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 instructions/catter58/mcpbpmsoft/claude-mdgit clone --depth 1 https://github.com/Catter58/mcpBPMSoftWrote 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/instructions/catter58/mcpbpmsoft/claude-md)<a href="https://agentmods.dev/instructions/catter58/mcpbpmsoft/claude-md"><img src="https://agentmods.dev/badge/instructions/catter58/mcpbpmsoft/claude-md.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 | $0.02398 | $0.02398 |
| Opus 5 | $0.01199 | $0.01199 |
| Sonnet 5 | $0.00480 | $0.00480 |
| Haiku 4.5 | $0.00240 | $0.00240 |
Grade A, and why
mcpBPMSoft CLAUDE.md 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 4d 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 — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Руководство для Claude Code (и других LLM-агентов) по работе с этим репозиторием. Сервер реализует MCP-интеграцию с BPMSoft OData API на TypeScript (ESM, Node 18+).
Архитектура
Слои (сверху вниз — от MCP-вызова к сети):
- Tools —
src/tools/*.ts. Каждый файл (read-tools.ts,write-tools.ts,schema-tools.ts,batch-tools.ts,stream-tools.ts,init-tool.ts) регистрирует MCP-инструменты черезserver.registerTool. Метаданные (title/description/annotations/blurb/category) живут в едином реестреsrc/tools/registry.ts— это единственный источник правды. - Service Container — собирается в
init-tool.ts(initializeServices/createEmptyContainer). Контейнер хранитauthManager,odataClient,lookupResolver,metadataManager,httpClientиconfig. Инструменты получают контейнер по ссылке и используютnotInitialized()guard, если сервер ещё не сконфигурирован. - ODataClient —
src/client/odata-client.ts. Строит URL-ы коллекций с учётом версии OData (v3/v4) и платформы (net8/netframework), сериализует параметры запроса ($filter,$select,$expand,$orderby,$top,$skip,/$count). - HttpClient —
src/client/http-client.ts. Тонкая обёртка надfetchс управлением cookies, тайм-аутами, ретраями и проверкой origin. Здесь же —buildHeaders(contentKind). - Типы —
src/types/index.ts(BpmConfig,ODataVersion,PlatformType, и пр.).
Модель авторизации и транспорт
Транспорт по умолчанию — Streamable HTTP (порт MCP_HTTP_PORT, default 8007).
Для локальной отладки: MCP_TRANSPORT=stdio.
Авторизация по умолчанию — per-request.
Каждый входящий HTTP-запрос должен нести заголовок BPMCSRF и cookie .ASPXAUTH,
BPMSESSIONID, CsrfToken. Сервер извлекает их через AsyncLocalStorage и пробрасывает
в OData-запросы к BPMSoft. Секреты на сервере не хранятся. Запрос без авторизации →
AuthRequiredError. Эта модель аналогична mcp-proxy-server.
BPMSOFT_URL — единственная обязательная переменная среды. Если не задана — сервер
завершается с фатальной ошибкой при старте.
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.
- 4d ago First seen · 150 lines · 2,398 tokens per session scan A 4dcc67513423
mcpBPMSoft CLAUDE.md is an instructions file published in the GitHub repository Catter58/mcpBPMSoft (0 stars, last pushed yesterday), licensed MIT. It adds 2,398 tokens to every session, about $0.0120 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 instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.