workrail AGENTS.md

workrail AGENTS.md is an instructions file for Codex, OpenCode from EtienneBBeaulac/workrail. It costs 7,331 tokens per session, scanned D, original, MIT.

Repository instructions for WorkRail, a workflow system whose MCP server, autonomous WorkTrain daemon, and read-only console share an engine and session store. They explain these systems separately and describe how the v1 and v2 parts work.

In plain words
What is it for?
Use them when developing or debugging the WorkRail MCP server, WorkTrain daemon, WorkTrain console, durable engine, session storage, or workflow registry.
Why use it?
They prevent changes to one WorkRail component from being based on assumptions about another component’s role or architecture.

Instructions file for CodexOpenCode

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

Made for: Codex, OpenCode.

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 workrail AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/etiennebbeaulac/workrail/agents-md.svg)](https://agentmods.dev/instructions/etiennebbeaulac/workrail/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/etiennebbeaulac/workrail/agents-md"><img src="https://agentmods.dev/badge/instructions/etiennebbeaulac/workrail/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 7,331 This file is loaded in full into every session.
When invoked 7,331 The same file — it is already loaded in full.
Security scan D 2 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 $0.07331 $0.07331
Opus 5 $0.03666 $0.03666
Sonnet 5 $0.01466 $0.01466
Haiku 4.5 $0.00733 $0.00733

Measured 4d ago against content hash 60d715891065, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade D, and why

workrail AGENTS.md scanned grade D with 2 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

**Config note:** The project `.mcp.json` `workrail` entry should shadow the global `~/.claude/settings.json` entry when Claude Code is started from this repo. Verify via `/mcp` on first use -- if two `workrail` entries a

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

rm -rf ~/.workrail/dev
AGENTS.md · 498 lines

How it starts

The opening of the file, as written. The whole thing — 498 lines — stays where its author put it; the contents beside it link to each section on GitHub.

WorkRail -- Agent Instructions

CRITICAL: Three separate systems -- do not conflate them

WorkRail/WorkTrain is three distinct systems that share a common engine and session store. Understanding this separation is essential before working on any part of this codebase. Confusing them leads to wrong fixes, wrong architecture decisions, and real production problems.

┌─────────────────────────────────────────────────────────────────┐
│  Shared: WorkRail engine (src/v2/durable-core/) + session store │
│          ~/.workrail/data/sessions/  + workflow registry        │
└──────────────┬──────────────────┬───────────────────────────────┘
               │                  │                    │
   ┌───────────▼───────┐  ┌───────▼────────┐  ┌───────▼──────────┐
   │  WorkRail MCP     │  │ WorkTrain       │  │ WorkTrain        │
   │  Server           │  │ Daemon          │  │ Console          │
   │  workrail start   │  │ worktrain daemon │  │ worktrain console│
   │  (stdio → Claude) │  │ (autonomous     │  │ (read-only HTTP  │
   │                   │  │  agent loop)    │  │  session viewer) │
   └───────────────────┘  └─────────────────┘  └──────────────────┘

WorkRail MCP Server (workrail start)

  • A standalone stdio MCP server that Claude Code (and other MCP clients) connect to
  • Provides start_workflow, complete_step, continue_workflow, list_workflows etc. as MCP tools
  • Must be bulletproof -- crashes here kill all in-flight Claude Code sessions that depend on it
  • Has NOTHING to do with the daemon's internal machinery
  • Source: src/mcp/

WorkTrain Daemon (worktrain daemon)

  • An autonomous agent runner that drives workflow sessions without human involvement
  • Listens for triggers (webhooks, polling), spawns LLM agent loops, uses complete_step in-process
  • Completely separate process from the MCP server
  • Does NOT depend on the MCP server being alive -- it calls the WorkRail engine directly in-process
  • Source: src/daemon/, src/trigger/

Read the full file on GitHub · 498 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. 4d ago First seen · 498 lines · 7,331 tokens per session scan D 60d715891065

Subscribe to this mod's changes

workrail AGENTS.md is an instructions file published in the GitHub repository EtienneBBeaulac/workrail (4 stars, last pushed yesterday), licensed MIT. It adds 7,331 tokens to every session, about $0.0367 per session on Opus 5. A static security scan graded it D with 2 findings (reads agent configuration directories, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.