agentmods.dev

mcp-gtags-server: Instructions file for Claude Code

CLAUDE.md

mcp-gtags-server CLAUDE.md is an instructions file for Claude Code from harshithsunku/mcp-gtags-server. It costs 2,310 tokens per session, scanned A, original, MIT.

Repository instructions for AI assistants working on an MCP server that provides GNU Global code navigation for large C and C++ codebases. GNU Global creates an index so code symbols can be found without searching every file as plain text.

In plain words
What is it for?
Use them when modifying or reviewing the mcp-gtags-server repository, its Python server, indexing toolchain, code-navigation tools or Linux-kernel-specific symbol handling.
Why use it?
They give an assistant the project layout, command-line details and special handling for Linux-kernel code. This helps it understand how the server's tools and symbol lookup work.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md.

This is harshithsunku/mcp-gtags-server's own configuration. It tells Claude Code how to work on mcp-gtags-server 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 mcp-gtags-server configures →

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /home/ai/linux.

not rated 1repo 1mo ago A scan 2,310 tokens original MIT
View source ↗ harshithsunku/mcp-gtags-server pypi.org
Reuse

Borrowing it

Nothing to install: this file belongs to harshithsunku/mcp-gtags-server. 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/harshithsunku/mcp-gtags-server/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/harshithsunku/mcp-gtags-server

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 mcp-gtags-server CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/harshithsunku/mcp-gtags-server/claude-md"><img src="https://agentmods.dev/badge/instructions/harshithsunku/mcp-gtags-server/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,310 This file is loaded in full into every session.
When invoked 2,310 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 $0.02310 $0.02310
Opus 5 $0.01155 $0.01155
Sonnet 5 $0.00462 $0.00462
Haiku 4.5 $0.00231 $0.00231

Measured 9d ago against content hash b679ec849022, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

mcp-gtags-server 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 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.

CLAUDE.md · 157 lines

How it starts

The opening of the file, as written. The whole thing — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Context for AI assistants working on this repository.

What this project is

mcp-gtags-server — an MCP (Model Context Protocol) server that exposes GNU Global (gtags) code navigation for C/C++ codebases, tuned for Linux-kernel-scale trees (37M+ lines). Published to PyPI, the MCP Registry (io.github.harshithsunku/mcp-gtags-server), and as a Claude Desktop .mcpb bundle. Python ≥ 3.10, packaged with uv.

The pitch: indexed symbol lookups instead of grep, with kernel-specific smarts that plain gtags lacks — macro-generated symbol resolution (SYSCALL_DEFINE3, DEFINE_SPINLOCK, …), recovery of definitions the Global parser missed (via their EXPORT_SYMBOL* site + ctags), #ifdef guard stacks on every result, and kernel-.config-aware filtering (active_config).

Layout

src/gtags_mcp/
  server.py      (~2300 lines) MCP tools, root detection, index lifecycle, CLI main()
  toolchain.py   toolchain install: managed GNU Global/ctags/Pygments in ~/.gtags-mcp
  guards.py      #if/#ifdef guard-stack scanner + active_config evaluation
  macros.py      macro-generated symbol resolution (SYSCALL_DEFINE etc.), EXPORT_SYMBOL detection
  enrich.py      ctags metadata enrichment (kind/typeref/scope/signature); probe_binary + cache
  config.py      settings: CLI flag > env var > project .gtags-mcp.toml > user config > default
                 user config: ${XDG_CONFIG_HOME:-~/.config}/gtags-mcp/config.toml
  output.py      JSON envelope: {tool, root, results, total, truncated, hints, message, ...}
  fileset.py     file listing helpers
  evalharness.py golden-set eval runner (see Evals below)
tests/           pytest suite (315 tests, ~4s, no network; heavy use of tmp fixture projects)
evals/golden.jsonl        65-case golden set run against a real kernel tree
evals/agent/              agent A/B eval harness (run_ab.py, grade.py, questions.jsonl)
scripts/stability_exercise.py  operational latency/size matrix against a real tree
docs/capability.md        capability matrix; docs/bringup-hurdles.md
mcpb/manifest.json        Claude Desktop bundle manifest
.github/workflows/        ci.yml, eval.yml, publish.yml, publish-registry.yml, release-binaries.yml

Read the full file on GitHub · 157 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. 9d ago First seen · 157 lines · 2,310 tokens per session scan A b679ec849022

Subscribe to this mod's changes

mcp-gtags-server CLAUDE.md is an instructions file published in the GitHub repository harshithsunku/mcp-gtags-server (1 stars, last pushed 1mo ago), licensed MIT. It adds 2,310 tokens to every session, about $0.0115 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.

C and C++Claude CodeLanguagesai-agentsclaudecode-navigationcode-searchcursor
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 · 3,735 tokens