01-omnidev-workflow

01-omnidev-workflow is a cursor rule for Cursor from zayeagle/omnidev-kit. It costs 601 tokens per session, scanned A, original, MIT.

A trigger rule that controls when the OmniDev development workflow starts in Cursor.

In plain words
What is it for?
It recognizes approved commands such as /od or $od, resumes or advances the workflow, handles numbered choices when a pending decision exists, and explains how to activate it when needed.
Why use it?
It prevents ordinary messages, bare numbers, or an attached reference from accidentally starting the workflow.

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/zayeagle/omnidev-kit/01-omnidev-workflow
Clone the repo
git clone --depth 1 https://github.com/zayeagle/omnidev-kit

Made for: 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 01-omnidev-workflow

README.md
[![agentmods](https://agentmods.dev/badge/rules/zayeagle/omnidev-kit/01-omnidev-workflow.svg)](https://agentmods.dev/rules/zayeagle/omnidev-kit/01-omnidev-workflow)
Your own site
<a href="https://agentmods.dev/rules/zayeagle/omnidev-kit/01-omnidev-workflow"><img src="https://agentmods.dev/badge/rules/zayeagle/omnidev-kit/01-omnidev-workflow.svg" alt="Measured on agentmods" height="20"></a>
Per session 601 This file is loaded in full into every session.
When invoked 601 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 $0.00601 $0.00601
Opus 5 $0.00300 $0.00300
Sonnet 5 $0.00120 $0.00120
Haiku 4.5 $0.00060 $0.00060

Measured 4d ago against content hash 8c56037ebdeb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

01-omnidev-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 4d 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.

.cursor/rules/01-omnidev-workflow.mdc · 41 lines

What it actually says

OmniDev Trigger Gate (Cursor)

→ Spec: .cursor/skills/od/engine/trigger-gate.md

ACTIVATE

  1. Signal A: Message starts with /od (or $od) — includes /od 1/od 9 index pick
  2. Signal A-index: Whole message is bare 19 and session-log has matching pending_decision
  3. Not a trigger: @od skill attach without /od — reference only, do not Phase 0

On activate: Read SKILL.md → engine/activation.md §0–§6 (A-index → §0.1 only). Tool calls first.

DO NOT ACTIVATE

  • Normal chat without /od/$od / valid bare index
  • Mid-sentence mentions of /od … (must be line-start)
  • Bare n / ad / continue / yNOT workflow input
  • Bare 19 without disk pending_decision
  • Do NOT infer OmniDev from prior chat turns alone

If bare n/ad/re/continue or digit-without-pending looks like workflow intent, reply one line only: ⚠️ OmniDev is not active. Use /od 1 (row index), /od n, or /od re.

Advance workflow

Action Command
Resume /od re
Next phase /od n
Index pick /od 1/od 9 or bare 19 (with pending)
Full autopilot /od auto / /od al
Revise /od ad
End session /od x

Phase end: print Handoff (next phase + what to do + /od n + skip /od sk N or "not allowed") then must call AskQuestion when tool exists → UI pick or /od N / bare N / Send command. Autopilot soft-gates skip STOP; hard gates STOP then resume after confirm (board.md §2.5). If tool absent → §8 Markdown table + write pending_decision (forbid box-drawing frames). STOP & WAIT only when actually waiting. Phase 0 chat: ≤6 lines + Full auto: /od auto hint; details → session-log.

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. 4d ago First seen · 41 lines · 601 tokens per session scan A 8c56037ebdeb

Subscribe to this mod's changes

01-omnidev-workflow is a cursor rule published in the GitHub repository zayeagle/omnidev-kit (5 stars, last pushed 2d ago), licensed MIT. It adds 601 tokens to every session, about $0.0030 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.