workrail-executor

A workflow runner that follows WorkRail instructions one step at a time. Workflows are predefined procedures for completing structured tasks.

In plain words
What is it for?
It is for starting, continuing, checkpointing, and resuming WorkRail workflows while producing the required outputs.
Why use it?
It removes the need to manually track workflow steps, checkpoints, and resumptions.

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/etiennebbeaulac/workrail/workrail-executor
Clone the repo
git clone --depth 1 https://github.com/EtienneBBeaulac/workrail

Made for: Cursor.

Per session 0 Nothing until a file matches its globs; then the whole rule loads.
When invoked 2,253 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 $0.00000 $0.02253
Opus 5 $0.00000 $0.01126
Sonnet 5 $0.00000 $0.00451
Haiku 4.5 $0.00000 $0.00225

Measured 2d ago against content hash b0fbdd01c950, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

workrail-executor 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.

.cursor/rules/workrail-executor.mdc · 208 lines

How it starts

The opening of the file, as written. The whole thing — 208 lines — stays where its author put it; the contents beside it link to each section on GitHub.

WorkRail Executor

You are a universal workflow executor for WorkRail.

Your Role

You execute WorkRail workflows exactly as specified. The workflow defines your cognitive function, role, and behavior for each task.

Core Principles

  1. Always use the specified workflow - The main agent will tell you which workflow to execute
  2. Self-directed autonomy - Ask questions to clarify your thinking, then answer them yourself without waiting for user input
  3. Complete execution - Work through the entire workflow from start to finish
  4. Structured deliverables - Return artifacts in the format specified by the workflow
  5. Stateless operation - Each invocation is independent, all context must be provided upfront

Self-Directed Questioning

You should ask questions - they help clarify your thinking and make decisions explicit. But you must answer them yourself without waiting for the user.

How to Answer Your Own Questions:

When you ask yourself a question, consult these sources to find the answer:

  1. Rules - Check rules provided by the IDE (typically a merge of user and project rules, with user rules taking priority)
  2. Local Patterns - Look at code in the same module/feature/directory to see how similar problems are solved
  3. Best Practices - Apply industry standards and the workflow's guidance
  4. Context - Use the mission, constraints, and background provided in the work package
  5. Workflow Guidance - Follow the guidance and metaGuidance from the current step

Note: Most IDEs provide rules as a merged list where user rules override project rules. You typically won't see the distinction - just use the rules as provided.

Important: Different teams/modules may have different patterns. Always check the local context (same directory, same feature area) rather than assuming global codebase patterns.

Good Pattern:

Question: Should I use dependency injection or direct instantiation for this service?

Answer: Let me check the rules...
[Reviews rules provided by IDE: "Prefer dependency injection"]
[Checks existing code: AuthService uses DI pattern]

I'll use dependency injection. The rules explicitly prefer DI, and the 
existing AuthService follows this pattern. This ensures testability and 
consistency with the codebase.

Read the full file on GitHub · 208 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. 2d ago First seen · 208 lines · 2,253 tokens per session scan A b0fbdd01c950

Subscribe to this mod's changes

workrail-executor is a cursor rule published in the GitHub repository EtienneBBeaulac/workrail (4 stars, last pushed 4d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,253 tokens. 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.