cursorrules

A set of rules for recording coding-agent conversations in VibeTrace, a VS Code extension that shows a timeline of a project's agent-assisted work. Each substantive response or code change must produce a metadata record.

In plain words
What is it for?
Use it to create session identifiers, choose the correct module from .vibe/MODULE_DICT.md, and record metadata after substantive answers or code changes.
Why use it?
It preserves a searchable history of what happened during agent sessions and groups each turn under a consistent session and project module. The rules also require checking the project's module dictionary before classifying work.

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/zpeakj/vibe-trace/cursorrules
Clone the repo
git clone --depth 1 https://github.com/zpeakj/vibe-trace

Made for: Cursor.

Per session 1,197 This file is loaded in full into every session.
When invoked 1,197 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 $0.01197 $0.01197
Opus 5 $0.00598 $0.00598
Sonnet 5 $0.00239 $0.00239
Haiku 4.5 $0.00120 $0.00120

Measured yesterday against content hash bc813adf7218, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cursorrules 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.

.cursorrules · 112 lines

How it starts

The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.

VibeTrace — Automatic Conversation Recording xxxxxx、

You are an agent in a VibeTrace-enabled project. At the end of every response where you made code changes or provided a substantive answer, you MUST generate a metadata record of this conversation turn.

This metadata powers the VibeTrace VS Code extension, which gives the user a visual timeline of their entire project's vibe-coding journey.


1. Determine Session ID

The session_id identifies which agent window this conversation belongs to. It should be human-readable so the user can recognize it in the VibeTrace sidebar.

  • First turn in this window: Create a session_id from the user's first request — a short CamelCase topic + 3 random lowercase letters. Example: user asks "add login page" → LoginPage-k7m.
  • Subsequent turns: Reuse the session_id from earlier in this conversation. Do not change it.

2. Determine Module

The module field classifies which business feature this turn belongs to.

  • BEFORE assigning a module, you MUST read the file .vibe/MODULE_DICT.md using the Read File tool.
  • If the current work matches an existing module in the dictionary, use that EXACT name (case-sensitive).
  • If NO existing module matches, you may create a new one.
    • New module names should be short CamelCase (e.g., UserProfile, PaymentGateway, DashboardUI).
    • Do NOT create variants of existing modules (e.g., if Auth exists, do NOT create Authentication or auth).

3. Generate the Metadata JSON

After completing the user's request, create a JSON file with the following structure:

{
  "id": "<YYYYMMDD>-<session_id>-<3randomchars>",
  "session_id": "<ShortTopic>-<3chars>, e.g. WechatQrLogin-a3f",
  "module": "<your determined module name>",

  "original_prompt": "<the user's raw prompt, copied verbatim>",
  "intent": "<1-sentence condensation of what the USER asked for>",
  "summary": "<1-sentence summary of what YOU did to fulfill it>",

  "impactFiles": [
    {
      "path": "relative/path/to/file.ts",
      "action": "create | modify | delete | read",
      "description": "<one-line description of what changed and why>"
    }
  ],

  "unresolved_issues": "<optional — things left undone, config needed, follow-up required>"
}

Read the full file on GitHub · 112 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. yesterday First seen · 112 lines · 1,197 tokens per session scan A bc813adf7218

Subscribe to this mod's changes

cursorrules is a cursor rule published in the GitHub repository zpeakj/vibe-trace (5 stars, last pushed 3mo ago), licensed MIT. It adds 1,197 tokens to every session, about $0.0060 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.