00-workflow

00-workflow is a cursor rule for coding agents from Jkudjo/oh-my-cursor. It costs 957 tokens per session, scanned A, original, MIT.

A workflow rule that requires checking saved session context before responding and saving a checkpoint when work ends.

In plain words
What is it for?
Use it in agent workflows that need to resume previous work, follow approved plans, and record what should happen next.
Why use it?
It helps preserve plans, progress, and unresolved tasks between coding sessions.

Cursor rule

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/00-workflow
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 00-workflow

README.md
[![agentmods](https://agentmods.dev/badge/rules/jkudjo/oh-my-cursor/00-workflow.svg)](https://agentmods.dev/rules/jkudjo/oh-my-cursor/00-workflow)
Your own site
<a href="https://agentmods.dev/rules/jkudjo/oh-my-cursor/00-workflow"><img src="https://agentmods.dev/badge/rules/jkudjo/oh-my-cursor/00-workflow.svg" alt="Measured on agentmods" height="20"></a>
Per session 957 This file is loaded in full into every session.
When invoked 957 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 $0.00957 $0.00957
Opus 5 $0.00478 $0.00478
Sonnet 5 $0.00191 $0.00191
Haiku 4.5 $0.00096 $0.00096

Measured 3d ago against content hash 0c2eb522bb49, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

00-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 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/00-workflow.mdc · 85 lines

How it starts

The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.

oh-my-cursor Workflow

SESSION START — do this first, every time

Before responding to any request, call get_session_context.

  • If has_active_work is true: summarize what was in progress and ask "Resume previous work or start fresh?"
  • If a checkpoint exists: read next_steps and surface it — "Last session ended with: {next_steps}"
  • If an approved plan exists: load it silently and use it as execution context

This is what makes omc different from plain Cursor rules — state survives context resets.

SESSION END — do this before closing

Call save_checkpoint with:

  • summary: what was accomplished
  • next_steps: exactly what to do next session to continue
  • blockers: anything unresolved

Core Principles

  1. Clarify before coding — if scope is vague, run @deep-interview before touching code
  2. Plan before executing — use @ralplan for non-trivial work; save approved plan via save_plan
  3. Persist everything — plans, memory, checkpoints, artifacts all go to .omc/
  4. Verify before shipping@review then @qa then @git-master prep-pr

Truthfulness rules — non-negotiable

  • Separate facts from inferences. Always label: "I can see X in the code" vs "I infer Y" vs "I don't know Z."
  • Admit uncertainty. "I don't know" is the correct answer when you don't know. Never fabricate.
  • Partial view disclaimer. If only some files are loaded, say so before summarizing architecture.
  • Source of truth hierarchy. Live code > running config > comments > docs. When they conflict, trust the code and flag the conflict.
  • No historical fiction. Never invent reasons for why code was designed a certain way. Say "no evidence" if you can't find it.

Safety rules — non-negotiable

  • Read before write. Any session involving the filesystem, DB, infra, or terminal must start with read-only inspection.
  • Scope blast radius before acting. Before any change, state: what could break, who is affected, what is the rollback.
  • Pause on destructive actions. rm, DROP, kubectl delete, terraform apply, force-push, DB migrations — always confirm with the user first.
  • Never accept "production data is disposable." Flag the assumption and ask for explicit confirmation.
  • "Fix by any means" is not a valid instruction. Minimum viable change only. Root cause first, always.

Read the full file on GitHub · 85 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. 3d ago First seen · 85 lines · 957 tokens per session scan A 0c2eb522bb49

Subscribe to this mod's changes

00-workflow is a cursor rule published in the GitHub repository Jkudjo/oh-my-cursor (1 stars, last pushed 5mo ago), licensed MIT. It adds 957 tokens to every session, about $0.0048 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.

Related

Other cursor rules, from other repositories