Skip to content
runward
runward
Product
Who it is for
Trust
Documentation
News
Try it on an example Talk to us

Get started

Install the check in your repository.

One command creates the team’s record next to the code. Another reads it again at every delivery, and says what is missing.

  1. 01Install
  2. 02Run the check
  3. 03Wire it into your delivery chain

To see it first

Try it on an example

In an empty folder, with git initialised:

Terminal
npx --yes runward@0.47.0 init --example

The command writes a complete example and runs the check: everything is green. Then rename the function it points to, run the tests (in code/, after npm install) and then the check: the tests pass, the check refuses and names the two lines of the record that cite it. The scene, on a public repository, shows the same gesture.

Before you start

What you need

  • Node.js 22.12 or later, and git.
  • The repository of an application.
  • If you ship with a coding agent: the command creates its instructions, in an AGENTS.md file.

Step 1

Install

At the root of your repository:

Terminal
npx --yes runward@0.47.0 init

The command asks a few questions, then creates an AGENTS.md file, a runward/ folder and an .agents/skills/ folder for your agents. It overwrites no existing file. The runward/ folder is the team’s record: the team sets in it what it requires before production, and its agents draft most of it, with what proves it.

The main filesWhat it holds
runward/framing.mdThe problem, the expected value, the success criterion.
runward/architecture.mdThe system’s boundaries.
runward/adr/The structural decisions, written and dated.
runward/floor.mdThe first-version measurements.
runward/governance/threat-model.mdThe security assessment.
runward/runbook.mdThe recovery procedure.
runward/handover.mdThe handover note.
AGENTS.mdThe team’s instructions for your coding agents.

The six steps, and what the record holds at each

Step 2

Run the check

Terminal
npx runward check

The check says which document of the record is missing or not filled in. It exits with code 1 while a gap remains, and with code 0 when nothing is blocking.

Terminal
npx runward check --strict

With --strict, it also verifies that each piece of evidence cited in the record still exists: a file, a test, a written decision. When it refuses, it names the file and the line.

Step 3

Wire it into your delivery chain

Add the same command to your delivery chain, with the version you chose:

Delivery chain
npx --yes runward@0.47.0 check --strict

It fails while a gap remains. You decide whether that failure blocks the release to production.

The wiring, in the documentation

With a coding agent

Your agents read the same record.

Codex, Cursor, Copilot and the other tools that read AGENTS.md find the team’s instructions there. Claude Code reads it too when the repository has no CLAUDE.md. For Gemini CLI, add its profile: npx runward init --tools gemini. Ask your agents to run runward check before they say they are done: the check answers them as it answers you.

Using runward from an agent, in the documentation

Without installing anything in your repository

First see a refusal, on a public repository.

This command runs the check again on the commit of the scene of the home page. It refuses, and says which lines.

Terminal
git clone https://github.com/stranxik/runward-demo-renaming && git -C runward-demo-renaming checkout 97fce96d901d0d07cad8a230950d391b223736af && npx --yes runward@0.47.0 check --strict --path runward-demo-renaming

Check it yourself

Try it on an example, in one command.

Try it on an example

Talk to us

Tell us who you are, and we will get back to you.

Your details are recorded by Another Framework, publisher of runward, to get back to you. They are neither sold nor shared, and are deleted three years after our last exchange. To see or delete them: contact@runward.dev.