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 flukeatzerocool/infobroker --skill proofreadinggit clone --depth 1 https://github.com/flukeatzerocool/infobrokerWrote 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/flukeatzerocool/infobroker/proofreading)<a href="https://agentmods.dev/skills/flukeatzerocool/infobroker/proofreading"><img src="https://agentmods.dev/badge/skills/flukeatzerocool/infobroker/proofreading/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/flukeatzerocool/infobroker/proofreading"><img src="https://agentmods.dev/badge/skills/flukeatzerocool/infobroker/proofreading.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 | $0.00050 | $0.00877 |
| Opus 5.5 | $0.00020 | $0.00351 |
| Sonnet 5.5 | $0.00010 | $0.00175 |
| Haiku 4.5 | $0.00005 | $0.00088 |
Grade A, and why
proofreading 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 16d 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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Proofreading
When NOT to Use
- For creative writing where intentional rule-breaking is part of the voice.
- When the user wants a full rewrite rather than corrections.
Workflow
-
Establish the baseline. Before changing anything, identify the document's regional spelling (American or British), register, and any deliberate stylistic fragments. A consistent convention is authoritative: do not normalize it to another variant, and do not expand deliberate fragments. If the document is genuinely inconsistent, use the dominant convention and note the choice.
-
Grammar check. Fix subject-verb agreement, tense errors, dangling modifiers, fragments, and run-on sentences.
-
Spelling and word choice. Catch misspellings, homophones, and words used in the wrong context. Verify domain terms.
-
Punctuation. Review commas, semicolons, colons, dashes, hyphens, apostrophes, and quotation marks according to the style guide.
-
Style and consistency. Enforce heading capitalization, number formatting, abbreviations, passive voice, and consistent terminology. Verify the document conforms to any design philosophy or principles it declares (e.g., simplicity, no jargon, beginner-friendly). Flag deviations from that philosophy.
-
Clarity and readability. Flag long sentences, dense paragraphs, and jargon. Provide a readability score if useful.
-
Tone check. Ensure the tone matches the user's intent. Flag tonal shifts.
Output Format
Provide the corrected text and an annotated list of changes with original,
correction, and reason. Number each correction PR-<n> so it can be
referenced downstream:
1. PR-1 [location]: "original" → "correction" — [reason].
2. PR-2 [location]: "original" → "correction" — [reason].
Output Contract
Always produce a searchable one-line status:
proofread passed. [scope] — N corrections
The token is grep-able by build-review (as an Evidence: source) and
after-action-report (follow-through register).
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.
- 16d ago Changed · +10 lines 281a719581bf
- 2mo ago First seen · 102 lines · 50 tokens per session scan A 034085d2c834
proofreading is a skill published in the GitHub repository flukeatzerocool/infobroker (1 stars, last pushed 2d ago), licensed MIT. It adds 50 tokens to every session and 877 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.
proofreading compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| proofreadingflukeatzerocool/infobroker | Skill | 1 | 2d ago | MIT | A | 50 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |