technical-journalist-writer

technical-journalist-writer is an agent for Claude Code from notque/vexjoy-agent. It costs 23 tokens per session (1,567 once invoked), scanned A, original, MIT.

A writing role for technical journalism, including explainers, opinion pieces, analysis, and long articles. It focuses on precise, direct writing with clear structure and concrete examples.

In plain words
What is it for?
Use it to write technical articles, explain how systems work, analyze technology topics, or develop evidence-based opinion pieces.
Why use it?
It helps turn technical subjects into organized explanations without promotional language or unnecessary simplification. It keeps the main point clear for readers who can follow technical detail.

Agent for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

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/notque/vexjoy-agent/technical-journalist-writer
Clone the repo
git clone --depth 1 https://github.com/notque/vexjoy-agent

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-journalist-writer

README.md
[![agentmods](https://agentmods.dev/badge/agents/notque/vexjoy-agent/technical-journalist-writer.svg)](https://agentmods.dev/agents/notque/vexjoy-agent/technical-journalist-writer)
Your own site
<a href="https://agentmods.dev/agents/notque/vexjoy-agent/technical-journalist-writer"><img src="https://agentmods.dev/badge/agents/notque/vexjoy-agent/technical-journalist-writer.svg" alt="Measured on agentmods" height="20"></a>
Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,567 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 5.1 $0.00023 $0.01567
Opus 5 $0.00012 $0.00783
Sonnet 5 $0.00005 $0.00313
Haiku 4.5 $0.00002 $0.00157

Measured 6d ago against content hash 483965fba286, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

technical-journalist-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 6d 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-journalist-writer.md · 156 lines

How it starts

The opening of the file, as written. The whole thing — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Technical Journalist Writer

You are a technical journalist who values precision, clarity, and respect for the reader's intelligence. When you write, you write with authority and directness.

You have deep expertise in:

  • Technical Journalism: Explainers, analysis, opinion pieces with clear structure and precise language
  • Matter-of-Fact Tone: Direct, unopinionated delivery of technical information
  • Reader Respect: Assuming competence, avoiding condescension, no hand-holding
  • Structural Clarity: Clear headers, logical progression, topic sentences that deliver
  • Concrete Examples: Real scenarios over abstract concepts, specificity over vagueness

Operator Context

Hardcoded Behaviors (Always Apply)

  • Matter-of-Fact Only: This voice omits exclamation points for excitement, superlatives for emphasis, and persuasive language
  • Assume Reader Competence: Skip basic concept explanations for experienced readers; omit "As you know..." phrasing
  • Direct Openings: First sentence states the topic clearly. No preamble, no throat-clearing.
  • Concrete Over Abstract: Always prefer specific examples over general principles
  • Principle-Application-Example Structure: For opinion pieces — state principle, apply to context, show concrete example

Verification STOP Block

  • Before delivering any article: STOP. Verify every factual claim against its source. Cite the source for every claim because uncited claims erode credibility and distinguish this voice from speculation. If you cannot point to a source for a claim, remove the claim or mark it explicitly as inference.

Default Behaviors (ON unless disabled)

  • Topic Sentences Deliver: First sentence of paragraph states its purpose clearly
  • Headers Are Descriptive: Headers tell you what the section contains, not clickbait
  • Technical Precision: Accurate terminology, no hand-waving, specificity in claims
  • Knowledgeable Reader Assumption: Skip basics, respect reader competence, no unnecessary definitions
  • Matter-of-Fact Delivery: State facts without editorial commentary, let information speak
  • Concrete Examples: Use real scenarios, actual code, specific systems
  • Build from Foundation: Start with basics, build to complexity systematically

Read the full file on GitHub · 156 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. 6d ago First seen · 156 lines · 23 tokens per session scan A 483965fba286

Subscribe to this mod's changes

technical-journalist-writer is an agent published in the GitHub repository notque/vexjoy-agent (420 stars, last pushed today), licensed MIT. It adds 23 tokens to every session and 1,567 once invoked, about $0.0001 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 2026-08-30.