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 theafh/ai-modules --skill language_humanizergit clone --depth 1 https://github.com/theafh/ai-modulesWrote 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/theafh/ai-modules/language_humanizer)<a href="https://agentmods.dev/skills/theafh/ai-modules/language_humanizer"><img src="https://agentmods.dev/badge/skills/theafh/ai-modules/language_humanizer/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/theafh/ai-modules/language_humanizer"><img src="https://agentmods.dev/badge/skills/theafh/ai-modules/language_humanizer.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 | $0.00209 | $0.03241 |
| Opus 5.5 | $0.00084 | $0.01296 |
| Sonnet 5.5 | $0.00042 | $0.00648 |
| Haiku 4.5 | $0.00021 | $0.00324 |
Grade A, and why
language_humanizer 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 20d 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 — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.
language_humanizer
<language_humanizer>
<role_and_activation>
<activation_triggers> Activate on a request to make a document easier to understand, simplify wording, cut jargon, unpack a dense paragraph, spell out abbreviations, sharpen a goal or decision so readers can act on it, check whether a draft will land with a particular audience, or turn notes, bullets, or findings into a document a reader can follow. </activation_triggers>
<review_mode>Return findings on an existing draft and leave the text untouched.</review_mode>
<rewrite_mode>Return the edited version of an existing draft.</rewrite_mode>
<write_mode>Return a new document produced from supplied material.</write_mode>
<mode_selection> Select rewrite when the user hands over a draft and asks for it improved. Select write when the input is material to turn into a document rather than a draft to fix. Select review when the user asks what is wrong with a draft, asks whether it reads clearly, or wants to keep authorship of the wording. When a request over an existing draft leaves the mode open, deliver the review and offer the rewrite. </mode_selection>
<mode_to_path_mapping> Each mode runs on one of two paths, and a mode's path follows its input. Review and rewrite both start from an existing draft, so both run the rewrite path, which optimizes text that already exists. Write starts from supplied material (notes, bullets, findings, source facts, a brief), so it runs the write path, which produces the document that says all of it.
What a mode returns then sets its route through the three passes. Review and rewrite both build pass one's ledger from the draft; rewrite carries that ledger through pass two into pass three, while review holds it as the yardstick for judging the draft against pass two's moves and reports what it finds, rather than producing text for pass three to verify. Write builds its ledger from the supplied material and runs all three passes over the document it produces.
This is the whole mapping. Every later section names the rewrite path and the write path and takes this statement as given. </mode_to_path_mapping>
<establish_the_reader> Establish the intended reader and that reader's task before judging anything, drawing on the request and the document itself. When neither names a reader, state the assumed reader in the output so the author can correct it. </establish_the_reader>
</role_and_activation>
<fidelity_contract> These rules bind whatever the skill delivers, and they outrank every stylistic preference below them. The ledger they refer to is the inventory pass one builds.
<keep_qualifiers_conditions_and_exceptions> Keep every qualifier, condition, exception, and scope limit, splitting a sentence to accommodate them rather than trimming them to fit. </keep_qualifiers_conditions_and_exceptions>
<keep_requirement_strength> Keep requirement strength exactly as written, in both directions: a must stays a must, a should stays a should, a may stays a may, and a hedge marking real uncertainty stays a hedge. A hedge is real when it marks doubt about whether a statement is true; a phrase that only softens a statement whose modal verb already carries its strength is hedging padding, and it comes out with the rest of the padding. Carry the strength on the modal verb the input used, because a paraphrase into a noun phrase silently reclassifies the requirement. A must rewritten as a hard limit, a firm constraint, or a target reads as a description of the world instead of an obligation on someone, and a should rewritten as a requirement invents an obligation the input never gave. </keep_requirement_strength>
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.
- 20d ago Changed · +1 lines · -14 tokens per session 9742bcd34794
- 21d ago First seen · 179 lines · 223 tokens per session scan A adaa20be6a46
language_humanizer is a skill published in the GitHub repository theafh/ai-modules (38 stars, last pushed today), licensed MIT. It adds 209 tokens to every session and 3,241 once invoked, about $0.0008 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 2026-10-08.
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…