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/corezoid/corezoid-ai-plugin/corezoid-node-layoutnpx skills add corezoid/corezoid-ai-plugin --skill corezoid-node-layoutgit clone --depth 1 https://github.com/corezoid/corezoid-ai-pluginWrote 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/corezoid/corezoid-ai-plugin/corezoid-node-layout)<a href="https://agentmods.dev/skills/corezoid/corezoid-ai-plugin/corezoid-node-layout"><img src="https://agentmods.dev/badge/skills/corezoid/corezoid-ai-plugin/corezoid-node-layout.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 | $0.00215 | $0.02388 |
| Opus 5 | $0.00108 | $0.01194 |
| Sonnet 5 | $0.00043 | $0.00478 |
| Haiku 4.5 | $0.00021 | $0.00239 |
Grade A, and why
corezoid-node-layout 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 4d 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 — 201 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Auto-Layout Corezoid Process Nodes
You make a process readable: business logic as a clear vertical spine,
error handling collected in a tidy right-hand rail, nothing overlapping. This is
the mechanical companion to the positioning rules in
${CLAUDE_PLUGIN_ROOT}/docs/process/node-positioning-best-practices.md — that
doc is the source of truth for why; this skill does it deterministically.
When you MAY re-layout — and when you MUST NOT
A process's layout is part of how its author reads it. Re-flowing someone's diagram without asking is destructive even though the logic is untouched — it throws away a mental map they are used to. So the rule is about authorship, not just readability:
-
A process YOU built this session, from scratch → always lay it out. You own its positions; arrange it cleanly before
push-process. No need to ask. -
An existing / pulled / user-authored process → do NOT re-layout by default. Preserve the author's
x/y. This holds even if you just edited it — a user who is used to their arrangement must not find it rearranged. -
When you add nodes to someone else's process (an edit, not a rebuild): leave the new nodes at
x: 0, y: 0—push-processauto-places them next to their graph neighbours while keeping every existing node where it was (preserve mode; see node-positioning-best-practices.md § Automatic Placement on Push). Do not run the whole-process auto-layout — that repositions everything. Full re-layout on a foreign process happens only on request. -
The user explicitly asks ("tidy this up", "fix the positions", "make it readable" — in any language) → re-layout the whole process. This is the one case where rearranging a foreign process is wanted.
-
The process is genuinely unreadable (heavy node overlaps, a tangled mess) → don't silently fix it. Offer: briefly say it's hard to read and ask if they want it re-arranged. Re-layout only after a clear yes. If they decline, leave it exactly as is.
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.
- 4d ago First seen · 201 lines · 215 tokens per session scan A cec1f144a543
corezoid-node-layout is a skill published in the GitHub repository corezoid/corezoid-ai-plugin (73 stars, last pushed today), licensed MIT. It adds 215 tokens to every session and 2,388 once invoked, about $0.0011 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.
Other skills, from other repositories
watch
File sentinel that monitors the working directory for changes and marker comments, then auto-triggers appropriate skills. Poll-based via git diff against the last scan commit. Writes intake items for batch processing and routes marker actions through /do. Use for automatic reactions to file changes; do NOT use for…
review
5-pass structured code review — correctness, security, performance, readability, consistency.
live-preview
Mid-build visual verification loop. Takes screenshots of components during construction, not just after. Catches visual regressions and invisible features before they compound. Requires Playwright or similar screenshot tool.
marshal
Meta-orchestrator that takes any direction — broad, specific, or vague — and autonomously chains skills and context into actionable work. Gathers context from codebase, docs, and memory. Only asks the user when it genuinely cannot proceed. Single-session orchestrator.
wiki
Markdown-first knowledge base where the LLM acts as librarian. Ingests raw sources, compiles and interlinks topic files, self-maintains an index. No vector DB or embeddings required -- uses LLM-native navigation over structured markdown up to 400K words.
mindtrain
Configure a private MindTrain instance, query its knowledge catalog, create user-approved training domains and knowledge points from AI dialogue or local reference libraries, and run persistent conversational training through Trainer MCP. Use when the user configures MindTrain, asks what domains or topics exist…