Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/Syedomershah99/being-humannpx agentmods add skills/syedomershah99/being-human/being-humanWrote 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/syedomershah99/being-human/being-human)<a href="https://agentmods.dev/skills/syedomershah99/being-human/being-human"><img src="https://agentmods.dev/badge/skills/syedomershah99/being-human/being-human/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/syedomershah99/being-human/being-human"><img src="https://agentmods.dev/badge/skills/syedomershah99/being-human/being-human.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 | $0.00076 | $0.02104 |
| Opus 5 | $0.00038 | $0.01052 |
| Sonnet 5 | $0.00015 | $0.00421 |
| Haiku 4.5 | $0.00008 | $0.00210 |
Grade A, and why
being-human 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 10d 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 — 198 lines — stays where its author put it; the contents beside it link to each section on GitHub.
being-human
Generic AI prose is not a style. It's the absence of one. It happens because a model with no information about who is speaking falls back to the average of everyone, and the average of everyone reads like a press release.
The fix is information. This skill supplies it: a voiceprint measured from the user's own writing, and a slop filter built by contrast.
the loop
Learn. Harvest their writing into a corpus, measure it, write a voiceprint. Once. Then it improves on its own as they keep typing.
Write. Draft with the voiceprint loaded, not from your defaults.
Check, twice. Two different failures, two different tests:
slopscore.pyasks is this generic AI writing? -- tells, rhythm, structure.verify.pyasks is this THIS PERSON? -- authorship distance against a null resampled from their own writing.
A draft has to pass both, because passing one says nothing about the other. Clean well-written prose by an obviously different hand scores 97/100 on slop and 94th percentile on authorship. Generic slop can score 0/100 on tells while sitting at the 19th percentile on authorship, because its grammar is unremarkable and what betrays it is vocabulary and structure.
Revise. Fix what they flagged. Run both again. Repeat until both pass.
Do not skip these. You are a poor judge of your own slop -- it reads fluent to you because fluent is what you optimized for. The detectors don't care how it reads.
running it
Setup, once:
python3 scripts/harvest.py --source claude-history --out .being-human/
python3 scripts/harvest.py --source claude-projects --out .being-human/ --append --contrast
python3 scripts/analyze.py --in .being-human/ --name "Their Name"
--contrast is what makes the slop list personal. It collects the model's own
replies alongside the user's messages, then scores every word by log-odds. Words
the user reaches for and the model doesn't are their voice. Words the model
leans on and they never use are the slop -- measured against this person, not
a list someone published on the internet.
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.
- 10d ago First seen · 198 lines · 76 tokens per session scan A d8a0748a98c0
being-human is a skill published in the GitHub repository Syedomershah99/being-human (0 stars, last pushed 27d ago), licensed MIT. It adds 76 tokens to every session and 2,104 once invoked, about $0.0004 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
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…
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…
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…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…