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/paladini/harness-scoreWrote 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/rules/paladini/harness-score/docs-i18n-parity)<a href="https://agentmods.dev/rules/paladini/harness-score/docs-i18n-parity"><img src="https://agentmods.dev/badge/rules/paladini/harness-score/docs-i18n-parity.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 5.1 | $0.00000 | $0.00645 |
| Opus 5 | $0.00000 | $0.00322 |
| Sonnet 5 | $0.00000 | $0.00129 |
| Haiku 4.5 | $0.00000 | $0.00064 |
Grade A, and why
docs-i18n-parity 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 7d 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Guide i18n parity (mandatory)
This site ships five locales with the same ten guide chapters:
| Locale | Path |
|---|---|
| English (root) | docs/guide/ |
| pt-BR | docs/pt-BR/guide/ |
| es | docs/es/guide/ |
| zh-CN | docs/zh-CN/guide/ |
| hi-IN | docs/hi-IN/guide/ |
Non-negotiable
When you add, remove, rename, or substantively change any guide chapter or section in one locale, you must update all other locales in the same PR:
- Same file set — every locale has the same
*.mdfilenames underguide/. - Same anchor slugs —
{#scan-configuration},{#ctx-01}, etc. stay identical across locales (English slugs; never translate). CI enforces anchor parity formeasure-and-improve.md; treat all chapters the same way. - Same factual content — new features (CLI flags, scores, scopes, check behavior) must appear in every locale. Wording is translated per
docs/i18n/glossary.md; IDs, paths, JSON keys, and CLI stay English. - Sidebar — add/reorder entries in all five sidebar blocks in
docs/.vitepress/config.mts. - Glossary — new stable terms go in
docs/i18n/glossary.md.
Workflow
Edit docs/guide/foo.md (English source of truth for structure)
→ mirror docs/pt-BR/guide/foo.md
→ mirror docs/es/guide/foo.md
→ mirror docs/zh-CN/guide/foo.md
→ mirror docs/hi-IN/guide/foo.md
→ update sidebars if chapter list changed
→ npm run docs:build && npm test
If a locale is temporarily behind, do not merge until parity is restored.
Editorial rules (from glossary)
- Use relative links within the locale (
./metrics-and-codes#scopes), not/guide/...(escapes to English). - Do not translate check IDs, anchor slugs, file paths, or CLI examples.
- pt-BR: Brazilian Portuguese; es: Latin American; zh-CN: Simplified Chinese; hi-IN: Hindi (Devanagari), formal आप.
CI enforcement
packages/cli/test/docs.test.ts verifies:
- Every locale has the same guide filenames as English.
measure-and-improve.mdanchor sets match English in all locales.
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.
- 7d ago First seen · 57 lines · 0 tokens per session scan A d7c387098d47
docs-i18n-parity is a cursor rule published in the GitHub repository paladini/harness-score (395 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 645 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 2026-08-30.
Other cursor rules, from other repositories
project-instructions
Where vibe-replay's project instructions live.
frontend
UI/component conventions. Apply when building or changing user-facing frontend code.
core
The engineering contract for this repo lives in AGENTS.md (auto-loaded). Follow it. This rule only adds Cursor-specific behavior so the contract is not duplicated token-for-token on every request.
debugging
Debugging discipline. Apply when investigating a bug, test failure, or unexpected behavior.
tailwind-v4-core
Core Tailwind CSS v4 rules. Enforces correct v4 syntax and prevents common v3 fallbacks. Attach to all conversations involving Tailwind CSS.
tailwind-v4-migration
Tailwind CSS v3-to-v4 migration rules. Activated when the agent determines migration work is needed. Covers step-by-step upgrade process, common pitfalls, and automated migration tooling.