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/shir-danishyar/humanizeWrote 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/commands/shir-danishyar/humanize/humanizer)<a href="https://agentmods.dev/commands/shir-danishyar/humanize/humanizer"><img src="https://agentmods.dev/badge/commands/shir-danishyar/humanize/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/commands/shir-danishyar/humanize/humanizer"><img src="https://agentmods.dev/badge/commands/shir-danishyar/humanize/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 | $0.00022 | $0.00853 |
| Opus 5.5 | $0.00009 | $0.00341 |
| Sonnet 5.5 | $0.00004 | $0.00171 |
| Haiku 4.5 | $0.00002 | $0.00085 |
Grade A, and why
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 1mo 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 — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Humanize the text below (or the file it names) using the humanize-writing skill in rewrite mode.
If the humanize-writing skill is installed, load it now and follow it in full, including references/patterns.md and references/vocabulary.md. If it is not available, apply the rules summarized here.
Input
$ARGUMENTS
If the input is a file path, read the file and rewrite only its prose: leave code blocks, front matter, data, and link targets untouched, then write the result back to the same file. If the input is empty, ask the user to paste the text or give a file path. Do nothing else.
Rules (rewrite mode)
Preserve everything except the patterns:
- Never alter direct quotes; quoted third-party text stays verbatim.
- Never change citations, numbers, statistics, dates, URLs, or proper nouns.
- Keep every claim the text makes. Change phrasing, not meaning.
- Never add a fact, name, number, date, quote, or citation that is not in the source. If a sentence needs a specific you don't have, leave the sentence plainer rather than invent one.
- Detect the register (social / email / editorial / formal) and keep it. Contractions and fragments are fine in a post; neither belongs in a formal report.
- If a
voice-profile.mdexists in the project, match it.
Strip, in order of damage:
- Negative parallelism: "It's not X, it's Y", "not only X but also Y", "X rather than Y". State the positive claim.
- Trailing significance clauses: "..., reflecting / highlighting / underscoring / ensuring / contributing to ...". State the fact and stop.
- Significance inflation and puffery: pivotal moment, enduring legacy, setting the stage for, testament to, nestled, vibrant, renowned, rich heritage.
- AI vocabulary: delve, tapestry, intricate, interplay, crucial, pivotal, key (adj.), leverage, robust, seamless, foster, enhance, align with, showcase, underscore, empower, streamline, holistic, comprehensive, transformative, cutting-edge, game-changer, myriad, plethora, deep dive, ever-evolving.
- Copula avoidance: "serves as", "stands as", "boasts", "features", "offers" → "is", "has".
- Rule of three: keep the item that carries information; drop the padding.
- Vague attribution and canned coverage: "experts say", "studies show", "featured in national media outlets", "maintains an active social media presence". Name the source or cut.
- Vague association: "associated with", "in connection with" → the actual relationship (founded, taught, member of).
- Summary closers ("In conclusion", "Overall", "Ultimately"), editorializing ("It's important to note"), challenges-and-outlook endings. End on the last substantive point.
- Chatbot residue: "Great question", "You're absolutely right", "I hope this helps", "Let me know if", "Would you like me to", "As of my last update", "While specific details are not widely documented" followed by a guess. Delete.
- Formatting: at most one em dash per ~300 words and unspaced; no bold mid-sentence; no
**Term:** definitionbullets; no emoji in headings; sentence-case headings; no headings under ~400 words; consistent quotation marks; no two-row tables. - Rhythm: vary sentence length; say each idea once.
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.
- 1mo ago First seen · 48 lines · 22 tokens per session scan A ce3082cf8b08
humanizer is a command published in the GitHub repository shir-danishyar/humanize (20 stars, last pushed 1mo ago), licensed MIT. It adds 22 tokens to every session and 853 once invoked, about $0.0001 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 2026-09-03.
Other commands, from other repositories
ios-build
Plan, build, test and screenshot a native SwiftUI iOS app from a plain-language description.
true-platform-testing
End-to-end Katalon True Platform testing workflow and lifecycle router. Use when one request spans several stages and no single skill owns it, for example analyze a requirement, design and import the cases, build a suite, run it with AI, and report the outcome. Also use to route any testing request across the 7-stage…
playwright-execute
Run Playwright tests or suites and upload the resulting report to Katalon True Platform. Use when you need to execute Playwright scripts, package scripts, spec files, projects, or suites, configure or verify @katalon/playwright-reporter, upload Playwright reports with Katalon CLI/reporter commands, and verify uploaded…
analyze-failures
Triage Katalon True Platform/TestOps test failures and file defects. Use when you need to investigate failed test results, classify each failure as product defect vs automation defect vs environment/data issue, cluster failures by common signature, find likely root cause from execution data, and optionally create…
test-maintenance
Maintain and evolve a Katalon True Platform/TestOps regression suite as the application changes. Use when you need to detect which tests broke or became flaky from stability and result history, diagnose whether a case needs repair vs regeneration, repair test assets (update, move, reorganize cases), refresh coverage…
test-management
Organize, classify, and trace Katalon True Platform/TestOps test assets. Use when you need to structure test cases into folders and suites, move or reorganize cases, search and find existing assets at scale, link or unlink requirements to test cases, or produce a requirement-to-test traceability report (which…