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.
git clone --depth 1 https://github.com/Nisus74/humaniseWrote 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/commands/nisus74/humanise/guide)<a href="https://agentmods.dev/commands/nisus74/humanise/guide"><img src="https://agentmods.dev/badge/commands/nisus74/humanise/guide/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/commands/nisus74/humanise/guide"><img src="https://agentmods.dev/badge/commands/nisus74/humanise/guide.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 | $0.00000 | $0.00139 |
| Opus 5.5 | $0.00000 | $0.00056 |
| Sonnet 5.5 | $0.00000 | $0.00028 |
| Haiku 4.5 | $0.00000 | $0.00014 |
Grade A, and why
guide 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 1mo 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.
What it actually says
humanise: guide
Draft new content in the user's voice.
- Build the meaning contract and reader model in
references/meaning-and-voice.md. - Load the smallest drafting card described in
SKILL.md. - Classify the voice evidence as strong, moderate or thin.
- Draft through the content, rhetoric, voice and surface passes.
- Verify fidelity before voice and mechanics.
- Present the finished draft first. Mention only material assumptions, unsupported claims or evidence gaps.
Ask once for raw words when an external or consequential piece has no personal source material and that input would materially improve the result. Do not block a useful conservative draft.
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.
- 1mo ago First seen · 15 lines · 0 tokens per session scan A a5478a16d4aa
guide is a command published in the GitHub repository Nisus74/humanise (1 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 139 tokens. 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 commands, from other repositories
tray-referencia-api
Referência rápida de todos os endpoints da API da Tray, aceita nome do recurso como filtro.
humanizer
Humanize text — strip AI-writing patterns from pasted text or a file without changing what it says.
perf-investigate
Drive an iOS performance or memory-leak investigation on using Memory Graph + Time Profiler. Enforce data-before-architecture and stacked PRs.
verified-pr
Open a PR only after a full local build + test pass. When the project's PR CI does not run unit tests, so this skill enforces the gate locally before handing off to /create-pr. Use whenever the user asks to open, create, push, or ship a PR — including phrases like "open a PR", "make a PR", "ship it", "create the pull…
code-review
Review code quality applying DRY, SOLID, naming, and formatting standards.
feature-flag-check
Investigate the feature flag $ARGUMENTS and produce a detailed investigation for removal.