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 commands/nisus74/humanise/checkgit clone --depth 1 https://github.com/Nisus74/humaniseWhat 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 | $0.00000 | $0.00172 |
| Opus 5 | $0.00000 | $0.00086 |
| Sonnet 5 | $0.00000 | $0.00034 |
| Haiku 4.5 | $0.00000 | $0.00017 |
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.
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(thefailedlist and thestructural_densityblock).
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.
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 · 12 lines · 0 tokens per session scan A e8a5274fe455
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.
Other commands, from other repositories
refactor
Suggest refactoring opportunities.
test-coverage
Analyze test coverage and suggest improvements.
test-e2e
Write end-to-end tests for critical user journeys.
test-integration
Write integration tests for component boundaries.
export
Design public API exports.
newpkg
Generate new package with Nx.