technical-publishing

technical-publishing is a skill for Claude Code, Codex from fmind/dot. It costs 32 tokens per session (633 once invoked), scanned A, original, MIT.

A publishing workflow for technical articles, from source notes and editorial review to a canonical website version and channel-specific copy.

In plain words
What is it for?
Use it to draft, check, export, and publish technical articles through the defined package and website workflow.
Why use it?
It helps keep article packages, writing rules, visual sources, and published versions consistent while preventing unsupported claims.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

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 skills/fmind/dot/technical-publishing
Any agent
npx skills add fmind/dot --skill technical-publishing
Clone the repo
git clone --depth 1 https://github.com/fmind/dot

Made for: Claude Code, Codex.

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-publishing

README.md
[![agentmods](https://agentmods.dev/badge/skills/fmind/dot/technical-publishing.svg)](https://agentmods.dev/skills/fmind/dot/technical-publishing)
Your own site
<a href="https://agentmods.dev/skills/fmind/dot/technical-publishing"><img src="https://agentmods.dev/badge/skills/fmind/dot/technical-publishing.svg" alt="Measured on agentmods" height="20"></a>
Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 633 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 $0.00032 $0.00633
Opus 5 $0.00016 $0.00316
Sonnet 5 $0.00006 $0.00127
Haiku 4.5 $0.00003 $0.00063

Measured 2d ago against content hash 8f7b5d73bce0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

technical-publishing 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 2d 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/technical-publishing/SKILL.md · 40 lines

How it starts

The opening of the file, as written. The whole thing — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Publish Technical Articles

Publish technical articles from package sources through review, canonical web export, and channel copy. Third-party documentation sites and static websites use hugo, software releases use release, and standalone documents use typst.

pub init article <slug>                          # scaffold package directories and draft
pub check <package> --publish-ready              # offline gate; readiness, not authorization
pub publish <package> --site <site-directory>    # export to canonical site; --dry-run previews

Workflow

  1. Package pipeline: work inside the article package layout (draft.txt -> article.md -> canonical site -> posts/); draft.txt contains raw notes that agents never edit; see Package layout.
  2. Voice and boundaries: adhere to the editorial voice in Voice and identity; agree the register before drafting; never invent anecdotes, clients, or metrics; keep published articles immutable.
  3. Visuals: explanatory diagrams follow fmind-visuals and d2 using the light-surface theme; store .d2 sources beside rendered PNGs.
  4. Canonical export: export to the canonical site only when authorized; live article corrections belong on the site.
  5. Channel copy: prepare channel adaptations in posts/ (LinkedIn, X, Bluesky, Medium); channels are posted by hand, never automated or scheduled.

Gotchas

  • Channel automation: only canonical site export is automated; all other channels are manual copy-paste.
  • Immutable published copy: once published, package copy is historical; live corrections stay on the published site.
  • Anti-slop enforcement: avoid hype lead-ins, decorative lists, and empty corporate summaries; maintain the direct first-person voice.

Documentation

Read the full file on GitHub · 40 lines

Files

What ships with it

2 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. 2d ago First seen · 40 lines · 32 tokens per session scan A 8f7b5d73bce0

Subscribe to this mod's changes

technical-publishing is a skill published in the GitHub repository fmind/dot (4 stars, last pushed yesterday), licensed MIT. It adds 32 tokens to every session and 633 once invoked, about $0.0002 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.