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 skills/muredsa/1c-enterprise-agent-toolkit/onec-devnpx skills add Muredsa/1C-Enterprise-Agent-Toolkit --skill onec-devgit clone --depth 1 https://github.com/Muredsa/1C-Enterprise-Agent-ToolkitWrote 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/muredsa/1c-enterprise-agent-toolkit/onec-dev)<a href="https://agentmods.dev/skills/muredsa/1c-enterprise-agent-toolkit/onec-dev"><img src="https://agentmods.dev/badge/skills/muredsa/1c-enterprise-agent-toolkit/onec-dev.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 | $0.00067 | $0.00547 |
| Opus 5 | $0.00034 | $0.00273 |
| Sonnet 5 | $0.00013 | $0.00109 |
| Haiku 4.5 | $0.00007 | $0.00055 |
Grade A, and why
onec-dev 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 5d 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 — 36 lines — stays where its author put it; the contents beside it link to each section on GitHub.
1C Development Router
Operate through an isolated, auditable session. Preserve the source infobase and remove session-owned data after the task.
Start safely
- Read references/safety-contract.md.
- Locate
scripts/onec.py. CheckONEC_DEV_CLI, a project checkout two levels above this skill, the executableonec-devonPATH, then the user data locations documented in the safety contract. - Run
discoverand select the newest compatible platform unless the user requested a specific version. - Run
session-create. For a file infobase, keep the default sandbox copy. Treat server, named, connection-string, and--no-sandboxsessions as live and require the user's explicit authorization. - Keep the returned manifest path. Pass it to every subsequent command with
--session.
Never put a password in a command, manifest, log, or chat. Pass only the name of an environment variable with --password-env. When an explicit 1C user is supplied, keep OS authentication disabled unless the user explicitly requests it.
Route the work
- Invoke
$onec-selective-exportto inspect or export only the metadata required for the task. - Invoke
$onec-extension-lifecycleto create, load, dump, edit, back up, roll back, or delete one named extension. - Invoke
$onec-extension-validateto check BSL, validate applicability, update the extension database configuration, or verify the resulting.cfe. - Combine the focused skills in that order for implementation work: inspect dependencies, modify an extension, then validate it.
Do not change the main configuration for extension work. Do not use destructive Designer switches outside the allowlist in the safety contract.
Finish deterministically
- Report the meaningful result and any diagnostics from the JSON output and linked log files.
- Run
session-cleanup --session <manifest>in a finally-style step whether the work succeeds or fails. - If cleanup fails, stop and report the exact session path. Do not broaden the deletion target or retry with a stronger deletion command.
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.
- 5d ago First seen · 36 lines · 67 tokens per session scan A 16c8a34045d9
onec-dev is a skill published in the GitHub repository Muredsa/1C-Enterprise-Agent-Toolkit (21 stars, last pushed 24d ago), licensed MIT. It adds 67 tokens to every session and 547 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
composing-1c-queries
Rules and patterns for writing correct 1C:Enterprise query language (язык запросов 1С). Queries are executed via the executequery tool/endpoint.
humanize-ai-text
Применять при переписывании текстов, сгенерированных LLM-агентами (отчеты, README, доки, письма, посты), в живой человеческий стиль. Триггеры - пользователь пишет 'убери AI-стиль', 'перепиши по-человечески', 'сделай естественно', 'убери воду', 'не как ChatGPT', 'убери LLM-штампы'; либо на входе текст с явными…
transcribe
Транскрибирование видео и аудио файлов. Используй когда пользователь просит транскрибировать, расшифровать запись, сделать конспект встречи, извлечь речь из видео или аудио, преобразовать речь в текст. Для аудио (m4a/mp3/wav/ogg/flac/aac/wma) по умолчанию локальный faster-whisper + диаризация с автодетектом числа…
1c-web-test
Тестирование 1С через веб-клиент - автоматизация действий в браузере. Используй когда пользователь просит проверить, протестировать, автоматизировать действия в 1С через браузер.
lmstudio-api
Справочник по HTTP-API LM Studio (сервер локальных моделей, обычно порт 1234). Используй когда надо программно управлять моделями на LM Studio - узнать что загружено, загрузить или выгрузить модель, задать длину контекста и параллельность, отключить размышления модели, - а также при диагностике: модель…
1c-naparnik
1C:Naparnik (1С:Напарник) MCP server tools - BSL code analysis, review, rewriting, ITS knowledge base, platform documentation search, configuration documentation. Use when checking BSL code quality, searching ITS standards, reading platform docs, comparing versions, or finding configuration-specific documentation.