header already correct: python3 scripts/new_doc.py --layer playbook --domain BACKEND --title "Service X runbook" --root docs/playbooks

The doc system — taxonomy, layers, naming, header rules — is governed by docs/governance/docs-system.md (SSOT). This skill is the craft layer on top: how to write each layer well.

The five craft rules

  1. Altitude — match detail to the reader's decision. An index routes; a playbook sequences; a reference exhausts; an ADR justifies. Don't put reference-grade tables in a playbook, or hand-wave in a spec. Ask "what does the reader decide here?" and write exactly that.
  2. One idea per section. A heading is a promise. If a section covers two things, split it. The reader scans headings first — they must predict content.
  3. Active voice, present tense, specific subject. "The hook blocks the write" not "the write may be blocked". Name the actor.
  4. Specificity over vagueness. "completes in <50 ms on the highest-degree hub" beats "is fast". Numbers, file paths, exact commands — never "appropriately" or "as needed".
  5. Bad→good for every rule. Show the failure and the fix. Prose advice the reader can't anchor to an example is weak.

Full sentence/paragraph craft → references/writing-craft.md.

The coding-os doc-header + navigation contract

Every active doc opens with a machine-readable header + nav block; regen_doc_index.py depends on it — malformed, and the doc is invisible to its index. The canonical field spec is owned by docs/governance/docs-system.md (it ships to every project); don't carry a second copy. Or scaffold it correctly with new_doc.py. Shape, for orientation:

Read the full file on GitHub · 86 lines

Files

What ships with it

4 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. 4d ago First seen · 86 lines · 174 tokens per session scan A fdb939c94fa8

Subscribe to this mod's changes

technical-writing is a skill published in the GitHub repository kouroshez/coding-os (6 stars, last pushed yesterday), licensed Apache-2.0. It adds 174 tokens to every session and 1,438 once invoked, about $0.0009 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 2026-09-03.

Related

Other skills, from other repositories

potpie-source-ingestion

Use when the user explicitly asks to ingest, refresh, or deeply understand a repository, PR, issue, ticket, runbook, incident report, document, or web link into Potpie. The harness performs todo-driven discovery, uses local/GitHub/integration tools and read-only subagents when available, builds evidence-backed…

potpie-ai/potpie · 82 tokens

booboo-vault

Emit a Booboo brain as a wiki-linked markdown vault for Obsidian, author authored edges with double-bracket links, and read the ingestion quality gate. Use when someone wants their system as plain files, an Obsidian second brain generated from real data, a portable insurance copy, or wants to know why their orphan…

jessymariau/booboo · 76 tokens

typescript-providers

Implement, modify, test, or document TypeScript provider packages under ts/packages/providers, including framework adapters for OpenAI, Anthropic, Google, LangChain, Mastra, Vercel, LlamaIndex, Cloudflare, and Claude Agent SDK. Use for provider-specific TS work; do not use for core-only changes.

ComposioHQ/composio · 70 tokens

graph-mutation-plan

Cookbook for composing an applygraphmutations plan — stable entitykey patterns, the canonical label/edge vocabulary, evidence/invalidation/confidence discipline, and a worked example. Load this when building a non-trivial mutation plan.

potpie-ai/potpie · 51 tokens

potpie-cli

Use when the task is centered on running, explaining, configuring, or troubleshooting the potpie command: doctor, login, pot management, source registration, search, graph workbench reads/writes, and pot scope behavior.

potpie-ai/potpie · 50 tokens

potpie-change-timeline

Use when an agent needs recent or historical change context: what changed recently, regressions, merged PRs, tickets, docs, incidents, deployments, releases, and source-history ingestion.

potpie-ai/potpie · 43 tokens