Bug investigation & fix
Assign a bug and a coding agent investigates the root cause, proves it with a failing test, fixes the smallest surface, self-reviews the diff, and drafts a pull request for you to merge.
Saves you ~3.9 h / run
How it works
- Trigger
- When you start the “Diagnose, fix, self-review, draft PR” workflow.
- Job
- Build a feedback loop, find the root cause, fix it with a test.
- Outcome
- A tested implementation and pull request draft.
What it installs
Agents 2
-
Coding Agent
Fixes assigned bugs in the connected repository with a proven regression test and a self-reviewed PR.
-
Bug investigation & fix Quality Reviewer
Checks primary evidence, domain controls, deliverable completeness, and communication quality, stopping the run when the work is wrong, unsupported, incomplete, or uncertain.
Teams 1
-
Bug investigation & fix quality team
The delivery agents produce the work while an independent quality reviewer checks each workflow handoff against explicit evidence, domain, and communication requirements before the run can continue.
Workflows 1
-
Diagnose, fix, self-review, draft PR
Build a feedback loop, find the root cause, fix it with a test, self-review the diff, and draft a PR for approval.
Goals 1
-
Bugs closed with a proven, self-reviewed fix
Reported bugs are resolved at the root cause, locked down by a regression test, and shipped through a self-reviewed PR. Success looks like: Every assigned bug closes with a regression test that fails before the fix and passes after, a diff that passed the pre-PR security and performance self-review with no unaddressed finding, and an approved pull request.
Skills 4
-
diagnosing-bugs
Feedback-loop-first diagnosis for hard bugs and performance regressions: build a tight, deterministic, red-capable signal before forming any theory. Adapted from mattpocock/skills/diagnosing-bugs.
-
systematic-debugging
A disciplined four-phase debugging loop governed by an iron law — no fix without root-cause investigation first — escalating to architecture after three failed fixes. Adapted from obra/superpowers/systematic-debugging.
-
find-bugs
Branch-diff review for bugs, security vulnerabilities, and quality issues: gather the full diff, map the attack surface, run a per-file security checklist, verify each finding is real, and audit before concluding. Adapted from getsentry/skills/find-bugs.
-
django-perf-review
Validated performance review (N+1 queries, unbounded querysets, missing indexes, write loops) where every finding is traced and proven before reporting, and severity must match real impact. Adapted from getsentry/skills/django-perf-review.
Requirements
- Connected repository — Needs a connected code repository to read the failing code, build a feedback loop, and propose a fix.
- Browser access to GitHub — The agent works in GitHub through its web interface in your browser and pauses for your approval before making any changes. Until you connect it, it works from attached exports.
- A runnable test or repro harness — The loop needs a way to run the bug code path unattended — a test runner, a dev server to curl, or a CLI invocation — so the fix can be proven, not assumed.
Setup guide
How to Fix Bugs With a Coding Agent
A practical guide to fixing bugs with a coding agent: feedback loops, root-cause investigation, regression tests, and approval before merge.
Read the setup guideDon't see your workflow? Describe it.
A sentence or two about a recurring job is enough. We design the playbook that runs it and show you exactly what it saves.