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 evergreentree97/K-Humanizer --skill k-humanizergit clone --depth 1 https://github.com/evergreentree97/K-HumanizerWrote 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/evergreentree97/k-humanizer/k-humanizer)<a href="https://agentmods.dev/skills/evergreentree97/k-humanizer/k-humanizer"><img src="https://agentmods.dev/badge/skills/evergreentree97/k-humanizer/k-humanizer.svg" alt="Measured on agentmods" 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 | $0.00130 | $0.02127 |
| Opus 5 | $0.00065 | $0.01064 |
| Sonnet 5 | $0.00026 | $0.00425 |
| Haiku 4.5 | $0.00013 | $0.00213 |
Grade A, and why
k-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 8d 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 — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.
K-Humanizer
Core Rule
Make Korean text sound naturally written by a fluent Korean speaker without changing facts, intent, constraints, names, numbers, or quoted text.
Do not optimize for "AI detector bypass." Optimize for reader trust: clear meaning, believable rhythm, context-appropriate wording, and no over-polishing.
Never output U+2013 (en dash), U+2014 (em dash), or U+00B7 (middle dot) in rewritten prose. If quoted text, a code identifier, or a URL contains one, preserve the verbatim material separately instead of silently changing it.
Resume First
Treat resumes and career documents as a high-stakes humanization task. The default is to improve the supplied wording, regardless of field, without choosing a different career story for the user. For every resume, career description, portfolio summary, or application-writing task:
- Read
references/resume.mdandreferences/resume-workflow.md. - If a target role or job description is supplied, also read
references/resume-roles.md. - Preserve the field's established terms and the writer's actual experience.
- Unless the user asks for composition or tailoring, do not select, remove, or reorder experience. Remove only the AI-like wording and awkward Korean.
Resume writing can be a light edit or a structural rewrite. Humanization is the default, and the user's request sets any broader scope:
- Polish or humanize: edit only the supplied wording and follow the change budget.
- Turn notes into bullets: organize only facts present in the notes and expose any missing evidence that affects the claim.
- Tailor to a posting: only when requested, rank verified experience for one primary role and at most one supporting role. Do not copy requirements into the resume.
- Review a full resume: check section roles, repetition, evidence gaps, reader fit, and contribution boundaries before rewriting affected sections.
Do not force every career into one problem-action-metric formula. A policy decision, exception rule, research method, design choice, release decision, customer follow-up, or program operation can be useful experience without a percentage.
What ships with it
7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 8d ago First seen · 179 lines · 130 tokens per session scan A 0c6e20798b48
k-humanizer is a skill published in the GitHub repository evergreentree97/K-Humanizer (8 stars, last pushed 14d ago), licensed MIT. It adds 130 tokens to every session and 2,127 once invoked, about $0.0006 per session on Opus 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.
Other skills, from other repositories
humanizer
A Korean-language editor that detects patterns often found in AI-generated writing and rewrites the text to sound more natural.
grammar-checker
A Korean-language checker based on standard Korean spelling, spacing, grammar, and punctuation rules. It also explains why a suggested correction is needed.
seedance-vocab-ko
This skill should be used when the user asks for Korean Seedance 2.0 prompt wording, Korean cinematic vocabulary, or translation of camera, lighting, action, VFX, audio, and production terms into Korean.
speak-human-tw
A Traditional Chinese editing guide for making public-facing writing sound more natural and less machine-generated. It also checks wording associated with Mainland China and half-width punctuation.
Executive Resume Writer
Create C-suite and VP level resumes emphasizing strategic leadership.
Automation Tester Resume Optimizer
Build an SDET or automation engineer resume around framework ownership, tool-stack evidence, CI/CD integration, and GitHub proof that survives technical screening and recruiter keyword search.