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 skills add mooqii/OpenPanels --skill publication-layout-defaultgit clone --depth 1 https://github.com/mooqii/OpenPanelsWrote 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/mooqii/openpanels/publication-layout-default)<a href="https://agentmods.dev/skills/mooqii/openpanels/publication-layout-default"><img src="https://agentmods.dev/badge/skills/mooqii/openpanels/publication-layout-default/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/mooqii/openpanels/publication-layout-default"><img src="https://agentmods.dev/badge/skills/mooqii/openpanels/publication-layout-default.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00043 | $0.00631 |
| Opus 5.5 | $0.00017 | $0.00252 |
| Sonnet 5.5 | $0.00009 | $0.00126 |
| Haiku 4.5 | $0.00004 | $0.00063 |
Grade A, and why
publication-layout-default 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 2mo 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Default Publication Layout
Improve the reading structure, not the author's argument. Work in three passes.
1. Diagnose
Read the complete title and document before editing. Identify:
- the opening, main ideas, topic shifts, examples, and conclusion;
- walls of text containing multiple complete ideas;
- paragraphs that mix unrelated topics or fragments that belong together;
- genuine section labels, parallel items, sequences, and quotations.
Do not mistake a change in formatting for a change in subject. Treat the captured publication title as context and do not duplicate it in the body.
2. Restructure
Apply the smallest set of changes that makes the article easy to follow.
- Paragraphs come first. Give each paragraph one main idea. Split a long paragraph at clear topic shifts, examples, contrasts, consequences, or transitions. Merge accidental fragments that form one idea. A document must not remain a single wall of text when clear paragraph boundaries exist.
- Use headings for real sections. Preserve existing headings and repair inconsistent levels. In a longer article, you may add a short, neutral heading where an unmistakable section boundary lacks one. Prefer words already present in the article. Do not over-section short prose, promote ordinary sentences, duplicate the publication title, or use a heading with only one trivial paragraph beneath it.
- Use semantic structures only when earned. Convert genuinely parallel items or sequential steps to bullet or ordered lists. Use blockquotes only for actual quoted passages. Never create a one-item list or turn ordinary promotional prose into a quotation.
- Keep emphasis restrained. Preserve meaningful bold and italic marks. Add them only to a small number of key terms or conclusions when they improve scanning; never emphasize whole paragraphs or decorate every section.
- Polish lightly. Fix obvious punctuation, spacing, and paragraph-boundary errors. Make only minimal transition or wording edits needed after restructuring. Do not invent claims, examples, data, summaries, or calls to action, and do not alter the author's position or voice.
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.
- 2mo ago First seen · 63 lines · 43 tokens per session scan A 9f1816989794
publication-layout-default is a skill published in the GitHub repository mooqii/OpenPanels (8 stars, last pushed 3mo ago), licensed MIT. It adds 43 tokens to every session and 631 once invoked, about $0.0002 per session on Opus 5.5. 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.
publication-layout-default compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| publication-layout-defaultmooqii/OpenPanels | Skill | 8 | 3mo ago | MIT | A | 43 | Claude Code, Codex |
| image-generationbytedance/deer-flow | Skill | 85k | yesterday | MIT | A | 42 | Claude Code, Codex |
| podcast-generationbytedance/deer-flow | Skill | 85k | yesterday | MIT | A | 38 | Claude Code, Codex |
| skill-reviewerbytedance/deer-flow | Skill | 85k | yesterday | MIT | A | 38 | Claude Code |
| surprise-mebytedance/deer-flow | Skill | 85k | yesterday | MIT | A | 67 | Claude Code, Codex |
| managing-mcp-serversJetBrains/thinkrail | Skill | 7.8k | yesterday | Apache-2.0 | A | 62 | Claude Code, Codex |
| todosJetBrains/thinkrail | Skill | 7.8k | yesterday | Apache-2.0 | A | 58 | Claude Code, Codex |