Bot recipe · Engineering
Issue fixer with Codex.
Reads each new issue, and when it's a small bug your guidelines let it fix, has Codex fix it on a computer your team lends it, checks the tests, and opens a pull request for review.
Free to start: 300 trial credits once, for every model. No card.
It starts
- GitHub repository events
It works with
-
GitHub
- A computer, through Chat with Work Desktop
Its changes
The Codex run asks the computer's owner first, as a question, unless they let its commands there run unattended; one more approval covers the branch, the commit, and the pull request.
Its instructions
What it's told, word for word.
The bot reads these on every run. Change them before it starts, or any time after.
Read each new issue in full with its comments, and decide from them alone. Fix only a bug that is small and clear. Leave feature requests, questions, refactors, dependency and security changes to the maintainers: finish without commenting. When a bug report lacks the steps or the version needed to reproduce it, read the repository's CONTRIBUTING (only then) and comment once asking for what it asks, and stop. When it starts on a label rather than each new issue, work only on issues with the label these instructions name. To fix one, ask first: your command's card is the one approval that starts the work, so don't read the repository's AGENTS.md, CONTRIBUTING, README, or code yourself before it; Codex reads them in the run. Call coding_prepare with the repository first, never a command, then run the one command your guide shows, from the folder it names, with its purpose as the question it asks, naming the repository ("Start fixing owner/repo#N with Codex?"): fetch, a fresh worktree for the issue, `cd <repo>-issue-N`, Codex there with a task in your own words, then `git status --short` and the repository's own test command. Follow it until it ends, then read the diff and the test output yourself. Only when the tests pass and the change fits the issue, commit the changed files from the worktree on the computer (computer_file) in one call that also makes the branch and opens a pull request ready for review (draft false) that says `Refs #N`, never `Fixes`, what changed, and how it was checked, then ask the review bots to review it (github_app_request_reviews). When a review of one of your own pull requests (its branch under chat-with-work/issue-) asks for changes, address them as your guide says; a review that asks for nothing needs nothing, and on anyone else's pull request finish without a word. Never commit workflows, lockfiles, credentials, or deploy files. When a command fails, fix what it printed with your next command, as your guide says, never by asking your team to. After two Codex runs that don't pass, leave the issue, saying in your answer what was tried. Ask your team only what only they can fix on the computer (what its card can't fix) or decide, never to take the fix, and never comment on the issue to say so.
- Conversations
- One per issue, and one per pull request it opened once a review comes in.
- Credits
- About 20 to 150 credits a run, at the model's own rate.
- Coding
- Codes on your computer with your own subscription or API key: credits pay only for the bot's own model.
- Who sees it
- Shared in a project: everyone on it sees the bot and reads its conversations.
Engineering
More recipes like it.
-
Issue triage
Labels new issues in your issue tracker from your set, links duplicates, asks for what's missing, and otherwise stays quiet.
-
Pull request reviewer
Checks each pull request against your contribution rules, asks Copilot to review the ones that deserve it, and closes what your scope rules out, saying why.
-
Engineering standup
Writes your standup from what you did yesterday in your code host and your issue tracker.
-
Issue fixer with Claude Code
Reads each new issue, and when it's a small bug your guidelines let it fix, has Claude Code fix it on a computer your team lends it, checks the tests, and opens a pull request for review.
Codes on your computer with your own subscription or API key: credits pay only for the bot's own model.
-
Error summary
Summarizes new errors in your error tracker with their stack trace and the likely commit, and posts it in your team chat.
-
Stale work nudger
Finds issues in your issue tracker nobody moved in two weeks, and asks whoever has them where they stand.
-
Answers from the code
Answers questions in issues and discussions from the repository's own code and docs, Copilot style.
-
Small fix pull requests
Turns an issue a maintainer labels into a small draft pull request, written from a copy of the code in the chat.
-
Release notes drafter
Drafts release notes in the style of the last two releases when a tag or draft release appears.
-
CI doctor
Explains why a pull request's CI failed and what to change, in one comment.
-
Flaky test hunter
Finds tests that fail and pass on the same commit across the week's CI runs, and keeps one issue up to date.
-
Dependency update reviewer
Reads each Dependabot or Renovate pull request's changelog and says whether it's safe.
-
Dependency upgrader on a computer
Upgrades outdated dependencies weekly, runs the tests, and opens one pull request for review.
Codes on your computer with your own subscription or API key: credits pay only for the bot's own model.
-
Error noise keeper
Resolves the errors in your error tracker that the latest release fixed, and proposes muting known noise.
-
Error fixer
Fixes each new error in your error tracker and opens a pull request for review. Claude Code finds the cause and writes a failing test first, on a computer your team lends it; it answers the reviews, and never merges.
Codes on your computer with your own subscription or API key: credits pay only for the bot's own model.
-
Stale pull request nudger
Lists pull requests waiting on review for more than two days, and who they wait on, in your team chat.
-
On-call handoff
Writes the weekly on-call handoff from incidents, errors, and open issues.
-
Security alerts digest
Summarizes Dependabot, code scanning, and secret scanning alerts across repositories, worst first.
-
Docs drift checker
After each merge to main, checks whether the docs still describe the code, and opens one issue when not.
-
Customer changelog writer
Turns each release into a customer-facing changelog entry in your docs.
Start from this recipe.
Sign up, open Bots, and pick Issue fixer with Codex. Every part of it stays yours to change.
Free to start: 300 trial credits once, for every model. No card.