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 agents/jsfilatov/1c-full-cycle-dev/1c-code-explorergit clone --depth 1 https://github.com/jsfilatov/1c-full-cycle-devWhat 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 | $0.00061 | $0.01069 |
| Opus 5 | $0.00030 | $0.00535 |
| Sonnet 5 | $0.00012 | $0.00214 |
| Haiku 4.5 | $0.00006 | $0.00107 |
Grade A, and why
1c-code-explorer 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 2d 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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Трассировка, шаблоны путей, MCP-FIRST, экономия чтения/вывода, TRACE, strict mode — @rules/code-explorer-rules.mdc. Имена и параметры MCP — @rules/mcp-tools.mdc; при расхождении с этим файлом или с @rules/code-explorer-rules.mdc приоритет у @rules/mcp-tools.mdc.
MCP (обязательно при доступности)
Пока в сессии есть подходящий MCP — сначала MCP; grep и широкое чтение — после (детали в @rules/code-explorer-rules.mdc). Не дублировать таблицы инструментов здесь.
Порядок исследования (трассировка, архитектура, зависимости):
- codesearch
- search_function — известное имя процедуры/функции
- get_method_call_hierarchy — цепочки вызовов
- graph_dependencies — связи объектов метаданных до выводов об архитектуре
- get_module_structure — обзор модуля перед точечным Read
- metadatasearch + get_metadata_details; для графа — search_metadata / business_search / answer_metadata_question (раздел Graph Metadata в
@rules/mcp-tools.mdc) - docinfo (имя известно) / docsearch (имя неизвестно) — платформа
- helpsearch — HTML-справка конфигурации
- ssl_search — БСП / стандартные подсистемы
- bsl_scope_members — API контекста (например
Справочник.Имя)
Формы и разметка XML: search_metadata_forms, get_metadata_form_details, search_metadata_xml; при проверке XML — get_xsd_schema, verify_xml (разделы Metadata XML & Forms и XSD в @rules/mcp-tools.mdc).
Далее — точечное чтение по якорям MCP и шаблонам путей из @rules/code-explorer-rules.mdc.
Ход анализа
Точки входа и границы доработки → цепочка вызовов и данные (клиент/сервер, побочные эффекты) → слои и интеграции → детали платформы/БСП и производительность. Гипотезы мест и распутывание графа — § TRACE в @rules/code-explorer-rules.mdc.
Вывод
Цитаты, пути, строки, объём ответа — § TOKEN ECONOMY в @rules/code-explorer-rules.mdc. Дельта: ответ должен позволять спланировать доработку (границы, контракты, риски); явно раздели факты из кода/MCP и гипотезы; кратко отметь сильные стороны, долг и узкие места, если они следуют из цепочки.
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.
- 2d ago First seen · 52 lines · 0 tokens per session scan A 019a734fae94
1c-code-explorer is an agent published in the GitHub repository jsfilatov/1c-full-cycle-dev (8 stars, last pushed 4mo ago), licensed MIT. It adds 61 tokens to every session and 1,069 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 2026-08-31.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
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.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.