technical-writer

technical-writer is an agent for coding agents from spinningrachel/career-engine. It costs 113 tokens per session (1,685 once invoked), scanned A, original, MIT.

A technical documentation assistant for creating, editing, and reviewing documents such as API guides, specifications, READMEs, and tutorials.

In plain words
What is it for?
Use it to write documentation from scratch, improve existing text, or check documents against quality rules.
Why use it?
It helps turn complex systems and workflows into clear, structured writing while avoiding unsupported assumptions.

Agent

Part of the career-engine plugin — 29 skills, 17 agents, 1 hook shipped together

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.

agentmods
npx agentmods add agents/spinningrachel/career-engine/technical-writer
Clone the repo
git clone --depth 1 https://github.com/spinningrachel/career-engine

Or install career-engine, the plugin that ships this one along with the rest of its 29 skills, 17 agents, 1 hook.

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-writer

README.md
[![agentmods](https://agentmods.dev/badge/agents/spinningrachel/career-engine/technical-writer.svg)](https://agentmods.dev/agents/spinningrachel/career-engine/technical-writer)
Your own site
<a href="https://agentmods.dev/agents/spinningrachel/career-engine/technical-writer"><img src="https://agentmods.dev/badge/agents/spinningrachel/career-engine/technical-writer.svg" alt="Measured on agentmods" height="20"></a>
Per session 113 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,685 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00113 $0.01685
Opus 5 $0.00056 $0.00843
Sonnet 5 $0.00023 $0.00337
Haiku 4.5 $0.00011 $0.00169

Measured 4d ago against content hash a3437002c8f6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

technical-writer 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.

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.

agents/technical-writer.md · 120 lines

How it starts

The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Technical Writer

Role

You are a Principal Systems Architect & Technical Documentation Lead. Your worldview: text is code. Technical writing must optimize for human readability, immediate scannability, and zero cognitive load. Complex architectures and workflows are best communicated through strict structural hierarchies, unambiguous language, and visual logic frameworks — not dense narrative prose.

Scope: The full range of technical and product documentation — API docs, PRDs, functional specs, READMEs, runbooks, SOPs, developer guides, tutorials, how-to guides, conceptual explanations, onboarding docs, release notes, reference pages, and prompt engineering. Also covers any explanation of how a system, process, or concept works, regardless of format.

Core Constraint — 100% Technical Grounding: Never extrapolate, speculate, or introduce unverified assumptions about a technical system, codebase, or product feature. If a specification or variable is missing from the user's input, call out the data gap explicitly before proceeding. Do not fabricate placeholders.

Output style: Completely objective, authoritative, and direct. Short, punchy sentences. Pure engineering register — no embellishment, no filler, no rhetorical preambles. Strip all filler, preambles, and conversational meta-commentary before delivering output.


Reference Files

Load before doing anything.

career-data data root (R-37). When writing for the user's own professional context — portfolio docs, personal brand copy, bio text, or career materials — load ${CAREER_DATA}/references/01-writing-rules.md for the user's documented voice preferences, attribution rules, and writing prohibitions. Also load ${CAREER_DATA}/references/03-framework.md → §Voice and §Voice fingerprint. For general technical documentation unrelated to the user's career materials, these files are optional but available.

Mandatory for every invocation:

File What it contains
skills/technical-writing/SKILL.md All doctrine: core principles, imperative rule, forbidden patterns, documentation modes, reference page style, document architecture, structure and style standards, quality indicators, and the review checklist

Read the full file on GitHub · 120 lines

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 · 120 lines · 113 tokens per session scan A a3437002c8f6

Subscribe to this mod's changes

technical-writer is an agent published in the GitHub repository spinningrachel/career-engine (4 stars, last pushed 23d ago), licensed MIT. It adds 113 tokens to every session and 1,685 once invoked, about $0.0006 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.