DEDUPED Hot AI repos, turned into use cases Get 5 a day

How to stop an agent from closing unfinished tasks with Procoder

Make todo close refuse until criteria are checked, evidence is recorded, and the gate is clean.

Who it is forA developer using an agent for standalone tasks who keeps finding work marked done that was not finished.

The problemAn agent reports a task as complete without checking the acceptance criteria or running verification.

The outcomeA task closes only after every acceptance criterion is checked, evidence is recorded, and the gate is clean.

What you need first

  • A git repository you want the agent to work in
  • Claude Code for the plugin install commands shown, or another agent that reads AGENTS.md through the adapters the README links
  • Permission to install the procoder plugin and run /procoder:init in that repository

Steps

  1. Run /plugin install procoder in the repository if it is not installed yet
  2. Create a todo item with its acceptance criteria using the Procoder todo command (inferred, check the README)
  3. Run procoder check and fix every blocking finding
  4. Run procoder todo close on the item and read any refusal (inferred, check the README)
  5. Record the missing evidence or unchecked criteria the refusal names, then close again

Prompt for your agent

In the procoder-enabled repository at <repo-path>, close the todo item <item-id> only after its acceptance criteria are checked and the gate is clean. Report the refusal text if the close is refused. Verify that the item shows as closed only when the gate result is clean.

Caveat. The README names the todo close behavior but does not show the exact todo subcommand syntax, so the steps marked inferred need checking against the command reference.

Share: X LinkedIn Hacker News Email Copy link

Disclaimer

Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page