dev-workflow

A set of rules for how an AI coding agent handles feature requests and user stories. It uses a lean and Agile workflow, breaking work into tasks, tracking progress, and applying test-driven development when suitable.

In plain words
What is it for?
Use it to turn user stories into ordered tasks, define tests and edge cases, fix code errors, and report progress. It can guide work in JavaScript, TypeScript, JSX, TSX, and Markdown files.
Why use it?
It keeps implementation work organized and visible, so large requests are less likely to be missed or left half-done. It also sets limits on simultaneous work and defines what to do when checks or commits fail.

Skill for Claude CodeCodexCursor

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 skills/usrrname/cursorrules/dev-workflow
Any agent
npx skills add usrrname/cursorrules --skill dev-workflow
Clone the repo
git clone --depth 1 https://github.com/usrrname/cursorrules

Made for: Claude Code, Codex, Cursor.

Per session 30 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,435 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00030 $0.01435
Opus 5 $0.00015 $0.00718
Sonnet 5 $0.00006 $0.00287
Haiku 4.5 $0.00003 $0.00144

Measured yesterday against content hash 5ac706c27d20, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

dev-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 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/skills/dev-workflow/SKILL.md · 182 lines

How it starts

The opening of the file, as written. The whole thing — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Lean and Agile Development Workflow Standards

This rule defines the workflow for AI agents to follow when implementing features from user stories, focusing on lean development principles and agile methodologies.

Critical Rules

  • AI agents should read from the latest user story in .cursor/.ai/ that is not of "Done" or "Blocked" status.
  • No more than 2 stories or spikes can be in progress at any time.
  • Break down complex problems into a manageable task list and update the relevant user story or task with this list
  • Check off tasks one by one as they are completed
  • Assist with fixing errors in the code
  • Follow test-driven development when appropriate
  • Maintain continuous communication with the user about progress
  • If linting or committing fails, do not retry.

filters:

  • type: file_extension pattern: "\.(js|ts|jsx|tsx|md)$"
  • type: content pattern: "user story|feature request|backlog item"

actions:

  • type: suggest message: | Follow the lean-agile workflow pattern:
    1. Break down the user story into atomic tasks
    2. Prioritize tasks based on dependencies
    3. Based on user goals and acceptance criteria, create a list of test cases and edge cases with scenarios for testing the business-critical functionality. This must be approved by the user.
    4. Implement each task incrementally
    5. Write tests and ensure they pass before moving to the next task
    6. Refactor as needed
    7. Maintain communication with the user

metadata: priority: high version: 1.0

Workflow Process

1. User Story Analysis

When given a user story or feature request:

  • Mark the corresponding user story to Status: In Progress
  • Read and analyze the user story requirements
  • Break down the story into actionable tasks
  • Check if any existing components or utilities can be reused
  • Writing scenarios and expected outcomes.

Read the full file on GitHub · 182 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 · 182 lines · 30 tokens per session scan A 5ac706c27d20

Subscribe to this mod's changes

dev-workflow is a skill published in the GitHub repository usrrname/cursorrules (10 stars, last pushed 4mo ago), licensed ISC. It adds 30 tokens to every session and 1,435 once invoked, about $0.0002 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.