What is stellaris-explore?

A code-exploration guide that routes searches to Stellaris MCP, a tool for finding code by names or meaning, or to ordinary grep and rg searches. It also guides reading large files and tracing imports and dependencies.

Use it to locate symbols, find where a feature lives, outline large files, inspect one symbol, find callers and dependencies, and search project documentation.

It reduces wasted searches and helps avoid missing definitions, occurrences, or related code in an unfamiliar repository.

stellaris-explore — Skill for Claude Code by GDM-Pixel

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 GDM-Pixel/stellaris-code-search --skill stellaris-explore

Clone the repo

git clone --depth 1 https://github.com/GDM-Pixel/stellaris-code-search

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/gdm-pixel/stellaris-code-search/stellaris-explore/github.svg)](https://agentmods.dev/skills/gdm-pixel/stellaris-code-search/stellaris-explore)

Your own site

<a href="https://agentmods.dev/skills/gdm-pixel/stellaris-code-search/stellaris-explore"><img src="https://agentmods.dev/badge/skills/gdm-pixel/stellaris-code-search/stellaris-explore/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/gdm-pixel/stellaris-code-search/stellaris-explore"><img src="https://agentmods.dev/badge/skills/gdm-pixel/stellaris-code-search/stellaris-explore.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 64 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 895 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.

Model	Per session	Once invoked
Fable 5.1	$0.00064	$0.00895
Opus 5.5	$0.00026	$0.00358
Sonnet 5.5	$0.00013	$0.00179
Haiku 4.5	$0.00006	$0.00089

Measured 15d ago against content hash 463f647dd5d3, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

stellaris-explore 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 15d 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.

skills/stellaris-explore/SKILL.md · 61 lines

How it starts

The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Stellaris explore

search_code classifies the query (query_kind, skipped_vector, QUERY_TOO_BROAD). Trust that. Do not add a second search_code "to be sure".

Grep/rg wins on a known name for occurrences. Stellaris wins for intent, ranked definition, and large-file outline/symbol. Identifier / dotted / quoted string → FTS only (never embeds; empty = no symbol, not a vector guess). Language keywords like export function are refused.

Routing

Need	Tool
Identifier / exact string, definition	`search_code` (FTS, no vector) or grep/rg
All occurrences, logs, lockfiles, generated dumps, CSS	grep/rg
Intent / name unknown	`search_code` (hybrid)
File known, ≳150 lines	`get_file_outline` then `get_symbol` for ONE body
File known, small	Read the file — `get_symbol` wrapping an 80-line file costs more
Impact	`get_blast_radius`
Imports	`get_dependents` / `get_dependencies`
Docs meaning	`search_docs`
Identifier / exact miss (`skipped_vector: true`, empty)	grep/rg — do not rephrase as intent
Intent miss	rewrite the intent once, or grep/rg if you now have a name

Optional path on search_code / search_docs / reindex / get_file_tree = another already-indexed project root. Not a reason to index $HOME. Not a substitute for cwd when you will edit.

Default search_code filter is code extensions only. Pass extensions (e.g. [".html"]) to include content files.

Sequence

session_briefing only at session start (or after compact).
If you already have a file path → get_file_outline (file ≳150 lines) or Read (small file). Never search_code to rediscover it. Skip get_file_folded unless outline is not enough.
If you have a symbol name and need the definition → search_code(name) (FTS, never embeds). Empty → grep/rg. Do not retry as intent. Then outline/symbol on the file it returned.
If you have an intent and no name → search_code in natural language. Then outline the top file, get_symbol for ONE body.
All call sites, logs, lockfiles, CSS dumps → grep/rg. Stellaris is a definition/intent index, not rg.

Read the full file on GitHub · 61 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.

15d ago Changed 463f647dd5d3
1mo ago First seen · 61 lines · 64 tokens per session scan A 00766cc16bc8

Subscribe to this mod's changes

stellaris-explore is a skill published in the GitHub repository GDM-Pixel/stellaris-code-search (4 stars, last pushed 17d ago), licensed MIT. It adds 64 tokens to every session and 895 once invoked, about $0.0003 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 2026-09-09.

Productivity ast claude code-search developer-tools embeddings lancedb

organize

Rules for acting on files and folders on disk — sort, move, copy, bulk-rename, rename by content, convert formats, create folder structures, or move to the trash. Plan every target path before changing anything, never overwrite or permanently delete, confirm with a listing, and report every change as old path → new…

Marker-Inc-Korea/AutoRAG · 70 tokens

codebase-search

Task-specific semantic code and documentation retrieval. Use compact context for unfamiliar repository orientation, direct lookup for known definitions, graph tools for relationships, and grep for exhaustive literal matches.

Helweg/open-codebase-index · 38 tokens

gno

Search local documents, files, notes, and knowledge bases. Index directories, search with BM25/vector/hybrid, get AI answers with citations. Use when user wants to search files, find documents, query notes, look up information in local folders, index a directory, set up document search, build a knowledge base, needs…

gmickel/gno · 86 tokens

stellaris-explore