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 tomzx/agents --skill create-article-plangit clone --depth 1 https://github.com/tomzx/agentsWrote 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/tomzx/agents/create-article-plan)<a href="https://agentmods.dev/skills/tomzx/agents/create-article-plan"><img src="https://agentmods.dev/badge/skills/tomzx/agents/create-article-plan/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/tomzx/agents/create-article-plan"><img src="https://agentmods.dev/badge/skills/tomzx/agents/create-article-plan.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 | $0.00074 | $0.01357 |
| Opus 5.5 | $0.00030 | $0.00543 |
| Sonnet 5.5 | $0.00015 | $0.00271 |
| Haiku 4.5 | $0.00007 | $0.00136 |
Grade A, and why
create-article-plan 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 17d 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 — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan Article
Settles a long-form article's argument and structure before any prose is written, so the core insight, section order, and evidence can be checked while they are still cheap to change.
The output is a plan.md next to the target article, and it becomes the input to /create-article.
Prerequisites
- Target article: the intended topic and the file path the article will be written to (or at least its directory)
- Audience: who will read the article
- Sources: the research brief from
/research-article, or a set of sources (URLs, file paths, inline content) - Format (optional): long-form essay, tracker, or another structure. Infer it when not stated.
If sources are not yet gathered, run /research-article first and plan from its brief.
The brief's "Recommendation for the Article" already proposes a core insight and angle, which the plan turns into a concrete structure.
If you decide not to run it, say so and give your reasoning before proceeding, so the user can course-correct.
When to Plan
Plan a long-form article (roughly four or more sections, or any article whose structure is not fixed by a template).
Skip the plan for a short templated piece (for example a research note on a fixed skeleton, roughly one screen): the template is the plan, so a plan.md would only duplicate it.
When revising an existing article, plan only when the revision changes the argument or the section structure; otherwise edit the article in place.
Plan Structure
Write plan.md next to the target article file.
Keep it to about one screen: it records the argument and structure, not the prose.
---
artifact: article-plan
audience: <target audience>
status: draft
---
# Article Plan: <working title>
## Core insight
<One sentence: the single thesis the article argues.>
## Audience and calibration
<Who reads it, the prior knowledge assumed, and the tone and depth to use.>
## Format and length
<Long-form essay / research note / tracker, and the target length.>
## Section outline
### <Section title>
- Claim: <what this section establishes.>
- Evidence: <the sources that support the claim, with links.>
- Visualization: <the planned figure, or "none".>
### <Section title>
- Claim: ...
- Evidence: ...
- Visualization: ...
## Opening and takeaway
- Hook: <how the article opens, leading with the most important point.>
- Takeaway: <what the reader should think or do after reading.>
## Non-goals
- <What to leave out, to prevent scope creep.>
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.
- 17d ago First seen · 144 lines · 74 tokens per session scan A 360d26ab2a3d
create-article-plan is a skill published in the GitHub repository tomzx/agents (13 stars, last pushed yesterday), licensed MIT. It adds 74 tokens to every session and 1,357 once invoked, about $0.0003 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 2026-10-13.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…