A set of code-search and change-safety rules for a repository with an indexed map of its code.

Finding code concepts, inspecting symbols and callers, checking change impact, and refreshing the code index when it is out of date.

It tells coding agents which commands to use before changing code and helps them inspect related symbols and possible effects.

code-intel — Cursor rule by vohongtho

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/vohongtho/code-intel-platform/code-intel

Clone the repo

git clone --depth 1 https://github.com/vohongtho/code-intel-platform

Made for: Cursor.

Per session 2,647 This file is loaded in full into every session.

When invoked 2,647 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.

Model	Per session	Once invoked
Fable 5	$0.02647	$0.02647
Opus 5	$0.01324	$0.01324
Sonnet 5	$0.00529	$0.00529
Haiku 4.5	$0.00265	$0.00265

Measured yesterday against content hash d95092eba184, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

code-intel 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-intel.mdc · 183 lines

How it starts

The opening of the file, as written. The whole thing — 183 lines — stays where its author put it; the contents beside it link to each section on GitHub.

code-intel.mdc

Code Intelligence — code-intel-platform

⚠ This section is auto-managed by code-intel analyze. Do not edit between the markers — your changes will be overwritten. Add your own notes below the  marker.

FORBIDDEN: grep, rg, find, cat, sed, ls (for symbol/code discovery) REQUIRED BEFORE ANY CODE ACTION:

code-intel search "" ← replaces grep/rg/find
code-intel inspect ← replaces cat + manual file reading
code-intel impact ← replaces manual caller tracing

Indexed: 6,254 nodes | 11,376 edges | 333 files | analyzed in 1.8s

Index stale? Re-run: code-intel analyze

Mandatory Rules — ALL Agents (Amp, Claude Code, Codex, Copilot, Cursor, Aider, Gemini, Kiro, Trae, Hermes, Factory, OpenCode, Pi, Antigravity, OpenClaw, and others)

These rules apply to every coding agent or AI assistant working in this repository.

Before Implementing Any Change

Run code-intel search "<concept>" — find existing symbols related to the task.
Run code-intel inspect <symbol> — understand callers, callees, and imports.
Run code-intel impact <symbol> — check blast radius before touching anything.
If impact shows ≥ 5 direct callers → warn the user: HIGH risk.

While Implementing / Fixing a Bug

NEVER open a file cold — always code-intel search first.
NEVER grep for symbols — use code-intel search instead.
NEVER rename symbols with find-and-replace — use code-intel inspect to find all usages first.
Use code-intel inspect <symbol> to understand a function's callers/callees before modifying it.
Use code-intel query "TRAVERSE CALLS FROM '<symbol>' DEPTH 3" to trace execution paths.

Before Committing / Code Review

Run code-intel impact <symbol> for every symbol you changed.
Run code-intel pr-impact --base main --head HEAD to see full PR blast radius.
Fail PR if HIGH risk symbols are changed without reviewer sign-off.

Read the full file on GitHub · 183 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.

yesterday First seen · 183 lines · 2,647 tokens per session scan A d95092eba184

Subscribe to this mod's changes

code-intel is a cursor rule published in the GitHub repository vohongtho/code-intel-platform (3 stars, last pushed 5d ago), licensed MIT. It adds 2,647 tokens to every session, about $0.0132 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 2026-08-31.

Research

code-intel

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

code-intel.mdc

Code Intelligence — code-intel-platform

Mandatory Rules — ALL Agents (Amp, Claude Code, Codex, Copilot, Cursor, Aider, Gemini, Kiro, Trae, Hermes, Factory, OpenCode, Pi, Antigravity, OpenClaw, and others)

Before Implementing Any Change

While Implementing / Fixing a Bug

Before Committing / Code Review

What this file has done since we first saw it

Other cursor rules, from other repositories

angular-20

dev-standard

typescript

coolify-ai-docs

python_lib

specs