The same standard Cursor writes, verified outside the editor
Cursor applies Project Rules from .cursor/rules, plus User Rules, Team Rules, and AGENTS.md, each with its own Always, Auto Attached, or Agent Requested trigger. They resolve Team, then Project, then User, so overlapping rules can quietly conflict and cloud agents can run with a different scope. Baz discovers the repo-held rules, grounds the plan in organization-wide search, and verifies the result outside the editor where the merge decision is made.
Cursor tells the agent how to work. Baz keeps the standard.
Native customization tells an agent how to work. Baz turns the durable guidance already stored with your code into scoped requirements it can verify on every Change.
Native customization
Project, team, and user Rules, AGENTS.md, Skills, hooks, subagents, plugins, and MCP
Where instructions drift
With Team, Project, and User rules resolving in precedence order, overlapping instructions can conflict, and cloud agents can operate with a different scope than the editor.
What Baz adds
Baz discovers repo-held .cursor/rules, AGENTS.md, and Skills, scopes them to the changed paths, and verifies the result outside the editor.
A plan Cursor can defend
Cursor has plan mode. Baz adds organization-wide search and a durable plan record, so editor work and cloud agents share the same planning discipline.
Add the Baz Rule and MCP connection to your project.
Run /plan-with-baz so Cursor searches the organization through Baz before coding.
The plan is checked against cross-repository dependencies and risk.
The final plan is recorded before implementation, in the editor and in cloud agent workflows.
Result The same planning discipline inside the editor and cloud agent workflows, recorded before code.
One independent merge standard
Cursor can produce work many ways: IDE edits, background work, cloud agents, Rules, Skills, hooks, and subagents. Baz reviews the result after the code exists and decides one thing: Whether code produced under overlapping editor and team settings still satisfies the repo's durable requirements.
| Baz capability | Evidence used | Decision supported |
|---|---|---|
| AI Coding Guidelines | AGENTS.md, CLAUDE.md, Cursor rules, and Skills matched to changed paths | Did the agent follow the team's durable instructions? |
| Spec Reviewer | The approved requirements and the resulting implementation | Did the agent build what the team asked for? |
| Checks | CI failures mapped to the relevant files and lines | Does the Change pass the tests and checks that matter? |
| Usage and impact | Services, APIs, consumers, entry points, and runtime context | What could the Change affect beyond the edited files? |
| Advanced Security | Code, dependencies, vulnerability patterns, and adversarial review | Does the Change introduce a security risk? |
| Merger | Findings, discussions, approvals, checks, and team merge requirements | Is the Change ready to merge, blocked, or waiting for a human decision? |
Keep every agent’s strengths. Add one control layer.
Each agent keeps its own way to shape behavior. Baz adds the same evidence before code and the same independent verdict after, so the toolchain can change without resetting the standard.
| Capability | Claude Code | OpenAI Codex | Cursor | Devin |
|---|---|---|---|---|
| Durable repo guidance | CLAUDE.md, imported AGENTS.md, .claude/rules | AGENTS.md | Project Rules, AGENTS.md | AGENTS.md |
| Reusable workflows | Skills and plugins | Skills and plugins | Skills and plugins | Skills and Playbooks |
| Specialized workers | Subagents | Subagents | Subagents | Subagents |
| Tool connections | MCP and plugin-bundled | MCP and plugin-bundled | MCP and plugin-bundled | MCP |
| Baz before code | Packaged Planner plugin and plan capture | Packaged Planner plugin and plan capture | Baz Rule, MCP, and plan capture | Baz MCP with repo-held guidance |
| Baz after code | Independent review and merge verdict | Independent review and merge verdict | Independent review and merge verdict | Independent review and merge verdict |
One control layer, whichever agent your team picks
Claude Code
Baz discovers CLAUDE.md, its @-imported files, .claude/rules, and Skills, then loads only the rules relevant to the changed paths and verifies the Change against them.
Baz + Claude CodeOpenAI Codex
Baz discovers AGENTS.md and Skills, then applies the matching requirements during an independent review in GitHub, outside the session that produced the code.
Baz + OpenAI CodexDevin
Baz enforces repo-held AGENTS.md and Skills. Teams can move durable requirements out of Knowledge or Playbooks into versioned repo guidance so every agent and reviewer works from the same contract.
Baz + DevinQuestions teams ask first
Does Baz enforce personal or team Rules?
Baz enforces the repo-held rules it can read. Personal Rules stay private. Requirements that must apply across the team belong in versioned repo guidance that Baz can verify.
Does Baz review Cursor's cloud agents?
Yes. Baz reviews the resulting Change outside the editor, so cloud agents and local edits meet the same durable standard.
Does guidance apply only to part of a repository?
Yes. Baz matches guidelines to changed paths and module scope, so a migration rule does not run on an unrelated frontend Change.
Let developers keep Cursor. Keep one standard for the code.
Connect Baz to your repositories and turn the guidance you already maintain into requirements verified on every Change, before code and again before merge.