code-index

A rule for exploring a codebase by tracing relevant symbols, execution paths, dependencies, and the parts affected by a change. When available, it uses a prebuilt code index; otherwise it falls back to normal file-search methods.

In plain words
What is it for?
Use it to trace a request through the code, find callers of a function, understand architecture, or estimate the impact of changing a symbol.
Why use it?
It helps answer how code works and what a change might affect without reading the entire project. It also provides a fallback when the index is missing or unusable.

Cursor rule for Cursor

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 rules/hoangp8/tokless/code-index
Clone the repo
git clone --depth 1 https://github.com/HoangP8/tokless

Made for: Cursor.

Per session 286 This file is loaded in full into every session.
When invoked 286 The same file — it is already loaded in full.
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 $0.00286 $0.00286
Opus 5 $0.00143 $0.00143
Sonnet 5 $0.00057 $0.00057
Haiku 4.5 $0.00029 $0.00029

Measured yesterday against content hash bd7fef358722, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

code-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 yesterday.

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/rules/code-index.mdc · 27 lines

What it actually says

Code Index (codegraph)

Prebuilt code index. codegraph_explore gives source, call path, and blast radius in one call.

.codegraph/ index exists?
├─ YES → Use CodeGraph FIRST.
│  ├─ Use for → how X works, flows, architecture, callers, blast radius, symbols.
│  ├─ Trust results — no re-read/re-grep. Stale banner? Read only listed files.
│  ├─ Result spilled? Grep the spill for needed symbol; never read whole spill.
│  └─ Configs/docs/.env/non-indexed → Use normal tools.
└─ NO  → `git ls-files | wc -l`.
   ├─ ≤5 files or no git → Use normal tools.
   └─ Otherwise → Run `tokless index` once.
      ├─ Ready → Use CodeGraph.
      └─ Fails/CLI missing → Use normal tools; do not retry.

Examples:

  • codegraph_explore("how does auth middleware validate a JWT")
  • codegraph_explore("flow from HTTP request to DB query")
  • codegraph_explore("OrderService.createOrder callers and blast radius")
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. yesterday First seen · 27 lines · 286 tokens per session scan A bd7fef358722

Subscribe to this mod's changes

code-index is a cursor rule published in the GitHub repository HoangP8/tokless (258 stars, last pushed yesterday), licensed MIT. It adds 286 tokens to every session, about $0.0014 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.