agentmods.dev

ultrawork

ultrawork is a cursor rule for coding agents from Jkudjo/oh-my-cursor. It costs 13 tokens per session (522 once invoked), scanned A, original, MIT.

A rule for running a complete software workflow: explore the code, clarify the task, plan it, implement it, review it, test it, check security, and prepare it for shipping.

In plain words
What is it for?
Use it for substantial changes that need broad investigation, planning, tests, code review, security checks, quality checks, and release preparation.
Why use it?
It coordinates many separate checks so a task is not treated as finished after coding alone. The workflow requires review and verification before shipping.

Cursor rule

not rated 1 5mo ago A scan 13 tokens original MIT
View the source file Jkudjo/oh-my-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/jkudjo/oh-my-cursor/ultrawork
Clone the repo
git clone --depth 1 https://github.com/Jkudjo/oh-my-cursor

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for ultrawork

README.md
[![agentmods](https://agentmods.dev/badge/rules/jkudjo/oh-my-cursor/ultrawork.svg)](https://agentmods.dev/rules/jkudjo/oh-my-cursor/ultrawork)
Your own site
<a href="https://agentmods.dev/rules/jkudjo/oh-my-cursor/ultrawork"><img src="https://agentmods.dev/badge/rules/jkudjo/oh-my-cursor/ultrawork.svg" alt="Measured on agentmods" height="20"></a>
Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 522 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 $0.00013 $0.00522
Opus 5 $0.00006 $0.00261
Sonnet 5 $0.00003 $0.00104
Haiku 4.5 $0.00001 $0.00052

Measured 3d ago against content hash 4b69f121be7e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ultrawork 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 3d 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.

rules/ultrawork.mdc · 54 lines

What it actually says

@ultrawork

Trigger: When you want the complete workflow executed at maximum rigor with no shortcuts.

This is @explore + @deep-interview + @ralplan + @tdd/@ralph + @review + @security-review + @qa + @pipeline + @git-master prep-pr run as a single coordinated sequence.

Protocol

  1. Call start_mode mode=autopilot task=ultrawork: {task}.
  2. Call save_checkpoint at the start so you can resume if interrupted.

Phase 1 — Understand (explore + deep-interview)

  1. Run @explore to map the relevant subsystem.
  2. Score ambiguity. If > 0.3: run @deep-interview --standard.
  3. Save clarified scope to memory.

Phase 2 — Plan (ralplan)

  1. Run @ralplan. Generate plan, present for approval.
  2. On approval: save_plan approved=true.

Phase 3 — Execute (tdd or ralph)

  1. If building new functionality: use @tdd (tests first).
  2. If modifying existing code: use @ralph.
  3. Call update_mode_state after each step.

Phase 4 — Verify (review + security + qa + pipeline)

  1. @review — full code review, PASS required to continue.
  2. @security-review — zero CRITICAL required to continue.
  3. @qa --full — all checks pass.
  4. @pipeline — full CI gate.

Phase 5 — Ship (git-master)

  1. @git-master clean-commit — conventional commit.
  2. @git-master prep-pr — full PR description.
  3. Call save_checkpoint with final summary.

Abort conditions

  • @review returns FAIL → fix issues before continuing (do not skip)
  • @security-review returns CRITICAL → fix before continuing (hard stop)
  • @pipeline FAIL after 2 cycles → surface to user, do not force-ship

Rules

  • No shortcuts. Every phase runs.
  • Each phase must pass before the next starts.
  • save_checkpoint after each phase so ultrawork is resumable.
  • This mode is slow by design — use it when quality matters most.
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. 3d ago First seen · 54 lines · 13 tokens per session scan A 4b69f121be7e

Subscribe to this mod's changes

ultrawork is a cursor rule published in the GitHub repository Jkudjo/oh-my-cursor (1 stars, last pushed 5mo ago), licensed MIT. It adds 13 tokens to every session and 522 once invoked, about $0.0001 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.

agentai-workflowcodexcursorcursor-aicursor-rules
Related

Other cursor rules, from other repositories

code-optimization

Guidelines for optimizing duplicate and poorly structured code.

leshchenko1979/fast-mcp-telegram · 0 tokens

memory-bank

You are an expert software engineer with a unique characteristic: your memory resets completely between sessions. This isn't a limitation - it's what drives you to maintain perfect documentation. At the beginning of each dialogue, you rely ENTIRELY on your Memory Bank to understand the project and continue work…

leshchenko1979/fast-mcp-telegram · 1,623 tokens

general

You are running in Cursor IDE. The tools of the MCP server that you are developing are connected to this IDE. When you've modified the code and want to use updated functionality, you must prompt the user to reload the server first.

leshchenko1979/fast-mcp-telegram · 228 tokens

create-rule-agent

This rule is responsible for creating and updating Cursor rules. Cursor rules govern the structure, hierarchy, style and organization of code in a project. This rule should be invoked in Agent mode when: 1. a user wants to create a new cursor rule, 2. a user wants to update or change an existing rule, 3. user wants…

usrrname/cursorrules · 3,429 tokens

cloudflare-workers-hono-auto

Cloudflare Workers with Hono framework development standards and best practices.

usrrname/cursorrules · 0 tokens

cloudflare-workers-auto

Cloudflare Workers development standards and best practices.

usrrname/cursorrules · 0 tokens