Make your coding agent show evidence before it says done
vstack is a small workflow for Claude Code and Codex based on pstack: the agent follows a state machine and must provide evidence before it can claim a task is done.
Source
@valentinoswe on X · 2026-10-17
Written in our own words. Credit to the original author. Link checked 2026-10-18.
What they did
vstack is a small workflow for Claude Code and Codex based on pstack: the agent follows a state machine and must provide evidence before it can claim a task is done.
Result (as claimed)
Open source on GitHub.
Tools they used
Cost: Claude Code: from $17/mo; OpenAI Codex: free plan, paid from $8/mo.
Set it up
Pick a contained repo or task
Start on a branch or side project where mistakes are cheap.
Install and configure
Set up Claude Code, OpenAI Codex. Read what it can run on your machine and limit permissions where possible.
Run it on a real task
Give it a well-scoped issue and let it work. Review the diff like any pull request.
Add guardrails
Keep tests and CI in the loop, and never let an agent push to main or touch production secrets unattended.
Copy the full setup prompt
Paste into your agent and it will walk you through the setup, asking before anything that sends, posts or spends.
You are helping me set up this AI use case end to end in Claude Code. Goal: Make your coding agent show evidence before it says done What the original author did: vstack is a small workflow for Claude Code and Codex based on pstack: the agent follows a state machine and must provide evidence before it can claim a task is done. Reported result (as claimed by the author): Open source on GitHub. Source: https://x.com/valentinoswe/status/2111573253785329669 Tools they used: Claude Code, OpenAI Codex Category: Dev & ops Please: 1. Ask me 3 short questions about my situation (accounts I have, budget, what I want the output to look like). 2. Propose a step-by-step plan using these tools or cheaper alternatives, with the time and cost of each step. Use official pricing pages; say "check pricing" if unsure. 3. Then do the setup with me one step at a time, waiting for my OK before anything that sends messages, posts publicly, spends money or deletes data. 4. Finish with a checklist to run it again next time.
You are helping me set up this AI use case end to end in Codex. Goal: Make your coding agent show evidence before it says done What the original author did: vstack is a small workflow for Claude Code and Codex based on pstack: the agent follows a state machine and must provide evidence before it can claim a task is done. Reported result (as claimed by the author): Open source on GitHub. Source: https://x.com/valentinoswe/status/2111573253785329669 Tools they used: Claude Code, OpenAI Codex Category: Dev & ops Please: 1. Ask me 3 short questions about my situation (accounts I have, budget, what I want the output to look like). 2. Propose a step-by-step plan using these tools or cheaper alternatives, with the time and cost of each step. Use official pricing pages; say "check pricing" if unsure. 3. Then do the setup with me one step at a time, waiting for my OK before anything that sends messages, posts publicly, spends money or deletes data. 4. Finish with a checklist to run it again next time.
You are helping me set up this AI use case end to end in Grok Bot. Goal: Make your coding agent show evidence before it says done What the original author did: vstack is a small workflow for Claude Code and Codex based on pstack: the agent follows a state machine and must provide evidence before it can claim a task is done. Reported result (as claimed by the author): Open source on GitHub. Source: https://x.com/valentinoswe/status/2111573253785329669 Tools they used: Claude Code, OpenAI Codex Category: Dev & ops Please: 1. Ask me 3 short questions about my situation (accounts I have, budget, what I want the output to look like). 2. Propose a step-by-step plan using these tools or cheaper alternatives, with the time and cost of each step. Use official pricing pages; say "check pricing" if unsure. 3. Then do the setup with me one step at a time, waiting for my OK before anything that sends messages, posts publicly, spends money or deletes data. 4. Finish with a checklist to run it again next time.
The Daily 5
Get five new use cases tomorrow morning
Free. Real sources. Unsubscribe any time.
Guides for this use case
How to automate work with n8n and AI · How to vibe code an app with Claude Code · How to run multiple coding agents together
Related use cases
Get one inbox for every coding agent that needs you
Agentrix is one inbox for AI coding tasks that need your attention, like Claude Code waiting for approval or Codex finishing, so you keep your CLIs and stop hopping between tabs.
Get notified when your coding agent finishes or needs approval
Midway is a Rust CLI that pings you when long commands finish and when Claude Code, Codex, Gemini CLI, Cursor and other agents are done or waiting for approval. Install with cargo install midway-cli.
Close the laptop lid and let your coding agent keep working
Nightcrew is a free open-source Windows tray app: close the lid and Claude Code or Codex keeps working, then the laptop sleeps when the agent is done. No hooks to set up.
Cut coding agent tokens and carry memory between Codex and Claude Code
TOMC is an open-source token saver for AI coding agents: it organizes history per task on CPU for smaller inputs, lets you save in Codex and recall in Claude Code, and carries notes between computers.