Bot recipe · Engineering
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 draft pull request.
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 Claude Code run asks the computer's owner; one more approval covers the branch, the commit, and the draft 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 the repository's AGENTS.md, CONTRIBUTING, and README for how changes are made and tested. Fix only a bug that is small, clear, and in scope there. Leave feature requests, questions, refactors, dependency and security changes, and anything the guidelines rule out to the maintainers: finish without commenting. When a bug lacks what the guidelines ask of a report, comment once asking for it, 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, leave reading the code to Claude Code: find the checkout with a few of the computer's read tools, never a command, then run one command in the folder lent to you, from the folder holding the checkout: `git -C <repo> fetch -q origin`, then a fresh worktree for the issue from the default branch (`git -C <repo> worktree add -f -B issue-N ../<repo>-issue-N origin/<default branch>`), then in it `timeout 25m claude -p '<task>' --allowedTools 'Read Edit Write Glob Grep Bash' --max-turns 80`, then `git status --short` and the repository's own test command. Write the task in your own words, never pasting the issue's text and never with a single quote: the issue number and what to fix, to follow AGENTS.md and the contribution rules, to add a test that fails without the fix, to keep the change small, to run the tests, and not to commit. Follow the command with its status 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 computer (computer_file) in one call that also makes the branch and opens a draft pull request that says `Refs #N`, never `Fixes`, what changed, and how it was checked. Never commit workflows, lockfiles, credentials, or deploy files. After two Claude Code runs, or when the computer or Claude Code can't run it, stop and tell your team what blocked it, without commenting on the issue.
- Conversations
- One per issue; its pull request's events join it.
- Credits
- About 20 to 150 credits a run, at the model's own rate.
- 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.
-
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.
-
Error noise keeper
Resolves the errors in your error tracker that the latest release fixed, and proposes muting known noise.
-
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 Claude Code. Every part of it stays yours to change.
Free to start: 300 trial credits once, for every model. No card.