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 timoshinoleg-eng/1c-ai-workbench --skill cfe-validategit clone --depth 1 https://github.com/timoshinoleg-eng/1c-ai-workbenchWrote 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/timoshinoleg-eng/1c-ai-workbench/cfe-validate)<a href="https://agentmods.dev/skills/timoshinoleg-eng/1c-ai-workbench/cfe-validate"><img src="https://agentmods.dev/badge/skills/timoshinoleg-eng/1c-ai-workbench/cfe-validate/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/timoshinoleg-eng/1c-ai-workbench/cfe-validate"><img src="https://agentmods.dev/badge/skills/timoshinoleg-eng/1c-ai-workbench/cfe-validate.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 | $0.00036 | $0.00329 |
| Opus 5 | $0.00018 | $0.00164 |
| Sonnet 5 | $0.00007 | $0.00066 |
| Haiku 4.5 | $0.00004 | $0.00033 |
Grade A, and why
cfe-validate scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
/cfe-validate — валидация расширения конфигурации (CFE)
Проверяет структурную корректность расширения: XML-формат, свойства, состав, заимствованные объекты. Аналог /cf-validate, но для расширений.
Параметры
| Параметр | Обяз. | Умолч. | Описание |
|---|---|---|---|
| ExtensionPath | да | — | Путь к каталогу или Configuration.xml расширения |
| Detailed | нет | — | Подробный вывод (все проверки, включая успешные) |
| MaxErrors | нет | 30 | Остановиться после N ошибок |
| OutFile | нет | — | Записать результат в файл |
Команда
powershell.exe -NoProfile -File "${CLAUDE_SKILL_DIR}/scripts/cfe-validate.ps1" -ExtensionPath "src"
powershell.exe -NoProfile -File "${CLAUDE_SKILL_DIR}/scripts/cfe-validate.ps1" -ExtensionPath "src/Configuration.xml"
What ships with it
2 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.
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 · 30 lines · 36 tokens per session scan A f0e89d7cb5a1
cfe-validate is a skill published in the GitHub repository timoshinoleg-eng/1c-ai-workbench (0 stars, last pushed 22d ago), licensed MIT. It adds 36 tokens to every session and 329 once invoked, about $0.0002 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
1c-form-validate
A checker for managed forms in 1C, a platform for building business applications. It checks a form's XML structure, identifiers, linked fields, and commands.
1c-meta-validate
A checker for 1C metadata objects stored in XML. It verifies that the object's structure is valid and can optionally compare referenced types with the wider configuration.
1c-xdto-validate
A checker for XDTO packages in 1C:Enterprise. XDTO describes the structure and data types used when 1C exchanges data with external systems.
1c-epf-validate
A checker for the XML source of a 1C external data processor or report. It checks the structure, properties, names, fields, tables, forms, and layouts.
1c-erf-validate
A checker for the XML source of a 1C external report. It verifies the report structure, properties, fields, tables, forms, layouts, and data-composition schema.
1c-cf-validate
A validator for a 1C configuration, where 1C is a business software platform. It checks the exported configuration files for structural problems in XML, settings, languages, and object folders.