yandex-wiki-search-mcp: Command for Claude Code

.claude/commands/add-tool.md

add-tool is a command for Claude Code from dlbolshov/yandex-wiki-search-mcp. It costs 11 tokens per session (309 once invoked), scanned A, original, Apache-2.0.

A coding task for adding a new MCP tool to yandex-wiki-search-mcp, a service that lets agents work with Wiki pages.

In plain words
What is it for?
Adding a read or write Wiki tool, registering it in the correct module, updating related tests, and revising the project's README, manifest, and changelog.
Why use it?
It turns a tool request into a defined implementation checklist covering code locations, read-only versus write behavior, tests, and documentation.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions CLAUDE.md.

This is dlbolshov/yandex-wiki-search-mcp's own configuration. It tells Claude Code how to work on yandex-wiki-search-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 yandex-wiki-search-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to dlbolshov/yandex-wiki-search-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/dlbolshov/yandex-wiki-search-mcp/main/.claude/commands/add-tool.md
Clone the repo
git clone --depth 1 https://github.com/dlbolshov/yandex-wiki-search-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 add-tool

README.md
[![agentmods](https://agentmods.dev/badge/commands/dlbolshov/yandex-wiki-search-mcp/add-tool/github.svg)](https://agentmods.dev/commands/dlbolshov/yandex-wiki-search-mcp/add-tool)
Your own site
<a href="https://agentmods.dev/commands/dlbolshov/yandex-wiki-search-mcp/add-tool"><img src="https://agentmods.dev/badge/commands/dlbolshov/yandex-wiki-search-mcp/add-tool/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 add-tool

Your own site · 80×15
<a href="https://agentmods.dev/commands/dlbolshov/yandex-wiki-search-mcp/add-tool"><img src="https://agentmods.dev/badge/commands/dlbolshov/yandex-wiki-search-mcp/add-tool.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 309 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00011 $0.00309
Opus 5 $0.00005 $0.00154
Sonnet 5 $0.00002 $0.00062
Haiku 4.5 $0.00001 $0.00031

Measured 11d ago against content hash 42d3f2926f47, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

add-tool 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 11d 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/commands/add-tool.md · 30 lines

What it actually says

Task

Add a new MCP tool to yandex-wiki-search-mcp.

Always follow @CLAUDE.md.

Instructions

  1. Keep the implementation aligned with the current Wiki architecture:
    • protocol in mcp_wiki/wiki/proto/pages.py
    • models in mcp_wiki/wiki/proto/types/pages.py
    • HTTP implementation in mcp_wiki/wiki/custom/client.py
    • MCP registration in mcp_wiki/mcp/tools/page_read.py or mcp_wiki/mcp/tools/page_write.py
  2. If the tool is read-only, register it only in page_read.py.
  3. If the tool mutates Wiki state, register it only in page_write.py and make sure it is hidden in read-only mode.
  4. Add or update tests:
    • HTTP-level tests in tests/wiki/custom/ when client behavior changes
    • MCP-level tests in tests/mcp/tools/
    • registration checks in tests/mcp/server/test_server_creation.py when a new tool is added
  5. Update @README.md, @README_ru.md, @manifest.json, and @CHANGELOG.md.

Tool description

$ARGUMENTS

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. 11d ago First seen · 30 lines · 11 tokens per session scan A 42d3f2926f47

Subscribe to this mod's changes

add-tool is a command published in the GitHub repository dlbolshov/yandex-wiki-search-mcp (6 stars, last pushed 16d ago), licensed Apache-2.0. It adds 11 tokens to every session and 309 once invoked, about $0.0001 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.