003-workflow

A set of development workflow rules for making small, traceable code changes. It covers commit messages, limiting change scope, managing context, separating environments, dependencies, and explaining rule-based decisions.

In plain words
What is it for?
Plan atomic changes, use conventional commits, keep development and production settings separate, review dependency additions, and document which rules shaped implementation choices.
Why use it?
It reduces accidental unrelated edits, unclear history, unsafe configuration changes, and unnecessary dependencies.

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/obviousworks/vibe-coding-ai-rules/003-workflow
Clone the repo
git clone --depth 1 https://github.com/obviousworks/vibe-coding-ai-rules

Made for: Cursor.

Per session 292 This file is loaded in full into every session.
When invoked 292 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 $0.00292 $0.00292
Opus 5 $0.00146 $0.00146
Sonnet 5 $0.00058 $0.00058
Haiku 4.5 $0.00029 $0.00029

Measured 2d ago against content hash 225518a97267, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

003-workflow 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.

ide-specific/cursor/.cursor/rules/003-workflow.mdc · 48 lines

What it actually says

Workflow Standards

Atomic Changes (AC)

Make small, self-contained modifications for traceability and rollback.

Commit Discipline (CD)

Use conventional commit format: type(scope): description Types: feat, fix, docs, style, refactor, test, chore

Change Scope Discipline (CSD)

Only modify files directly related to the current task. Never make unrelated "improvements" without explicit permission.

Context Window Management (CWM)

  • Be mindful of AI context limitations
  • Keep files focused and modular
  • Use file-scoped commands for individual changes
  • Only run project-wide commands when explicitly requested

Environment Awareness

  • Never modify production environment configurations
  • Maintain separate configs for DEV, TEST, PROD
  • Never hardcode environment-specific values

Transparent Reasoning (TR)

When generating code, explicitly reference which rules influenced decisions.

Dependency Governance

Never add new dependencies without explicit approval or compelling justification.

Token Efficiency

Use file-scoped commands. Reference docs instead of pasting. Optimize context window usage.

Industry Standards

Follow established conventions for the relevant language and tech stack.

Strategic Documentation

Comment only complex logic or critical functions. Avoid documenting the obvious.

Self-Review Before Commit

After generating code, argue against your own solution. Check for redundancy, unnecessary complexity, or simpler alternatives.

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 · 48 lines · 292 tokens per session scan A 225518a97267

Subscribe to this mod's changes

003-workflow is a cursor rule published in the GitHub repository obviousworks/vibe-coding-ai-rules (88 stars, last pushed 2mo ago), licensed MIT. It adds 292 tokens to every session, about $0.0015 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.