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 erf-dumpgit 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/erf-dump)<a href="https://agentmods.dev/skills/timoshinoleg-eng/1c-ai-workbench/erf-dump"><img src="https://agentmods.dev/badge/skills/timoshinoleg-eng/1c-ai-workbench/erf-dump/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/erf-dump"><img src="https://agentmods.dev/badge/skills/timoshinoleg-eng/1c-ai-workbench/erf-dump.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 | $0.00049 | $0.00961 |
| Opus 5.5 | $0.00020 | $0.00384 |
| Sonnet 5.5 | $0.00010 | $0.00192 |
| Haiku 4.5 | $0.00005 | $0.00096 |
Grade A, and why
erf-dump 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 1mo 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.
This is a copy
91% identical to erf-dump — 6 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/erf-dump — Разборка отчёта
Usage
/erf-dump <ErfFile> [OutDir]
| Параметр | Обязательный | По умолчанию | Описание |
|---|---|---|---|
| ErfFile | да | — | Путь к ERF-файлу |
| OutDir | нет | src |
Каталог для выгрузки исходников |
Параметры подключения (обязательно)
Для разборки EPF/ERF требуется информационная база с конфигурацией. Без базы ссылочные типы безвозвратно теряются.
- Прочитай
.v8-project.jsonиз корня проекта. Возьмиv8pathи разреши базу: - Если пользователь указал параметры подключения (путь, сервер) — используй напрямую
- Если указал базу по имени — ищи по id / alias / name в
.v8-project.json - Если не указал — сопоставь текущую ветку Git с
databases[].branches - Если ветка не совпала — используй
default - Если
.v8-project.jsonнет или база не найдена — сообщи пользователю об ошибке. Для dump база обязательна: в пустой базе ссылочные типы (CatalogRef, DocumentRef и т.д.) безвозвратно сбрасываются в строки. Предложи указать базу или зарегистрировать через/db-list add.
Если v8path не задан — скрипт сам попытается определить платформу (.v8-project.json → Program Files).
Если использованная база не зарегистрирована — после выполнения предложи добавить через /db-list add.
Команда
Используй общий скрипт из epf-dump:
powershell.exe -NoProfile -File "${CLAUDE_SKILL_DIR}/../epf-dump/scripts/epf-dump.ps1" <параметры>
Параметры скрипта
| Параметр | Обязательный | Описание |
|---|---|---|
-V8Path <путь> |
нет | Каталог bin платформы (или полный путь к 1cv8.exe) |
-InfoBasePath <путь> |
* | Файловая база |
-InfoBaseServer <сервер> |
* | Сервер 1С (для серверной базы) |
-InfoBaseRef <имя> |
* | Имя базы на сервере |
-UserName <имя> |
нет | Имя пользователя |
-Password <пароль> |
нет | Пароль |
-InputFile <путь> |
да | Путь к ERF-файлу |
-OutputDir <путь> |
да | Каталог для выгрузки исходников |
-Format <формат> |
нет | Hierarchical (по умолч.) / Plain |
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.
- 1mo ago First seen · 72 lines · 49 tokens per session scan A e82a7436aea9
erf-dump is a skill published in the GitHub repository timoshinoleg-eng/1c-ai-workbench (0 stars, last pushed 1mo ago), licensed MIT. It adds 49 tokens to every session and 961 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 91% identical to erf-dump, differing in 6 lines, and is treated as a copy.
Other skills, from other repositories
omh-rust
This is an OMH rust workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
horizon-app-testing
Run or inspect declared iOS and Android native app tests through Horizon devicetestrun and app MCP tools. Use for App Automate sessions, native actions, evidence, and cleanup; desktop fixtures use horizon-device.
horizon-cast
Cast Horizon panels, workspaces, cloud cards, or its main window to Apple TV through the public cast MCP tool. Use for receiver discovery, pairing, casting status, and stopping casts.
humanize-ai-text
A writing aid for rewriting text produced by language-model agents into a more natural human style. It keeps the original meaning, facts, numbers, and technical terms.
transcribe
A tool for turning video and audio recordings into written text, with optional speaker identification and video analysis.
1c-web-test
A browser-automation tool for testing the 1C:Enterprise web client. It uses scripted actions to navigate screens, fill forms, read tables and reports, and apply filters.