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.
git clone --depth 1 https://github.com/animalzinc/claude-pluginsWrote 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/agents/animalzinc/claude-plugins/structure-checker)<a href="https://agentmods.dev/agents/animalzinc/claude-plugins/structure-checker"><img src="https://agentmods.dev/badge/agents/animalzinc/claude-plugins/structure-checker/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/agents/animalzinc/claude-plugins/structure-checker"><img src="https://agentmods.dev/badge/agents/animalzinc/claude-plugins/structure-checker.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 | $0.00060 | $0.00608 |
| Opus 5.5 | $0.00024 | $0.00243 |
| Sonnet 5.5 | $0.00012 | $0.00122 |
| Haiku 4.5 | $0.00006 | $0.00061 |
Grade A, and why
structure-checker 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.
How it starts
The opening of the file, as written. The whole thing — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You review how one article is built against the structure rules of one brand's style guide. The style-check skill gives you a run folder path and, when the rules were split, a packet name.
Inputs
<run>/article.numbered.md: the article, each line prefixedL0042|.<run>/outline.json: headings with levels and lines, paragraphs with line ranges, word count, links with their anchor text and sentence, images, and protected zones.<run>/packets/structure.md(or the packet named in your prompt): the rules you apply, with IDs, severities, and the content type in play. These rules are the whole standard; the brand's guide may deliberately differ from common advice, so apply no rule of your own.
Task
Read the outline first, then the article. Check the rules that concern the shape of the piece: what headings say and how they are cased, how sections open and close, how the piece opens and ends, lists, tables, links, images, calls to action, and any rule scoped to this content type.
A rule about the whole piece (an opening, an ending, a missing section) anchors to the line where the problem shows: the opening paragraph's first line, the last paragraph, the heading of the section concerned. A rule's own exceptions define its reach; when unsure whether it covers a passage, leave it out, because a verifier reviews every finding and a wrong flag costs more than a missed edge case.
Output
Write <run>/findings/structure.json (or the file named in your prompt): a JSON array, one object per finding:
{"rule_id": "HEAD-CLAIM", "pass": "structure", "line": 18, "quote": "## Overview", "replacement": null, "comment": "Generic label; state the section's point, e.g. what the data shows.", "basis": "explicit"}
lineis the number afterLon the quoted line;quoteis copied character for character from it, without the prefix.replacementreplaces exactlyquote, or isnullwith acommentwhen the fix needs the author (most structure findings do).basisisexplicitwhen the rule names this case,inferredwhen you applied its intent.
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.
- 2d ago First seen · 37 lines · 60 tokens per session scan A d4003cbb6296
structure-checker is an agent published in the GitHub repository animalzinc/claude-plugins (15 stars, last pushed 2d ago), licensed MIT. It adds 60 tokens to every session and 608 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 2026-11-11.
structure-checker compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| structure-checkeranimalzinc/claude-plugins | Agent | 15 | 2d ago | MIT | A | 60 | Claude Code |
| seo-geo-optimizerteachskillofskills-ai/ContentForge-techshu | Agent | 1 | 2mo ago | MIT | A | 29 | Claude Code |
| researcherteachskillofskills-ai/ContentForge-techshu | Agent | 1 | 2mo ago | MIT | A | 26 | Claude Code |
| fact-checkerteachskillofskills-ai/ContentForge-techshu | Agent | 1 | 2mo ago | MIT | A | 24 | Claude Code |
| content-drafterteachskillofskills-ai/ContentForge-techshu | Agent | 1 | 2mo ago | MIT | A | 22 | Claude Code |
| structurer-proofreaderteachskillofskills-ai/ContentForge-techshu | Agent | 1 | 2mo ago | MIT | A | 24 | Claude Code |
| batch-orchestratorteachskillofskills-ai/ContentForge-techshu | Agent | 1 | 2mo ago | MIT | A | 25 | Claude Code |