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 agentmods add skills/yuri-semenenko/ai-engineering-workspace/humanizernpx skills add yuri-semenenko/ai-engineering-workspace --skill humanizergit clone --depth 1 https://github.com/yuri-semenenko/ai-engineering-workspaceWrote 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/yuri-semenenko/ai-engineering-workspace/humanizer)<a href="https://agentmods.dev/skills/yuri-semenenko/ai-engineering-workspace/humanizer"><img src="https://agentmods.dev/badge/skills/yuri-semenenko/ai-engineering-workspace/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 | $0.00162 | $0.02110 |
| Opus 5 | $0.00081 | $0.01055 |
| Sonnet 5 | $0.00032 | $0.00422 |
| Haiku 4.5 | $0.00016 | $0.00211 |
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 6d 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 — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Humanizer
Rewrite a piece of text so it reads like a competent person wrote it on purpose. Preserve the meaning, the facts, and the intended register. Remove everything that signals "a language model produced this".
Process
- Read the whole input once before touching anything.
- Flag every instance of the patterns in the catalog below.
- Rewrite flagged passages. Prefer deleting a bad sentence over decorating it.
- Produce a draft, then run the self-audit (see below) and revise.
- Return the final text per the output format.
Two principles govern every rewrite:
- Specificity beats polish. A concrete fact ("deploys dropped from 40 to 12 minutes") always outperforms an abstract claim ("significantly improved deployment efficiency"). If the input has no concrete facts, keep the claim modest instead of inventing details.
- Clean is not enough. Text with zero AI patterns can still read as lifeless. Vary sentence length, allow an opinion where the register permits one, and let the author's judgment show. Uniform, neutral, perfectly balanced prose is itself a tell.
Voice matching
When the user supplies a sample of their own writing, imitate it: typical sentence length, how paragraphs open, punctuation habits, how formal the vocabulary runs, whether they use first person. Replace AI patterns with that author's patterns, not with a generic "good writing" default. Without a sample, default to plain, direct, lightly opinionated prose.
Pattern catalog
Family 1 — Inflation
1.1 Manufactured significance. Claims that something "marks a pivotal moment", "underscores the importance of", "is a testament to", or "reflects broader trends". Strip the ceremony; state what the thing is or does.
Before: "The migration to the new build system represents a pivotal step in the team's journey toward engineering excellence." After: "We migrated to the new build system in March. CI time dropped by half."
1.2 Promotional register. "Seamless", "robust", "cutting-edge", "powerful", "best-in-class" — adjectives that sell instead of describe. In technical writing, every one of them should be replaced by the property it is hiding.
What ships with it
2 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.
- 6d ago First seen · 134 lines · 162 tokens per session scan A f680c673cdb4
humanizer is a skill published in the GitHub repository yuri-semenenko/ai-engineering-workspace (1 stars, last pushed 5d ago), licensed MIT. It adds 162 tokens to every session and 2,110 once invoked, about $0.0008 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
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
My Skill
Content here.
task-generation
Reference material with the canonical task-format grammar and decomposition rules for plan-to-tasks expansion. Loaded on demand by generate-tasks; not directly invokable.
implementation-standards
Reference material with coding standards (defensive coding, error handling, testing patterns). Loaded on demand by the Developer sub-agent (.github/agents/developer.md); not directly invokable.
spec-authoring
Reference material for writing product, technical, and operational specifications (work-item priorities, requirement families, success criteria). Loaded on demand by specify-feature; not directly invokable.
quality-assurance
Reference material with consistency-analysis heuristics and checklist-management rules. Loaded on demand by analyze-compliance and quality-control; not directly invokable.