agentmods.dev

ktalk-mcp: Instructions file for Claude Code

CLAUDE.md

ktalk-mcp CLAUDE.md is an instructions file for Claude Code from mdemyanov/ktalk-mcp. It costs 2,199 tokens per session, scanned A, original, MIT.

A set of project instructions for `ktalk-mcp`, a package that provides an MCP server and command-line tool for working with Kontur.Talk recordings and their SQLite registry. An MCP server lets an AI assistant access connected application data through defined tools.

In plain words
What is it for?
Use it when developing, checking, or extending the `ktalk-mcp` package, its recording access, its SQLite registry, or its command-line interface.
Why use it?
It gives contributors the project’s required style, entry points, architecture, and command checks in one place. It also records important limits, such as the lack of mutating MCP tools.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; names the TodoWrite tool.

This is mdemyanov/ktalk-mcp's own configuration. It tells Claude Code how to work on ktalk-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything ktalk-mcp configures →

not rated 1repo 18d ago A scan 2,199 tokens original MIT
View source ↗ mdemyanov/ktalk-mcp
Reuse

Borrowing it

Nothing to install: this file belongs to mdemyanov/ktalk-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/mdemyanov/ktalk-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/mdemyanov/ktalk-mcp

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.

agentmods badge for ktalk-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/mdemyanov/ktalk-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/mdemyanov/ktalk-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/mdemyanov/ktalk-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/mdemyanov/ktalk-mcp/claude-md/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.

agentmods 80×15 button for ktalk-mcp CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/mdemyanov/ktalk-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/mdemyanov/ktalk-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,199 This file is loaded in full into every session.
When invoked 2,199 The same file — it is already loaded in full.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.02199 $0.02199
Opus 5 $0.01099 $0.01099
Sonnet 5 $0.00440 $0.00440
Haiku 4.5 $0.00220 $0.00220

Measured 8d ago against content hash 30232d827de2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

ktalk-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 8d 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.

CLAUDE.md · 143 lines

How it starts

The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ktalk-mcp

Пакет с двумя командами: MCP-сервер для доступа к записям Контур.Толк (KTalk) и CLI ktalk — операционный реестр записей на SQLite.

Стиль (безусловное правило)

Писать сухо и сжато — в ответах, коммитах, статьях content/, докстрингах. Вывод, потом обоснование; без преамбул, повторов и похвалы. Нет факта — так и сказать. Правило действует всегда и приоритетнее привычки к развёрнутости.

Entry points

  • ktalk-mcp = ktalk_mcp.server:main — MCP-сервер (контент: транскрипты, саммари)
  • ktalk = ktalk_mcp.cli:main — CLI реестра (механика: sync/дедуп/статусы/экспорт)

Commands

  • bash scripts/check.sh --fast — гейты контура (тот же прогон, что на pre-commit)

Architecture

Один пакет ktalk_mcp, общие client.py/config.py для MCP и CLI.

  • Мутирующего MCP-инструмента нет: планирование отдаёт только предпросмотр (ADR-005)
  • Пути API живут в таблице OPERATION_PROFILES (auth.py), не хардкодом в методах — набор путей зависит от режима авторизации
  • calendar_reader.py: окно календаря режется клиентом (сервер лимитирует 7 днями, потолок сегмента 100, skip не работает)
  • cli.py: _REGISTRY_FREE_COMMANDS — команды, не открывающие БД
  • contour_diagnostics.py — диагностика недокументированного контура (ADR-004)

API Reference

Контракты, режимы авторизации и эмпирика поведения API (спеке верить нельзя) — в src/ktalk_mcp/CLAUDE.md, грузится при работе с файлами под src/.

Conventions

  • Async everywhere (httpx, fastmcp)
  • Каждый MCP tool принимает параметр format: "raw" (JSON as-is) или "markdown" (human-readable)
  • ktalk_get_transcript поддерживает чанкинг: chunk (0=авто, 1+=номер чанка), chunk_size (символов, по умолчанию 30000)
  • Ошибки API → человекочитаемые сообщения на русском
  • Имена пользователей: surname firstname, fallback: login → anonymousName → "Неизвестный"
  • Длительность: секунды → "X ч Y мин" или "X мин"

CLI / реестр (registry)

  • SQLite — операционный source of truth; registry.md в vault — генерируемое read-only зеркало (ktalk export), не редактировать руками.
  • Статусы: new → done|skipped|partial, partial → done. Экспирация: записи new строго старше N дней (по умолчанию 7) → skipped при sync.
  • Конкурентность: WAL + busy_timeout=5000, транзакция на операцию — параллельные mark-* из фоновых агентов безопасны.
  • --json у всех команд печатает валидный JSON в stdout; ошибки — в stderr с ненулевым кодом возврата (навык/агент парсят stdout).
  • Путь к БД бинарный → gitignore в vault (.registry.db, -wal, -shm).
  • ktalk migrate <vault> — разовый импорт из markdown-реестров; парсер устойчив к 7/8-колоночным архивам и | внутри ячеек.

Read the full file on GitHub · 143 lines

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.

  1. 8d ago First seen · 143 lines · 2,199 tokens per session scan A 30232d827de2

Subscribe to this mod's changes

ktalk-mcp CLAUDE.md is an instructions file published in the GitHub repository mdemyanov/ktalk-mcp (1 stars, last pushed 18d ago), licensed MIT. It adds 2,199 tokens to every session, about $0.0110 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.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

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).

microsoft/vscode · 5,001 tokens

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.

langchain-ai/langchain · 4,469 tokens

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.

deepseek-ai/deepseek-harness · 3,737 tokens