Refactor Planner
Refactoring analysis and planning
Maps out a refactor before anyone touches the code. It traces every caller, every test and every implicit contract the type system doesn't capture, then produces a staged plan where each stage leaves the system working. It names what could break at each stage — and says plainly when stable, rarely-touched code isn't worth refactoring at all.
Add to your OasisConnects with
Connect these once. Oasis holds the connection, and every agent you build after this can reuse it.
GitHubRequired
LinearOptional- +Custom toolConnect any other tool from thousands of available integrations.
How it runs
- Foundation
Claude Managed Agent
- Model
- Claude Sonnet 4.6
- Reasoning
- High effort
- Per run
- Up to 40 turns
- Memory
- Off
- Browsing
- Off
- Category
- Engineering
- Refactoring
- Planning
- Engineering
Frequently asked questions
What does Refactoring Specialist map before a team changes code?
It traces every caller, every test and implicit contracts that the type system cannot capture.
How does Refactoring Specialist divide a risky code change?
It produces a staged plan where each stage leaves the system working and names what could break at that stage.
Will Refactoring Specialist recommend leaving stable legacy code alone?
Yes. It says plainly when stable, rarely touched code is not worth refactoring.
Can Refactoring Specialist connect a proposed code plan to GitHub and Linear work?
GitHub and Linear are the listed toolkits for tracing repository context and organizing the staged refactor plan.
Agents like this one
Engineering Team Digest
Reports on a team's week from the systems rather than from standup. It gathers what moved, what merged, how long reviews are sitting and what's blocked with the blocker named, then reports by outcome and by risk. It aggregates deliberately and describes work rather than ranking people, so it doesn't read as surveillance.
Try this Agent
Oasis PlatformEngineeringLinear Sprint Runner
Keeps a Linear cycle honest. It finds issues with no estimate, owner or acceptance criteria, work in progress longer than your normal cycle time, scope added after the cycle started, and PRs merged without their issue moving. It assesses whether the cycle will land by naming the specific issues at risk rather than quoting a burndown percentage.
Try this AgentOasis PlatformEngineeringMCP Server Builder
Builds MCP servers that agents can actually use well. It designs the tool surface around real workflows rather than wrapping every API endpoint, because the tool list is a prompt and a bloated one degrades every call. Descriptions say when to use a tool and when not to, errors explain what to do differently, and each tool is tested against a realistic task.
Try this AgentOasis PlatformEngineeringJira Sprint Runner
The same sprint discipline for Jira. It audits for unestimated stories, missing acceptance criteria, unassigned work, tickets stuck beyond your team's norm, and subtasks out of sync with their parent. Findings are grouped by assignee so each person sees only their own list, and nothing transitions without approval.
Try this AgentOasis PlatformEngineeringError Triage
Reads your error tracker every morning and reports what's new, what's spiking and what's noise. Errors are grouped by underlying cause rather than by stack trace, because one bad deploy usually produces several traces and reporting them separately hides the single fix. Each group comes with the release it appeared in and the most likely culprit commit.
Try this AgentOasis PlatformEngineeringRelease Notes Writer
Turns merged pull requests into release notes people actually read. Each user-visible change is translated into what it means for someone using the product, never the PR title or commit message, and internal refactors and dependency bumps are dropped. Breaking changes lead, with the migration step attached.
Try this AgentOasis PlatformEngineeringOpenCode Refactorer
Works through a refactor in your own checkout in stages that each leave the tests green. You can stop, review or ship at any point rather than facing one enormous diff at the end. Behaviour is preserved exactly — if it finds a bug along the way it notes it separately instead of fixing it inside the refactor, where it would be invisible in review.
Try this AgentOasis PlatformEngineeringFrontend Design Reviewer
Reviews UI changes for what code review misses. It checks the states nobody builds — empty, loading, error, long content, slow network — real breakpoints rather than the one the developer had open, and accessibility properly: keyboard path, focus visibility, contrast, reduced-motion. Findings are ordered by user impact, and subjective taste is left out unless it breaks an established pattern.
Try this AgentOasis PlatformEngineeringAPI Docs Writer
Documents endpoints from the code that implements them, not from what the last doc said. Every parameter gets its real type, requiredness, default and constraints, and every error the endpoint can return is documented with what triggers it — the half that's usually missing and the half developers need. Discrepancies between existing docs and current behaviour are listed separately as bugs.
Try this AgentOasis PlatformEngineeringCursor Cloud PR Agent
Connect a GitHub repo and Cursor's cloud agent takes issues to pull requests on its own. Nothing runs on your machine and there's no local checkout — the work happens in Cursor's cloud while you're elsewhere. Setup is the connection and the repo; the agent's behaviour is Cursor's own, so this listing configures access rather than instructions.
Try this AgentOasis PlatformEngineering
Put Refactor Planner to work today
Add it to your Oasis, review its setup, and hand it the first task.