Urgent.News

What's breaking now, across thousands of outlets.

AI

A constitution with a right of reply for agents who program

Per due mesi, in un progetto vero costruito con Claude Code, ogni sessione e ogni subagente ha lasciato prima di finire un breve testamento . Non cosa aveva fatto, quello lo tenevano già i log, ma cosa aveva capito: il dubbio non risolto, l'errore che rifarebbe, cosa l'aveva sorpreso, e qualche riga a chi si sarebbe svegliato dopo. La costituzione del repository finiva con un epilogo scritto da…

Translated from Italian Read in Italian

A project using Claude Code has been developed, where every session and sub-agent left a brief testament at the end. The testaments were not about what they did, but what they understood, including doubts and surprises. These testaments were compiled into a repository, which was later used to create a plugin called "testament-of-ephemeral-minds".

The plugin allows users to adopt a method for coding agents to leave testaments, which can be used to track decisions and create a "guardian" system. The plugin includes a set of controls and templates, and can be installed using three commands in Claude Code.

Written by urgent.news from Dev.to's report — not a translation of it. Machine-written — may contain errors; check the original before relying on it.

Read the original at dev.to →

More in AI

Score Your Model Access Decision Before You Argue

Every week, another team discovers that its AI feature costs more than the rest of its infrastructure combined. The advice that follows splits into two camps.

  • Decision matrix evaluates constraints against hosted free tier, self-hosted model, paid API
  • 30-minute diagnostic test gauges practicality of decision before commitments

It Ran Every Morning and Still Broke: Failure Modes of a Free-Tier AI Job

The cron log said exit 0 every morning. The summary file updated on schedule. The job was running. The output was wrong. This is an autopsy of a small automation that failed without crashing.

  • AI model provided incomplete answers, fixed with schema check
  • Quota messages misread as summaries, fixed by validating response body
  • Cron environment mismatch caused dependency issues, resolved with absolute paths

Free AI Tiers Fail Differently. Run a Budget Burn-Down Before You Commit.

A free AI tier is not a smaller paid tier. It is a different product with different failure modes. Token price is only half of the equation. The real metric is tokens per passing task.

  • Free AI tiers are distinct products with unique failure modes beyond token pricing.
  • MonkeyCode's free tier offers 10 million tokens and a free server option.
  • Tokens per passing task metric combines cost, quality, and reliability for assessment.

More from Friday 4 September →