code-index-mcp: Skill for Claude Code

.agents/skills/verify-multilang-support/SKILL.md

verify-multilang-support is a skill for Claude Code, Codex from johnhuang316/code-index-mcp. It costs 43 tokens per session (851 once invoked), scanned A, original, MIT.

A verification process for checking that a code indexer understands all supported programming languages. It compares search results, file summaries, symbols, function bodies, imports, and caller relationships with expected baselines.

In plain words
What is it for?
Use it to test tree-sitter language strategies, symbol extraction, deep indexing, code search, imports, summaries, and called-by relationships in sample projects.
Why use it?
A non-empty search result can still be wrong or incomplete. The checks expose parser and indexing regressions after language or indexing changes.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is johnhuang316/code-index-mcp's own configuration. It tells Claude Code and Codex how to work on code-index-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 code-index-mcp configures →

About the project

Code Index MCP is a Model Context Protocol server that indexes code repositories so language models can search, examine, and navigate their contents. It supports tasks such as code review, refactoring, documentation, debugging, and architecture analysis. The catalogue skills help coding agents use the server's repository analysis workflow.

johnhuang316/code-index-mcp · 1,005 stars · on GitHub

Reuse

Borrowing it

Nothing to install: this file belongs to johnhuang316/code-index-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/johnhuang316/code-index-mcp/master/.agents/skills/verify-multilang-support/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/johnhuang316/code-index-mcp

Made for: Claude Code, Codex.

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 verify-multilang-support

README.md
[![agentmods](https://agentmods.dev/badge/skills/johnhuang316/code-index-mcp/verify-multilang-support/github.svg)](https://agentmods.dev/skills/johnhuang316/code-index-mcp/verify-multilang-support)
Your own site
<a href="https://agentmods.dev/skills/johnhuang316/code-index-mcp/verify-multilang-support"><img src="https://agentmods.dev/badge/skills/johnhuang316/code-index-mcp/verify-multilang-support/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 verify-multilang-support

Your own site · 80×15
<a href="https://agentmods.dev/skills/johnhuang316/code-index-mcp/verify-multilang-support"><img src="https://agentmods.dev/badge/skills/johnhuang316/code-index-mcp/verify-multilang-support.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 851 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00043 $0.00851
Opus 5 $0.00022 $0.00426
Sonnet 5 $0.00009 $0.00170
Haiku 4.5 $0.00004 $0.00085

Measured 9d ago against content hash 77e633a8fcb8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

verify-multilang-support 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 9d 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.

.agents/skills/verify-multilang-support/SKILL.md · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Verify Multi-Language Support

Overview

Verify search and deep indexing for every supported sample language. Non-empty results are insufficient; summaries must match maintained baselines.

When to Use

  • A language strategy, tree-sitter query, symbol range, indexer, or sample changes.
  • Search, summaries, symbol bodies, imports, or called_by may have regressed.

Run focused unit tests first when a specific failing strategy is known.

Verification Loop

Use each row in Targets, resolving paths below test/sample-projects.

  1. Call set_project_path with the sample project's absolute path.
  2. Call refresh_index, then build_deep_index.
  3. Run the query with search_code_advanced in literal mode.
  4. Call get_file_summary for the preferred file, then read the baselines and compare:
    • exact language
    • symbol_count at or above the minimum
    • every expected function, method, class, import, and called_by relationship
  5. Call get_symbol_body; require status: success and non-empty code.
  6. Record SEARCH, SUMMARY, SYMBOL_BODY, and FINAL. Any failed assertion makes the language FAIL.

After the final target, restore set_project_path to the repository root and call refresh_index.

Targets

Language Relative path Literal query Expected symbol Preferred file
Python python class UserManager cli user_management/cli.py
Go go/user-management UserService CreateUser internal/services/user_service.go
Java java/user-management class UserManager UserManager.createUser src/main/java/com/example/usermanagement/services/UserManager.java
JavaScript javascript/user-management class UserService UserService.createUser src/services/UserService.js
TypeScript typescript/user-management class UserService user src/services/UserService.ts
C# csharp/orders class OrderService Orders.Services.OrderService.Create src/Orders/Services/OrderService.cs
Kotlin kotlin/notes-api class NotesService NotesService.createNote src/main/kotlin/com/example/notes/NotesService.kt
Rust rust/conversation struct Conversation Conversation.append src/conversation.rs
Objective-C objective-c interface UserManager UserManager.addUser UserManager.m
Zig zig/code-index-example fn main main src/main.zig

Read the full file on GitHub · 79 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 9d ago First seen · 79 lines · 43 tokens per session scan A 77e633a8fcb8

Subscribe to this mod's changes

verify-multilang-support is a skill published in the GitHub repository johnhuang316/code-index-mcp (1,005 stars, last pushed 1mo ago), licensed MIT. It adds 43 tokens to every session and 851 once invoked, about $0.0002 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 2026-08-30.

Related

Other skills, from other repositories

compiler-port

Port a compiler pass from TypeScript to Rust. Gathers context, plans the port, implements in a subagent with test-fix loop, then reviews.

react/react · 35 tokens

build-and-test

How to build and test .NET projects in the Agent Framework repository. Use this when verifying or testing changes.

microsoft/agent-framework · 26 tokens

migrate-xunit-to-xunit-v3

Migrate .NET test projects from xUnit.net v2 to xunit.v3 and fix v3 breaks. Use for package/CPM conversion, OutputType=Exe, preserving the VSTest or MTP runner (including projects currently using YTest.MTP.XUnit2), incompatible TFMs, async void tests, string-to-Type attributes, custom Fact/Theory/BeforeAfterTest…

dotnet/skills · 149 tokens

platform-detection

Identify a .NET project's test platform, framework, command mode, and SDK-style vs classic project system. Use only for "which test platform/framework?", "VSTest or MTP?", or "what runner does this project use?", including bridge settings, UseVSTest opt-outs, and incompatible or conflicting VSTest/MTP configuration.…

dotnet/skills · 146 tokens

golang-testing

Production-ready Golang tests — table-driven tests, testify suites and mocks, parallel tests, fuzzing, fixtures, goroutine leak detection with goleak, snapshot testing, code coverage, integration tests, idiomatic test naming. Use when writing or reviewing Go tests, choosing a testing approach, setting up Go test CI…

samber/cc-skills-golang · 115 tokens

adk-setup

Sets up a local ADK Python development environment in a git clone of the open-source adk-python repository: a uv virtual environment, all dependency extras, pre-commit hooks, and a first unit-test run. Runs only when explicitly requested, never on its own. Use when asked to set up, bootstrap, or repair a development…

google/adk-python · 146 tokens