Run a coding-agent harness in about 400 lines of shell
Built Pu.sh, a full coding-agent harness in about 400 lines of shell.
Source
nahimn on Hacker News · 2026-04-30 · Project link
Written in our own words. Credit to the original author. Link checked 2026-10-15.
What they did
Built Pu.sh, a full coding-agent harness in about 400 lines of shell.
Result (as claimed)
Open-sourced minimal harness on Show HN.
Tools they used
Cost: Claude Code: free plan, paid from $17/mo; OpenAI Codex: free plan, paid from $8/mo. Checked 2026-10-14.
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: Run a coding-agent harness in about 400 lines of shell What the original author did: Built Pu.sh, a full coding-agent harness in about 400 lines of shell. Reported result (as claimed by the author): Open-sourced minimal harness on Show HN. Source: https://news.ycombinator.com/item?id=47968112 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: Run a coding-agent harness in about 400 lines of shell What the original author did: Built Pu.sh, a full coding-agent harness in about 400 lines of shell. Reported result (as claimed by the author): Open-sourced minimal harness on Show HN. Source: https://news.ycombinator.com/item?id=47968112 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: Run a coding-agent harness in about 400 lines of shell What the original author did: Built Pu.sh, a full coding-agent harness in about 400 lines of shell. Reported result (as claimed by the author): Open-sourced minimal harness on Show HN. Source: https://news.ycombinator.com/item?id=47968112 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.
Related use cases
Route coding-agent models to match frontier solo performance
Built an open-source model router that ensembles coding agents to reach Astra-level performance cheaper than one frontier model.
Run agents in a quality-focused AI coding environment
Built Command Center, an AI coding environment aimed at people who care about output quality.
Deploy coding-agent apps on open-source Heroku-style hosts
Built InsForge, an open-source Heroku-style platform aimed at coding agents.
Run up to 16 coding agents side by side
Built SwarmPane to run Claude Code, Codex, Gemini, Grok and Cursor in parallel panes with attention cues.