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.
npx agentmods add skills/code-katz/claude-publish-agent/publishnpx skills add code-katz/claude-publish-agent --skill publishgit clone --depth 1 https://github.com/code-katz/claude-publish-agentWrote 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.
[](https://agentmods.dev/skills/code-katz/claude-publish-agent/publish)<a href="https://agentmods.dev/skills/code-katz/claude-publish-agent/publish"><img src="https://agentmods.dev/badge/skills/code-katz/claude-publish-agent/publish.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00070 | $0.02710 |
| Opus 5 | $0.00035 | $0.01355 |
| Sonnet 5 | $0.00014 | $0.00542 |
| Haiku 4.5 | $0.00007 | $0.00271 |
Grade A, and why
publish 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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 259 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Publish Skill
This skill publishes markdown files to blogging platforms using the claude-publish CLI tool.
Prerequisites
The claude-publish CLI must be installed (the package is not on PyPI; install from the repo):
pipx install git+https://github.com/code-katz/claude-publish-agent
The gh CLI must be installed and authenticated (for GitHub Gist creation):
gh auth status
Remote/cloud sessions: Claude Code web and remote environments usually do not have gh (or the pipx CLI) installed. In those sessions, create the gist through the GitHub MCP server if one is connected, or draft and format the post there and defer the publish step to a local session. Do not dead-end at Step 5; say which path applies.
Trigger Conditions
Activate this skill when the user:
- Says "/publish", "publish this", "publish to Medium", "post this to Medium"
- Says "push this to my blog", "share this on Medium"
- References publishing, posting, or sharing a markdown file to a blogging platform
- Has just finished writing or editing a blog post and wants to publish it
Content Kit (publish/ directory)
The publish/ directory at the project root is the content kit — it stores branding assets and style guidance that ensure published content is on-brand and consistent.
Expected Structure
publish/
├── style-guide.md # Colors, typography, image style, voice/tone
├── images/
│ └── {project}-header.svg # SVG banner for README and blog posts (1280×320)
├── posts/ # Blog post files (post-{NN}-{slug}.md)
├── boilerplate.md # (optional) Standard footer, CTAs, about section
└── tags.json # (optional) Default tags per platform
Content Kit Detection
Before every publish action, check if the project has a publish/ directory:
- If
publish/style-guide.mdexists: Read it and use its guidance when the user asks you to draft, review, or format content for this project. Reference the color palette, typography, and image style when generating illustrations or diagrams.
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.
- 5d ago First seen · 259 lines · 70 tokens per session scan A f10c75d8de1c
publish is a skill published in the GitHub repository code-katz/claude-publish-agent (2 stars, last pushed 1mo ago), licensed MIT. It adds 70 tokens to every session and 2,710 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.
Other skills, from other repositories
export-pdf
Convert a markdown file to PDF using mdpdf. Use when exporting proposals, SOPs, or any markdown document to PDF.
markstream-react
Integrate the beta markstream-react package into a React 18+ or Next app. Use when Codex needs to add the React renderer, choose the root, next, or server entrypoint, import CSS correctly, choose between content and nodes, keep client boundaries safe, add renderer-local streamingComponents or htmlComponents, use…
rag-retrieval
Retrieval-Augmented Generation patterns for grounded LLM responses. Use when building RAG pipelines, embedding documents, implementing hybrid search, contextual retrieval, HyDE, agentic RAG, multimodal RAG, query decomposition, reranking, or pgvector search.
dev
One-command dev loop boot. Spins up portless (named HTTPS subdomain), emulate (stateful API mocks), the project's dev server, and an agent-browser session, all keyed to the current git branch. Use when starting a feature branch, switching worktrees, or returning to a project after a break. Skips silently with install…
publish-report
Publish local HTML, Markdown, or built static web projects with Pagecast as shareable public URLs. Use whenever Codex creates or finishes an .html, .htm, .md, .markdown, or static build output that a person could share (a report, plan, doc, dashboard, or analysis) — proactively offer to publish it without being asked…
alive:system-upgrade
Upgrade ALIVE to the current version. Handles v1/v2/v3.x source states, multi-surface aware (alive-mcp / Hermes / Codex), retroactive version detection, partial-failure resume, dry-run previews, and rollback inspection.