check

A deterministic checker for a draft that looks for mechanical writing problems and structural patterns without using an AI model. It reports failed checks and a structural-density summary.

In plain words
What is it for?
Use it to check a draft file from the terminal or within a tool before review, then inspect the reported problems and warnings.
Why use it?
It catches issues that are easy to miss during editing, while making clear that passing the checks does not prove the writing is meaningful or suitable for its reader.

Command

Install

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.

agentmods
npx agentmods add commands/nisus74/humanise/check
Clone the repo
git clone --depth 1 https://github.com/Nisus74/humanise
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 172 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00172
Opus 5 $0.00000 $0.00086
Sonnet 5 $0.00000 $0.00034
Haiku 4.5 $0.00000 $0.00017

Measured 2d ago against content hash e8a5274fe455, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

check 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.

skill/commands/check.md · 12 lines

What it actually says

humanise: check

Run the deterministic checker on a draft (no LLM). Wraps evals/assertions/writing_checks.py.

  • Terminal: npx humanise detect <file> [dialect] [medium]
  • In-tool: write the draft to a temp file, run python3 evals/assertions/writing_checks.py <file> <dialect> [medium], then read the _summary (the failed list and the structural_density block).

Use to catch mechanical and structural risks. The checker never sees the meaning contract, the reader or the user's voice, so a clean result is not proof that a draft is good. Treat advisory counts as prompts for review rather than targets. Use a separate adversarial reviewer only when the stakes or length justify it.

Changes

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.

  1. 2d ago First seen · 12 lines · 0 tokens per session scan A e8a5274fe455

Subscribe to this mod's changes

check is a command published in the GitHub repository Nisus74/humanise (1 stars, last pushed 5d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 172 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.