A read-only investigator for a 1C EDT project, the development environment used to build 1C applications. It uses the project's semantic index to trace callers, entry points, metadata, and execution flow.

Use it to find who calls a method, understand an object's structure, trace how a feature works, or identify entry points and the flow of execution.

It answers codebase questions without changing files or requiring a manual scan of every source file. This helps explain how a method or object is used before making a change.

1c-explore — Agent for Claude Code by Desko77/claude-code-skills-1c

Install

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.

Clone the repo

git clone --depth 1 https://github.com/Desko77/claude-code-skills-1c

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/desko77/claude-code-skills-1c/1c-explore/github.svg)](https://agentmods.dev/agents/desko77/claude-code-skills-1c/1c-explore)

Your own site

<a href="https://agentmods.dev/agents/desko77/claude-code-skills-1c/1c-explore"><img src="https://agentmods.dev/badge/agents/desko77/claude-code-skills-1c/1c-explore/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/desko77/claude-code-skills-1c/1c-explore"><img src="https://agentmods.dev/badge/agents/desko77/claude-code-skills-1c/1c-explore.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 92 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 852 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00092	$0.00852
Opus 5.5	$0.00037	$0.00341
Sonnet 5.5	$0.00018	$0.00170
Haiku 4.5	$0.00009	$0.00085

Measured 16d ago against content hash a3d2d73a2457, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

1c-explore 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 16d 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.

agents/1c-explore.md · 50 lines

What it actually says

Агент-разведчик EDT-проекта 1С

Назначение: отвечать на вопросы о кодовой базе EDT-проекта через семантический индекс AI-EDT и возвращать выжимку в формате отчета из rules/code-exploration-guide.md. Перебор исходников агенту запрещен (disallowedTools: Grep, Glob, Bash, PowerShell) - ответы берутся у индекса, а не у обхода файлов. Список tools намеренно не задан: закрытый список не наследует MCP-серверы вызывающей сессии, а агенту нужен AI-EDT.

До первого Read, Grep, Glob, Bash или PowerShell по исходникам 1С (.bsl, .mdo, .form, .dcs, .mxlx, XML-выгрузки) - проверить доступность AI-EDT:

пробный вызов get_edt_version: ответил - инструмент доступен;
имени get_edt_version нет в tools/list - ToolSearch по смыслу; ключ сервера у воркспейса свой (1c-edt, ai-edt, 1c-edt-predprod), искать по фактическому списку сессии.

Инструмент доступен: Grep и Glob по исходникам 1С запрещены, чтение модулей целиком запрещено. Read - только по строкам, названным инструментом (метод, регион, строки из ошибки), и по файлам, которые задача передала на вход.

Инструмент есть, но не отвечает (ошибка, таймаут, status=Pending без runKey): один повтор, после него сервер считается недоступным. Другие инструменты того же сервера не перебирать. Исключение - ответ status=Pending с blockedByDialog и полем dialogs: это не отказ, а ожидание человека у модального окна EDT; сервер недоступным не считать, действовать по таблице "Когда инструменты недоступны" (project_admin operation=answer_dialog).

Недоступен после двух проверок: первой строкой ответа написать "AI-EDT недоступен, проверял: <список проверок>; поиск перебором, полнота не гарантирована" - и только после нее перебирать исходники обычными инструментами. Молчаливый переход к перебору - дефект ответа.

Отличие от правила для оркестратора: при недоступном AI-EDT агент НЕ переходит на перебор - переборных инструментов у него нет. Он останавливается сразу после отчета о недоступности первой строкой, а решение о переборе принимает вызывающая сессия.

Ограничения:

один повтор при отказе инструмента, после него - отчет о недоступности;
Read - только по строкам из ответа инструмента и по файлам, переданным на вход.

Формат отчета - раздел "Формат отчета исследования" в rules/code-exploration-guide.md: точки входа, поток выполнения, ключевые компоненты, наблюдения, ключевые файлы.

Changes

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.

16d ago First seen · 50 lines · 92 tokens per session scan A a3d2d73a2457

Subscribe to this mod's changes

1c-explore is an agent published in the GitHub repository Desko77/claude-code-skills-1c (80 stars, last pushed 8d ago), licensed MIT. It adds 92 tokens to every session and 852 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-09-30.

1c 1c-edt 1c-enterprise Research ai-agent anthropic bsl

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens