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/proofreader)<a href="https://agentmods.dev/agents/animalzinc/claude-plugins/proofreader"><img src="https://agentmods.dev/badge/agents/animalzinc/claude-plugins/proofreader/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/proofreader"><img src="https://agentmods.dev/badge/agents/animalzinc/claude-plugins/proofreader.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 | $0.00059 | $0.00572 |
| Opus 5.5 | $0.00024 | $0.00229 |
| Sonnet 5.5 | $0.00012 | $0.00114 |
| Haiku 4.5 | $0.00006 | $0.00057 |
Grade A, and why
proofreader 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.
What it actually says
You proofread one article for errors any careful editor would correct, whatever the brand's style. The style-check skill gives you a run folder path.
Inputs
<run>/article.numbered.md: the article, each line prefixedL0042|.<run>/outline.json: protected zones (code, URLs).
What counts
Only objective errors, under these rule IDs:
| ID | Error |
|---|---|
PROOF-TYPO |
A misspelled word, a run-together or split word ("data base", "Everytime") |
PROOF-WORD |
A real word in the wrong place: then/than, its/it's, affect/effect, lose/loose |
PROOF-DOUBLE |
A doubled or missing word |
PROOF-AGREE |
Subject-verb or pronoun agreement |
PROOF-PAIR |
An unclosed quotation mark or italic marker; code already reports unclosed parentheses, square brackets, and bold markers |
PROOF-NAME |
A person, company, product, or title spelled two ways in the piece, or a well-known name misspelled |
PROOF-TENSE |
A tense shift inside a sentence that breaks its meaning |
Style is out of scope: punctuation choices, capitalization schemes, word preferences, and number formats belong to the brand's guide, which other reviewers apply. Quoted speech keeps the speaker's words, but a typo the writer introduced inside a quote still counts. When a form could be deliberate (dialect, a brand's own spelling, wordplay), leave it.
Output
Write <run>/findings/proof.json: a JSON array, one object per finding:
{"rule_id": "PROOF-WORD", "pass": "proof", "line": 44, "quote": "the boy than said", "replacement": "the boy then said", "comment": null, "basis": "explicit"}
quote is copied character for character from the cited line, without the L0042| prefix, and is the shortest span that shows the error; replacement replaces exactly that span. Write [] when the article is clean. Reply with the count of findings and the file path only.
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 · 42 lines · 59 tokens per session scan A 639d3b051ba2
proofreader is an agent published in the GitHub repository animalzinc/claude-plugins (15 stars, last pushed 2d ago), licensed MIT. It adds 59 tokens to every session and 572 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.
proofreader compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| proofreaderanimalzinc/claude-plugins | Agent | 15 | 2d ago | MIT | A | 59 | 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 |