Borrowing it
Nothing to install: this file belongs to indianic/byline. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/indianic/byline/main/.claude/skills/humanizer/SKILL.mdgit clone --depth 1 https://github.com/indianic/bylineWrote 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/indianic/byline/humanizer)<a href="https://agentmods.dev/skills/indianic/byline/humanizer"><img src="https://agentmods.dev/badge/skills/indianic/byline/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/indianic/byline/humanizer"><img src="https://agentmods.dev/badge/skills/indianic/byline/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 | $0.00035 | $0.01412 |
| Opus 5 | $0.00017 | $0.00706 |
| Sonnet 5 | $0.00007 | $0.00282 |
| Haiku 4.5 | $0.00003 | $0.00141 |
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 2d 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 — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Humanizer
This is the full version of the REVISION PASS printed at the bottom of every
build_writing_brief output. The brief carries a compressed, five-line form of
it and tells the writer to come here by name for the definitions. This file is
the one place the five groups are spelled out in full — do not re-derive them,
and do not shorten them back into the brief; one rule, one definition.
The five groups
Read the whole draft once, start to finish, before touching anything. Then mark every tell you find, grouped below in the order you act on them.
1. Staging instead of stating. The sentence spends its first half setting up a rhetorical move instead of just making the claim — "It's not just a tool, it's a platform," a one-line paragraph that exists purely for cadence, a saying that sounds deep on first read and empty on the second ("at its core," "make no mistake"), a run-up before the actual point, or an argument answering an objection nobody in the piece raised ("To be clear, this isn't about...").
2. Rhythm by rule. The prose follows a pattern instead of a reason to be shaped that way — three-item lists reached for out of habit rather than because the list has three things in it, three sentences in a row opening with the same word, a dash used as the universal connector between any two clauses instead of a period, a comma, or a colon, two hedges stacked on one claim ("could potentially"), a hyphenated compound in every other sentence, or a passive construction that hides who did the thing ("mistakes were made" instead of naming who made them).
3. Inflation. A plain fact dressed in language sized for something bigger — "pivotal," "landscape," "testament," "crucial" applied to an ordinary detail, a routine event framed as a turning point, "associated with" standing in for the actual mechanism ("caused," "delayed," "replaced"), an expert who is never named, or "serves as"/"stands as"/"boasts" used in place of a plain "is" or "has."
4. Formatting by rule. Visual structure applied as decoration rather than to carry meaning — bold text scattered through body paragraphs instead of reserved for the summary block and the callout label, a heading in Title Case where the rest of the piece is not, or a heading whose very next sentence just restates it instead of answering it.
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.
- 2d ago First seen · 119 lines · 35 tokens per session scan A 9fb6f9ea5700
humanizer is a skill published in the GitHub repository indianic/byline (2 stars, last pushed 2d ago), licensed MIT. It adds 35 tokens to every session and 1,412 once invoked, about $0.0002 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 2026-09-11.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…