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/vaayne/agent-kit/humanizernpx skills add vaayne/agent-kit --skill humanizergit clone --depth 1 https://github.com/vaayne/agent-kitWhat 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 | $0.00098 | $0.00996 |
| Opus 5 | $0.00049 | $0.00498 |
| Sonnet 5 | $0.00020 | $0.00199 |
| Haiku 4.5 | $0.00010 | $0.00100 |
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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Humanizer
Turn text that sounds model-written into text that sounds human-written. The goal is not to add quirks or make the prose messy. Preserve meaning and author intent while removing AI tells, promotional padding, formulaic structure, and the fake smoothness that makes text feel generated.
Workflow
-
Classify the task
- If the user asks to humanize, de-AI, or make text sound natural, rewrite the text.
- If the user asks for a review or AI-writing audit, return a concise issue list and fixes.
- If the user provides a file path, read the file and either rewrite or edit it as requested.
- If the user provides a writing sample, calibrate to that voice before rewriting the target text.
-
Preserve meaning and coverage
- Keep the core information and stance.
- Cover the same substantive points as the source.
- Flag suspicious facts, citations, and data. Do not invent sources to patch gaps.
-
Audit patterns before rewriting
- For a thorough review, read
references/ai-writing-patterns.md. - For a fast, strict cleanup, read
references/stop-slop-rules.md. - Look for clusters of tells. Do not rewrite normal human prose because of one em dash, one formal word, or one transition.
- For a thorough review, read
-
Run the stop-slop final gate
- Cut greeting residue, meta commentary, filler, fake profundity, and boilerplate.
- Prefer active voice and concrete nouns.
- The final rewrite must contain no em dash or en dash.
Output format
Default output:
## AI tells
- [the 3-6 most important problems]
## Rewrite
[final rewrite]
## Notes
- [optional: fact risks, voice choices, preservation/removal rationale]
If the user asks for final-only output, direct file edits, or no explanation, skip the commentary and provide only the result.
Voice calibration
When the user provides a writing sample, inspect it before rewriting:
- Sentence length: short, long, or mixed?
- Word choice: casual, technical, formal, sharp, plain?
- Paragraph openings: direct, contextual, narrative?
- Punctuation habits: parentheses, colons, semicolons, dash substitutes?
- Transitions: explicit connectors or hard cuts?
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.
- 2d ago First seen · 101 lines · 98 tokens per session scan A 467245e5737f
humanizer is a skill published in the GitHub repository vaayne/agent-kit (53 stars, last pushed 5d ago), licensed MIT. It adds 98 tokens to every session and 996 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…