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 skills add techartdev/BulgarianGrammarSkill --skill bulgarian-grammargit clone --depth 1 https://github.com/techartdev/BulgarianGrammarSkillWrote 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/skills/techartdev/bulgariangrammarskill/bulgarian-grammar)<a href="https://agentmods.dev/skills/techartdev/bulgariangrammarskill/bulgarian-grammar"><img src="https://agentmods.dev/badge/skills/techartdev/bulgariangrammarskill/bulgarian-grammar/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/skills/techartdev/bulgariangrammarskill/bulgarian-grammar"><img src="https://agentmods.dev/badge/skills/techartdev/bulgariangrammarskill/bulgarian-grammar.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 | $0.00103 | $0.04879 |
| Opus 5 | $0.00051 | $0.02440 |
| Sonnet 5 | $0.00021 | $0.00976 |
| Haiku 4.5 | $0.00010 | $0.00488 |
Grade A, and why
bulgarian-grammar 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 9d 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 — 320 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bulgarian grammar
Bulgarian is grammatically unlike English in ways that produce fluent-sounding but wrong output. The failure modes are systematic, not random. This skill turns them into explicit checks.
The five things that go wrong most often, in order:
- Full vs. short definite article (
-ът/-ятvs.-а/-я) — a syntactic rule with no spoken counterpart, so statistical intuition is useless. - Evidentials — Bulgarian grammatically marks whether you witnessed something. Reporting someone else's past statement in the indicative is a hard error.
- Participle selection —
бих мислилis correct,бих мислелdoes not exist. - The count form (
два столаvs.двама студенти) — turns on whether the noun denotes a person. - Clitic order and placement — a fixed template; clitics may never open a clause.
Workflow
Never emit Bulgarian in one pass. Draft, then run the verification pass below over your own text before showing it. The checks are cheap and the errors are invisible to fluency-based self-review.
- Draft. Write the Bulgarian.
- Verify. Walk the Verification checklist below. It is ordered by error frequency; do not skip items because the text "reads fine".
- Consult. When any check is not obviously satisfied, open the relevant reference file rather than guessing. Guessing is what produces the errors.
- Fix and re-verify the changed sentences.
For translation from English, first read references/translating-from-english.md —
several English structures have no direct Bulgarian equivalent and must be
restructured, not mapped.
Reference files
Load on demand; do not read them all up front.
| File | Read it when |
|---|---|
references/definite-article.md |
Any masculine singular noun/adjective/pronoun ending in a consonant is definite |
references/evidentiality.md |
Reporting speech, retelling, folk tales, news from a source, hedging, rumours |
references/verb-system.md |
Choosing a tense; forming any compound tense; conjugating; aspect questions |
references/participles.md |
Any form with -л, -н/-т, -щ or -йки; passive; conditional; perfect |
references/nouns-numerals.md |
Plurals, count form, numerals, vocative, gender, agreement |
references/clitics-word-order.md |
Any short pronoun (ме, го, ѝ, му, се, си, ми…), не, ще, ли, possession |
references/orthography.md |
Spelling, я/е alternation, ѝ, capitals, hyphens, numbers, dates |
references/punctuation.md |
Any comma decision; quotes; direct speech; dashes |
references/translating-from-english.md |
Translating or adapting English source text |
references/calques-and-false-friends.md |
The text came from English; any borrowed verb, idiom or figurative usage |
references/error-catalogue.md |
Proofreading someone else's Bulgarian; want the error→fix table |
references/worked-examples.md |
Want the checklist applied end-to-end on real drafts |
What ships with it
12 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/calques-and-false-friends.md 11 KB
- references/clitics-word-order.md 8.6 KB
- references/definite-article.md 11 KB
- references/error-catalogue.md 12 KB
- references/evidentiality.md 14 KB
- references/nouns-numerals.md 13 KB
- references/orthography.md 7.7 KB
- references/participles.md 10 KB
- references/punctuation.md 8.5 KB
- references/translating-from-english.md 8.9 KB
- references/verb-system.md 16 KB
- references/worked-examples.md 8.8 KB
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.
- 9d ago First seen · 320 lines · 103 tokens per session scan A 7f9c7bea796c
bulgarian-grammar is a skill published in the GitHub repository techartdev/BulgarianGrammarSkill (5 stars, last pushed 1mo ago), licensed MIT. It adds 103 tokens to every session and 4,879 once invoked, about $0.0005 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 skills, from other repositories
chinese-documentation
A Chinese technical-documentation style guide covering spacing, punctuation, numbers, terminology, and links when Chinese and English appear together.
azure-ai-translation-text-py
Azure AI Text Translation SDK for real-time text translation, transliteration, language detection, and dictionary lookup. Use for translating text content in applications. Triggers: "text translation", "translator", "translate text", "transliterate", "TextTranslationClient".
harden
Improve interface resilience through better error handling, i18n support, text overflow handling, and edge case management. Makes interfaces robust and production-ready. Use when the user asks to harden, make production-ready, handle edge cases, add error states, or fix overflow and i18n issues.
seedance-vocab-ja
This skill should be used when the user asks for Japanese Seedance 2.0 prompt wording, Japanese cinematic vocabulary, or translation of camera, lighting, action, VFX, audio, and production terms into Japanese.
asc-subscription-localization
Bulk-localize subscription, subscription-group, and in-app purchase display names across App Store locales using asc, including API 4.4.1 version-scoped v2 resources. Use when filling or updating subscription/IAP names and descriptions without App Store Connect UI work.
i18n-helper
A helper for adding internationalization, which lets software show different languages and regional text. It finds user-visible text written directly in code and moves it into language files.