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 kouroshez/coding-os --skill humanizergit clone --depth 1 https://github.com/kouroshez/coding-osWrote 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/kouroshez/coding-os/humanizer)<a href="https://agentmods.dev/skills/kouroshez/coding-os/humanizer"><img src="https://agentmods.dev/badge/skills/kouroshez/coding-os/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/kouroshez/coding-os/humanizer"><img src="https://agentmods.dev/badge/skills/kouroshez/coding-os/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 | $0.00154 | $0.02751 |
| Opus 5.5 | $0.00062 | $0.01100 |
| Sonnet 5.5 | $0.00031 | $0.00550 |
| Haiku 4.5 | $0.00015 | $0.00275 |
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 27d 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 — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Humanizer
Rewrite AI-sounding prose so it reads like the writer, without changing what it says.
The failure this prevents is not embarrassment. It is that a reader who smells generated text stops evaluating the argument and starts evaluating the author — so a correct, well-evidenced claim gets discarded on style. Published prose that trips those signals costs the credibility of everything it carries.
The seam — this skill vs technical-writing
They run in sequence and must not fight:
technical-writing |
humanizer |
|
|---|---|---|
| Owns | structure, altitude, accuracy, the doc-header contract | sentence-level texture and rhetoric |
| Asks | is it correct, findable, and at the right altitude? | does it read like a person wrote it? |
| Runs | while drafting | on the finished draft, before it ships |
Run technical-writing first. A humanized draft that is structurally wrong is still wrong.
Non-negotiables
- Keep every claim. Shorten dull parts, expand useful ones, merge or split paragraphs — but do not lose information. The exception is a pattern below that requires removal (unsupported importance, vague sources, invented context, unraised objections, fake alternatives, generic endings). Removing under one of those is correct, not a lost claim.
- Invent nothing. No fact, name, number, date, quote, or citation that the source or the user did not supply. If a sentence needs a missing detail, ask for it or write a simpler sentence.
- Never manufacture humanity. Do not add fake opinions, staged reactions, invented anecdotes, or fabricated specificity to make prose feel personal. That produces a different lie, not a human voice. Real voice comes from the writer's own material.
- Never claim to detect AI. In a review, report the specific patterns you found with file and line. Do not assign an "AI score" or assert that a model wrote something — you cannot know, and the claim is unfalsifiable.
- Match the writer's voice over these rules. If the user supplies a writing sample, read it first: sentence length, word choice, paragraph openings, punctuation, repeated phrases. Match those habits. A sample that uses em dashes keeps them; §14 is then not a ban.
- Leave good prose alone. Minimum effective edit. Normalizing already-clear writing is a diff-discipline failure (Rule 22).
What ships with it
3 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.
- 27d ago Changed · +4 lines 034f2bdd24c1
- 1mo ago First seen · 123 lines · 154 tokens per session scan A 4a46db9337b4
humanizer is a skill published in the GitHub repository kouroshez/coding-os (6 stars, last pushed 5d ago), licensed Apache-2.0. It adds 154 tokens to every session and 2,751 once invoked, about $0.0006 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.
Other skills, from other repositories
graph-mutation-plan
Cookbook for composing an applygraphmutations plan — stable entitykey patterns, the canonical label/edge vocabulary, evidence/invalidation/confidence discipline, and a worked example. Load this when building a non-trivial mutation plan.
scienceworld-growth-focuser
Use when you have planted a seed or need to track a plant's growth stage (sprouting, flowering, reproduction). Applies the 'focus on' action to a specific plant or biological entity to signal intent and monitor its development. Trigger after planting or when you need to observe life cycle progression in the…
scienceworld-conditional-box-placer
Moves an object to one of two destination containers based on a numeric threshold check. Trigger after a measurement (e.g., temperature) is taken. Place object in 'green' box if value > threshold, or 'blue' box if value < threshold.
scienceworld-object-classifier
Moves a tested or examined object into a designated container (e.g., a specific colored box) based on a determined property. Use when you have completed a test or inspection and need to fulfill a classification or sorting subtask. It takes the object and target container as inputs and performs the move action.
scienceworld-tool-user
Uses a tool from inventory on a target object or location to perform a specific environmental interaction, such as digging, cutting, or measuring. Use this skill when a task requires modifying the environment or manipulating materials with a tool (e.g., using a shovel to dig soil, a thermometer to measure temperature…
tencent-ima-wiki
A browser-automation workflow for reading articles from a logged-in Tencent ima knowledge base. It extracts article links and text from the ima.qq.com/wikis site, including pages whose details are not directly visible in the webpage.