c-code-navigation

c-code-navigation is a skill for Claude Code from harshithsunku/mcp-gtags-server. It costs 59 tokens per session (805 once invoked), scanned A, original, MIT.

An indexed navigation guide for large C and C++ codebases, including Linux kernels, firmware, and vendor board software. It uses GNU Global indexes to find definitions, callers, callees, references, and possible call paths instead of relying on text searches.

In plain words
What is it for?
Use it to trace who calls a function, what a function calls, where a symbol is defined, where it is used, whether one function can reach another, and what a file defines. Refresh the index after editing source files.
Why use it?
It reduces the noise and missed results that come from searching millions of lines with grep. It also helps account for conditional code marked with #ifdef, which enables different source depending on configuration.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the mcp-gtags-server plugin — 1 skill, 1 MCP server shipped together

Good fit Use it to trace who calls a function, what a function calls, where a symbol is defined, where it is used, whether one function can reach another, and what a file defines. Refresh the index after editing source files.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/harshithsunku/mcp-gtags-server/c-code-navigation
Install

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.

Any agent
npx skills add harshithsunku/mcp-gtags-server --skill c-code-navigation
Clone the repo
git clone --depth 1 https://github.com/harshithsunku/mcp-gtags-server

Made for: Claude Code.

Or install mcp-gtags-server, the plugin that ships this one along with the rest of its 1 skill, 1 MCP server.

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 c-code-navigation

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/harshithsunku/mcp-gtags-server/c-code-navigation"><img src="https://agentmods.dev/badge/skills/harshithsunku/mcp-gtags-server/c-code-navigation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 59 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 805 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 $0.00059 $0.00805
Opus 5.5 $0.00024 $0.00322
Sonnet 5 $0.00012 $0.00161
Haiku 4.5 $0.00006 $0.00081

Measured 5d ago against content hash d5daccb878da, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-23, from the pricing page.

Security

Grade A, and why

c-code-navigation 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 5d 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.

plugin/skills/c-code-navigation/SKILL.md · 64 lines

How it starts

The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.

These tools answer from a GNU Global index built from the source itself: no build, no compile_commands.json, every #ifdef variant of every config. Results come back as compact path:line: source rows.

Which tool for which question

Question Tool
Who calls this function? What would this change break? find_callers (dedupes per calling function, shows each call's source line)
Where is this defined? What is it? How widely used? find_definition (definitions + #ifdef guards + usage summary)
Every usage, including in a specific directory find_references (path_prefix="fs/ext4", group_by)
What does this function call? find_callees
Can A reach B, and through what? reachability
Show me the implementation get_symbol_body (the body only, not the file)
What does this file define? list_file_symbols
I just edited files and need fresh results now update_index

Keep using grep for string literals, comments, log messages, Kconfig and Makefiles, and anything that is not a C/C++ symbol. Grep is one cheap call for those; these tools win when the answer is a symbol relationship or when grep would return hundreds of lines.

Reading the output

path:line: source line [kind; #if CONFIG_X] — the tag shows what the symbol is and the #ifdef stack it lives under. A footer like [1-100 of 5290 · offset=100 for more] means there is another page. Results end with next: naming the most useful follow-up tool. Pass format="json" if you need to parse the envelope instead.

Rules that save round-trips

  • Pick the repository explicitly when more than one is open, or when the server reports it cannot determine one: project_root="/abs/path/to/repo".
  • Hot symbols: over 200 references come back grouped by file. Narrow with path_prefix rather than paging through thousands of sites.
  • First query on a new repository may answer "indexing in progress" — the index is building in the background; retry shortly.
  • Kernel specifics: pass active_config="/path/to/.config" to drop definitions your config cannot compile; macro-generated names resolve to their generator site (flagged resolved_via).

Read the full file on GitHub · 64 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. 5d ago First seen · 64 lines · 59 tokens per session scan A d5daccb878da

Subscribe to this mod's changes

c-code-navigation is a skill published in the GitHub repository harshithsunku/mcp-gtags-server (1 stars, last pushed 4d ago), licensed MIT. It adds 59 tokens to every session and 805 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-18.

Related

Other skills, from other repositories

unreal-live-coding

Trigger Live Coding compilation via UCP. Use when the user asks to recompile C++ code, trigger live coding, hot reload C++ changes, or check compilation status in Unreal Engine.

Italink/UnrealClientProtocol · 44 tokens

torchtalk-analyzer

Analyze PyTorch internals across Python, C++, and CUDA layers using the TorchTalk MCP server. Use when asked about how PyTorch operators work internally, where functions are implemented, what would break if code is modified, or finding tests for PyTorch operators.

opendatahub-io/ai-helpers · 58 tokens

torchtalk-trace

Trace a PyTorch function's cross-language binding chain (Python -> C++ -> CUDA).

opendatahub-io/ai-helpers · 24 tokens

vs-search

Routing rules for code search in C/C++, C#/.NET, JS/TS, and Python projects via vs-token-safer — use the vs-search MCP tools (clangd/Roslyn/tsserver/pyright language-server index) or the vts CLI instead of Bash grep. Use whenever searching for a symbol, definition, function, variable, type, or finding…

JSungMin/vs-token-safer · 109 tokens

agent-cpp-build-resolver

C++ build, CMake, and compilation error resolution specialist. Fixes build errors, linker issues, and template errors with minimal changes. Use when C++ builds fail.

KunanonJ/ai-skills-hub · 42 tokens

agent-cpp-reviewer

Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.

KunanonJ/ai-skills-hub · 43 tokens