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.
npx skills add harshithsunku/mcp-gtags-server --skill c-code-navigationgit clone --depth 1 https://github.com/harshithsunku/mcp-gtags-serverWrote 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.
[](https://agentmods.dev/skills/harshithsunku/mcp-gtags-server/c-code-navigation)<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.
<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>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.
| Model | Per session | Once 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 |
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.
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.
Navigating C/C++ code with an index
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_prefixrather 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 (flaggedresolved_via).
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.
- 5d ago First seen · 64 lines · 59 tokens per session scan A d5daccb878da
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.
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.
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.
torchtalk-trace
Trace a PyTorch function's cross-language binding chain (Python -> C++ -> CUDA).
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…
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.
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.