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 instructions/xusnitdinov/uzbek-humanizer/agents-mdgit clone --depth 1 https://github.com/xusnitdinov/uzbek-humanizerWrote 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/instructions/xusnitdinov/uzbek-humanizer/agents-md)<a href="https://agentmods.dev/instructions/xusnitdinov/uzbek-humanizer/agents-md"><img src="https://agentmods.dev/badge/instructions/xusnitdinov/uzbek-humanizer/agents-md.svg" alt="Measured on agentmods" 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 | $0.00939 | $0.00939 |
| Opus 5 | $0.00469 | $0.00469 |
| Sonnet 5 | $0.00188 | $0.00188 |
| Haiku 4.5 | $0.00094 | $0.00094 |
Grade A, and why
uzbek-humanizer AGENTS.md 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 4d 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Instructions for AI coding agents working in this repository (not end-user install of the skill).
What this repo is
- Product: Agent Skills that make Latin Uzbek copy sound natural +
/uzbek-humanizefor site/app i18n - Installer:
cli/→ npm packageuzbek-humanizer-cli(bin:uzhumanizer) - Source of truth:
skills/- never treat gitignoredcli/skills/orcli/skill/as editable sources
Layout
| Path | Edit? | Notes |
|---|---|---|
skills/uzbek-humanizer/ |
yes | Main skill - SKILL.md lean; bulk in references/ |
skills/uzbek-humanize/ |
yes | Slash companion (disable-model-invocation: true) |
skills/uzbek-humanizer/eval/ |
yes | cases.jsonl + matching goldens.json ids |
cli/lib/init.js |
yes | Install targets, dual-pack rules |
cli/skills/, cli/skill/ |
no | Rebuilt by cli/scripts/sync-skill.mjs on pack/publish |
README.md, INSTALL.md, CONTRIBUTING.md |
yes | Keep install commands accurate |
Commands
# from repo root - CI gate
npm run test:eval
npm run test:normalize
# try installer against a project cwd
node cli/bin/uzhumanizer.js init --ai cursor
node cli/bin/uzhumanizer.js uninstall --ai cursor
node cli/bin/uzhumanizer.js versions
# draft helpers
node skills/uzbek-humanizer/scripts/normalize-apostrophe.mjs path/to/draft.txt
node skills/uzbek-humanizer/scripts/lint-banned.mjs path/to/draft.txt
node skills/uzbek-humanizer/scripts/lint-stiff.mjs path/to/draft.txt
Node 18+. No app build step.
Hard rules
- Both packs - install/uninstall/publish must keep
uzbek-humanizeranduzbek-humanize - Eval sync - new/changed case
idincases.jsonlneeds the same key ingoldens.json; runnpm run test:eval - Orthography in goldens/Matn - oʻ/gʻ →
ʻ(U+02BB); tutuq →ʼ(U+02BC); do not accept ASCII'twins as valid expects; never rewrite digraphs into tutuq - Product/quiz = Siz - no
qilasan/ bareKelunless user asked for sen/youth - Soft synonyms - situation-natural verbs (
oʻxshamadinotchiqmadifor "didn't work out"); seereferences/soft-synonyms.md - Router - keep
SKILL.mdshort; Top 10 hard rules first; put domain detail inreferences/; one hop - Honesty - calque-safe draft; legal / medical / heavy youth / high-stakes synonym doubt =
draft/native_review_required - Place names in Uzbek text:
Toshkent, not Tashkent - Sister contract -
uzbek-humanizer= text quality;uzbek-humanize= i18n file wiring - Versions - bump
cli/package.json+ bothskills/*/SKILL.mdmetadata.version+CHANGELOG.mdtogether when cutting a release (maintainers) - Normalize bilingual safely -
npm run test:normalize; ENWho's/ tx() EN args must not change
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.
- 4d ago First seen · 68 lines · 939 tokens per session scan A 29699fd5596a
uzbek-humanizer AGENTS.md is an instructions file published in the GitHub repository xusnitdinov/uzbek-humanizer (2 stars, last pushed 24d ago), licensed MIT. It adds 939 tokens to every session, about $0.0047 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 instructions, from other repositories
globalize-skills CLAUDE.md
Claude Code instructions for globalize-now/globalize-skills, covering globalization skills, repository structure, conventions, installing a skill and install a single skill into the current project.
mcp-unity AGENTS.md
Instructions for CoderGamester/mcp-unity, covering mcp unity — ai agent guide (mcp package), purpose (what this repo is), how it works (high-level data flow), key defaults & invariants and repo layout (where to change what).
plugin-files-mode
Rosetta Plugin Mode Bootstrap.
rails-ai-context AGENTS.md
AGENTS.md instructions for crisnahine/rails-ai-context, covering rails-ai-context, agent skills, issue tracker, triage labels and domain docs.
inspecto CLAUDE.md
Instructions for inspecto-dev/inspecto, covering inspecto — claude code development guide, project overview, monorepo structure, development phases (load each file as needed) and key architectural decisions.
skill.color-expert CLAUDE.md
Claude Code instructions for meodai/skill.color-expert, covering claude.md, project overview, architecture, no build/test/lint and editing guidelines.