workflow-level2

A six-phase workflow for Level 2 tasks, meaning small enhancements that need some planning but do not change the system’s architecture. The phases cover setup, documentation, planning, implementation, reflection, and archiving.

In plain words
What is it for?
Use it for contained feature additions or moderate changes affecting several parts of a codebase.
Why use it?
It provides a repeatable process and checkpoints for changes that are larger than a quick fix.

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/alkoleft/platform-context-exporter/workflow-level2
Clone the repo
git clone --depth 1 https://github.com/alkoleft/platform-context-exporter

Made for: Cursor.

Per session 2,131 This file is loaded in full into every session.
When invoked 2,131 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin 100% copy Near-identical to another mod 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 $0.02131 $0.02131
Opus 5 $0.01066 $0.01066
Sonnet 5 $0.00426 $0.00426
Haiku 4.5 $0.00213 $0.00213

Measured 2d ago against content hash d683e028f808, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

workflow-level2 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.

Origin

This is a copy

100% identical to workflow-level2 — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.cursor/rules/isolation_rules/Level2/workflow-level2.mdc · 289 lines

How it starts

The opening of the file, as written. The whole thing — 289 lines — stays where its author put it; the contents beside it link to each section on GitHub.


description: Basic workflow for Level 2 Simple Enhancement tasks globs: "/level2/", "/workflow/" alwaysApply: false

WORKFLOW FOR LEVEL 2 TASKS

TL;DR: This document outlines a structured yet efficient workflow for Level 2 (Simple Enhancement) tasks, including 6 key phases with milestone checkpoints and quality verification.

🔍 LEVEL 2 WORKFLOW OVERVIEW

graph LR
    Init["1. INITIALIZATION"] --> Doc["2. DOCUMENTATION<br>SETUP"]
    Doc --> Plan["3. TASK<br>PLANNING"]
    Plan --> Impl["4. IMPLEMENTATION"]
    Impl --> Reflect["5. REFLECTION"]
    Reflect --> Archive["6. ARCHIVING"]
    
    %% Document connections for each phase
    Init -.-> InitDocs["INITIALIZATION"]
    Doc -.-> DocDocs["DOCUMENTATION"]
    Plan -.-> PlanDocs["PLANNING"]
    Impl -.-> ImplDocs["IMPLEMENTATION"]
    Reflect -.-> ReflectDocs["REFLECTION"]
    Archive -.-> ArchiveDocs["ARCHIVING"]

Level 2 tasks involve simple enhancements that require a structured approach with moderate planning and documentation. This workflow provides the right balance of process and efficiency.

📋 WORKFLOW PHASES

Phase 1: INITIALIZATION

graph TD
    Start["Start Level 2 Task"] --> Platform{"Detect<br>Platform"}
    Platform --> FileCheck["Critical File<br>Verification"]
    FileCheck --> LoadStructure["Load Memory<br>Bank Structure"]
    LoadStructure --> TaskCreation["Create Task<br>in tasks.md"]
    TaskCreation --> SetupComplete["Initialization<br>Complete"]

Steps:

  1. Platform detection
  2. Critical file verification
  3. Memory Bank structure loading
  4. Task creation in tasks.md
  5. Initial task scope definition

Milestone Checkpoint:

✓ INITIALIZATION CHECKPOINT
- Platform detected and configured? [YES/NO]
- Critical files verified? [YES/NO]
- Memory Bank loaded? [YES/NO]
- Task created in tasks.md? [YES/NO]
- Initial scope defined? [YES/NO]

→ If all YES: Proceed to Documentation Setup
→ If any NO: Complete initialization steps

Read the full file on GitHub · 289 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. 2d ago First seen · 289 lines · 2,131 tokens per session scan A d683e028f808

Subscribe to this mod's changes

workflow-level2 is a cursor rule published in the GitHub repository alkoleft/platform-context-exporter (48 stars, last pushed 1y ago), licensed MIT. It adds 2,131 tokens to every session, about $0.0107 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to workflow-level2, differing in 0 lines, and is treated as a copy.