project-indexing

project-indexing is a cursor rule for Cursor from Garyzhu-hub/software-controlled-skills. It costs 0 tokens per session (3,244 once invoked), scanned A, original, MIT.

A project-analysis workflow that creates or updates compact files describing a codebase, its platforms, important files, commands, and safe editing areas.

In plain words
What is it for?
Use it to initialize, rebuild, refresh, or audit indexes for web, backend, mobile, desktop, testing, CI, and documentation projects.
Why use it?
It gives future coding agents a map of the repository instead of making them infer its structure from scratch.

Cursor rule for Cursor

Written for Cursor: installed under .cursor/. Also seen: mentions CLAUDE.md; mentions AGENTS.md.

Good fit Use it to initialize, rebuild, refresh, or audit indexes for web, backend, mobile, desktop, testing, CI, and documentation projects.

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/garyzhu-hub/software-controlled-skills/project-indexing
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.

Clone the repo
git clone --depth 1 https://github.com/Garyzhu-hub/software-controlled-skills

Made for: Cursor.

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 project-indexing

README.md
[![agentmods](https://agentmods.dev/badge/rules/garyzhu-hub/software-controlled-skills/project-indexing.svg)](https://agentmods.dev/rules/garyzhu-hub/software-controlled-skills/project-indexing)
Your own site
<a href="https://agentmods.dev/rules/garyzhu-hub/software-controlled-skills/project-indexing"><img src="https://agentmods.dev/badge/rules/garyzhu-hub/software-controlled-skills/project-indexing.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Nothing until a file matches its globs; then the whole rule loads.
When invoked 3,244 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 $0.00000 $0.03244
Opus 5 $0.00000 $0.01622
Sonnet 5 $0.00000 $0.00649
Haiku 4.5 $0.00000 $0.00324

Measured 8d ago against content hash 7c93bb24118a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

project-indexing 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 8d 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/rules/project-indexing.mdc · 620 lines

How it starts

The opening of the file, as written. The whole thing — 620 lines — stays where its author put it; the contents beside it link to each section on GitHub.


name: project-indexing description: Graph-aware multi-platform project indexing skill. Use this skill to initialize, rebuild, refresh, or audit AI-readable project indexes for web, backend, full-stack, iOS, Android, mini program, macOS, desktop, Electron, Tauri, Flutter, React Native, CI, test, and documentation projects.

Project Indexing Skill v2.2.0 — Graph-aware Project Indexing

1. Role

You are a graph-aware multi-platform repository indexing agent.

Your job is to analyze the current repository and create or update AI-readable project index files under:

docs/ai-index/

This skill is for indexing only. Do not implement product features, fix bugs, refactor code, add dependencies, change configuration, install tools, initialize optional code graph systems, or modify production behavior unless the user explicitly asks for that in a separate task.

2. Core Objective

Build compact, accurate, platform-aware indexes that help future coding agents understand:

  1. What kind of project this is.
  2. Which platforms are present.
  3. Where key source files live.
  4. Which commands validate the project.
  5. Which files are safe to modify for common tasks.
  6. Which files or areas are high-risk.
  7. Which specialized indexes should be read for future tasks.
  8. Which entry points, key symbols, dependency boundaries, critical flows, and affected tests are known or uncertain.
  9. Whether optional structured code intelligence is available, fresh, useful, incomplete, stale, or absent.

3. Supported Project Types

Detect one or more of the following project types:

web-frontend
server-backend
fullstack
api
database
auth-security
ios
android
miniprogram
macos
desktop
electron
tauri
flutter
react-native
cross-platform-mobile
cli
library-package
test
ci-build
docs

A repository may contain multiple project types.

4. Required Index Files

Always create or update:

docs/ai-index/PROJECT_INDEX.md
docs/ai-index/INDEX_CHANGELOG.md

Create platform-specific indexes only when relevant:

Read the full file on GitHub · 620 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. 8d ago First seen · 620 lines · 0 tokens per session scan A 7c93bb24118a

Subscribe to this mod's changes

project-indexing is a cursor rule published in the GitHub repository Garyzhu-hub/software-controlled-skills (4 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,244 tokens. 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 2026-08-31.