explore-codebase-index

A guide for exploring the indxr code repository through an index that maps files, declarations, imports, and relationships.

In plain words
What is it for?
Use it to locate modules, functions, types, and cross-file connections before reading or editing source code. indxr is the repository this guide is designed for.
Why use it?
It helps you understand a large codebase and find relevant code without opening many unrelated files.

Skill for Claude CodeCodexCursor

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.

agentmods
npx agentmods add skills/bahdotsh/indxr/explore-codebase-index
Any agent
npx skills add bahdotsh/indxr --skill explore-codebase-index
Clone the repo
git clone --depth 1 https://github.com/bahdotsh/indxr

Made for: Claude Code, Codex, Cursor.

Per session 67 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 477 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00067 $0.00477
Opus 5 $0.00034 $0.00238
Sonnet 5 $0.00013 $0.00095
Haiku 4.5 $0.00007 $0.00048

Measured 2d ago against content hash e74864b5b602, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

explore-codebase-index 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 2d 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.

.cursor/skills/explore-codebase-index/SKILL.md · 35 lines

What it actually says

Explore codebase via INDEX.md

When to use

Apply this skill when exploring this repository and the user (or task) needs a structural picture: files, functions, types, classes, and imports across the project.

Instructions

  1. Start with the index — Read .cursor/INDEX.md early. It aggregates what would otherwise require many file opens: tree layout, per-file summaries, declarations, and import relationships (generated from the project indexer).

  2. Use it to route next steps — Pick files and symbols from the index, then open only those regions (e.g. via read_source, symbol search, or the Read tool for edits). Avoid reading large unrelated areas when the index already answers “what lives where.”

  3. If the index looks stale — Timestamps and counts appear at the top of INDEX.md. After substantial code changes, the maintainer may regenerate it (see project guidance such as regenerate_index / indexer docs in-repo). If sections clearly mismatch the tree on disk, say so briefly and fall back to directory listing plus targeted reads.

Relationship to other tooling

Project rules may require indxr MCP tools for surgical queries. INDEX.md is the offline, whole-repo structural digest; MCP tools are ideal for precise symbol lookup and line-scoped reads. Use both: index for orientation and breadth, MCP (or direct reads) for depth on chosen symbols.

Examples

User: “Where is Rust query logic for TypeScript?”

  1. Open .cursor/INDEX.md, find the directory tree and declaration sections for src/parser/queries/.
  2. Note typescript.rs (and related modules), then read only those files or the relevant symbols.

User: “What does the MCP server expose?”

  1. Scan INDEX.md for mcp, src/mcp.rs, and linked declarations.
  2. Drill into the named functions/types from there.
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. 2d ago First seen · 35 lines · 67 tokens per session scan A e74864b5b602

Subscribe to this mod's changes

explore-codebase-index is a skill published in the GitHub repository bahdotsh/indxr (72 stars, last pushed 4mo ago), licensed MIT. It adds 67 tokens to every session and 477 once invoked, about $0.0003 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

skill-creator

Create, install, or update skills in the workspace. Use when (1) installing a skill from a URL or remote source, (2) creating a new skill from scratch, (3) updating or restructuring existing skills. Always use this skill for any skill installation or creation task.

zhayujie/CowAgent · 61 tokens

langbot-space-ops

Browse and search the LangBot Space marketplaces (plugins, MCP servers, skills) through the Space MCP server. Use when an AI agent needs to discover LangBot extensions on space.langbot.app over MCP. Covers the /mcp endpoint, Personal Access Token (PAT) auth, the tool surface, and client configuration. Triggers on…

langbot-app/LangBot · 101 tokens

ocx

Drive a running opencodex (ocx) proxy from the CLI — account pools, provider routing, model catalog, usage and cost attribution, request logs, access keys, storage cleanup, and the management API. Use when a task involves controlling or inspecting an opencodex proxy rather than editing the opencodex codebase.…

lidge-jun/opencodex · 0 tokens

openai-knowledge

Use when working with the OpenAI API (Responses API) or OpenAI platform features (tools, streaming, Realtime API, auth, models, rate limits, MCP) and you need authoritative, up-to-date documentation (schemas, examples, limits, edge cases). Prefer the OpenAI Developer Documentation MCP server tools when available…

openai/openai-agents-python · 83 tokens

opik-external-integrations

Build or update an Opik integration that lives OUTSIDE this repo — a standalone opik- package (e.g. opik-openclaw, opik-claude-code-plugin) or Opik support contributed into a third-party project (e.g. LiteLLM, Dify). Use ONLY when the user names an external repository or external package as the target; for…

comet-ml/opik · 97 tokens

create-atomic-tool

Build a BaseTool[InSchema, OutSchema] subclass — input/output schemas, BaseToolConfig, run() (and optional runasync()), env-driven secrets, typed failure outputs. Use when the user asks to "add a tool", "create a tool", "wrap an API as a tool", "build a BaseTool", "make a calculator/search/weather tool", or runs…

Eigenwise/atomic-agents · 99 tokens