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 capabilityEvidence usedDecision supported
AI Coding GuidelinesAGENTS.md, CLAUDE.md, Cursor rules, and Skills matched to changed pathsDid the agent follow the team's durable instructions?
Spec ReviewerThe approved requirements and the resulting implementationDid the agent build what the team asked for?
ChecksCI failures mapped to the relevant files and linesDoes the Change pass the tests and checks that matter?
Usage and impactServices, APIs, consumers, entry points, and runtime contextWhat could the Change affect beyond the edited files?
Advanced SecurityCode, dependencies, vulnerability patterns, and adversarial reviewDoes the Change introduce a security risk?
MergerFindings, discussions, approvals, checks, and team merge requirementsIs 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.

CapabilityClaude CodeOpenAI CodexCursorDevin
Durable repo guidanceCLAUDE.md, imported AGENTS.md, .claude/rulesAGENTS.mdProject Rules, AGENTS.mdAGENTS.md
Reusable workflowsSkills and pluginsSkills and pluginsSkills and pluginsSkills and Playbooks
Specialized workersSubagentsSubagentsSubagentsSubagents
Tool connectionsMCP and plugin-bundledMCP and plugin-bundledMCP and plugin-bundledMCP
Baz before codePackaged Planner plugin and plan capturePackaged Planner plugin and plan captureBaz Rule, MCP, and plan captureBaz MCP with repo-held guidance
Baz after codeIndependent review and merge verdictIndependent review and merge verdictIndependent review and merge verdictIndependent review and merge verdict

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 Code

OpenAI 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 Codex

Devin

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 + Devin

Questions 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.