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/tehprof/support-mcp/claude-mdgit clone --depth 1 https://github.com/tehprof/support-mcpWrote 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/tehprof/support-mcp/claude-md)<a href="https://agentmods.dev/instructions/tehprof/support-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/tehprof/support-mcp/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 | $0.01821 | $0.01821 |
| Opus 5 | $0.00911 | $0.00911 |
| Sonnet 5 | $0.00364 | $0.00364 |
| Haiku 4.5 | $0.00182 | $0.00182 |
Grade A, and why
support-mcp 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 3d 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 — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Support MCP Server — CLAUDE.md
⛔ ГЛОБАЛЬНЫЕ ПРАВИЛА (подробности → /srv/CLAUDE.md)
#0 Ошибки первым делом — проверить ошибки ПЕРЕД любой задачей +
bash /root/.claude/hooks/guardian-check.sh#1 Автоклассификация — вопрос / любое изменение=architect-first / крупное=волны (категорий "мелкий"/"средний" НЕТ) + чеклисты до и после кода #2 Auto-Skills — hook подсказал Skill → вызвать Skill tool (security, perf, pipeline, qa...) TOOL USAGE — MCP (docker, postgres, redis, playwright, context7) вместо Bash Самоочистка — удалять temp файлы после задачи Размер файлов — Backend: 400 | Frontend: 350 | CSS: 250 строк Новый сервис →/master-architectобязательно
Назначение
MCP (Model Context Protocol) сервер для TehProf Support. Позволяет любому AI-клиенту (Claude, GPT, Gemini) управлять системой поддержки через стандартный протокол.
Stack
- Runtime: Node.js 20 + TypeScript strict
- SDK:
@modelcontextprotocol/sdkv1.12+ - Transport: Streamable HTTP (MCP spec 2025-03-26)
- Port: 8101 (127.0.0.1)
- Systemd:
support-mcp.service
Структура
mcp-server/
├── src/
│ ├── index.ts # HTTP server + MCP transport
│ ├── auth.ts # API key validation
│ ├── types.ts # TypeScript types + tier logic
│ ├── tool-registry.ts # Tool registration + tier gating
│ ├── support-client.ts # HTTP client → PHP backend
│ └── tools/
│ ├── free/ # Free tier tools
│ │ ├── knowledge.ts # knowledge_search/read/list
│ │ ├── onboarding.ts # onboarding_guide/features
│ │ ├── demo.ts # demo_create_ticket/view/workflow
│ │ ├── pricing.ts # pricing_plans/calculate
│ │ └── system.ts # system_health/info/tenant_info
│ ├── paid/ # Paid tier tools
│ │ ├── tickets.ts # tickets_list/get/create/reply/update
│ │ ├── analytics.ts # analytics_dashboard/sla/operators
│ │ ├── settings.ts # settings_get/update/operators
│ │ ├── channels.ts # channels_list/status/configure
│ │ └── automation.ts # automation_rules + webhooks
│ └── bitrix/
│ └── proxy.ts # bitrix_contacts/deals/tasks/users
├── dist/ # Compiled JS
├── package.json
└── tsconfig.json
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.
- 3d ago First seen · 127 lines · 1,821 tokens per session scan A 0a675fa4adfa
support-mcp CLAUDE.md is an instructions file published in the GitHub repository tehprof/support-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 1,821 tokens to every session, about $0.0091 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
Zammad-MCP AGENTS.md
AGENTS.md instructions for basher83/Zammad-MCP, covering automation foundation, definitions, mandatory minimal automation bootstrap, bootstrap requirements and bootstrap objectives.
Zammad-MCP CLAUDE.md
Claude Code instructions for basher83/Zammad-MCP, a project described as: A Model Context Protocol (MCP) server for Zammad integration, enabling AI assistants to interact with tickets, users, and organizations.
Unreal-MCP CLAUDE.md
Instructions for IvanMurzak/Unreal-MCP, covering claude.md — unreal-mcp, architecture in one screen, layout, editor vs runtime (in-game) and build / test (per leg).
calc-mcp CLAUDE.md
Claude Code instructions for coo-quack/calc-mcp, covering project rules, tech stack, commands, project structure and tool architecture.
pfsense-mcp-server AGENTS.md
AGENTS.md instructions for night4me/pfsense-mcp-server, covering pfsense mcp server, architecture and security, development workflow, long-running validation and test parallelism.
Noema AGENTS.md
Instructions for Fail-Safe/Noema, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and testing guidelines.