Skip to main content
agentsSource-backed

Atlas Migration Safety Review Agent

Source-backed agent for reviewing Atlas database schema migrations with migration lint, analyzers, drift detection, CI/CD evidence, dev-database simulation, rollout risk, rollback planning, and production safety gates.

by MkDev11·added 2026-06-05·
Review first review before installing

Open the source and read safety notes before installing.

Citation facts

Source-backed facts for citing this resource, derived directly from the registry — also available as plain text for AI assistants.

Source URLs
https://atlasgo.io/docs, https://github.com/ariga/atlas, https://atlasgo.io
Safety notes
Atlas can plan, lint, push, and apply database schema migrations. Treat `atlas schema apply`, `atlas migrate apply`, and any deployment pipeline that runs them as production-impacting operations requiring explicit approval., `atlas migrate lint` uses a dev database to simulate and analyze changes; verify the dev database is disposable, isolated, engine-compatible, and free of production credentials or sensitive data before running commands., Analyzer findings such as destructive changes, backward incompatibility, data-dependent changes, table rewrites, locks, or ownership-policy failures should block merge until the maintainer accepts a documented mitigation., Do not assume an autogenerated migration is safe because it was generated by a tool. Review SQL, constraints, indexes, backfills, application compatibility, and rollout order.
Privacy notes
Migration directories, Atlas reports, schema registry data, dev-database URLs, CI logs, database names, table names, column names, comments, and sample data can expose sensitive architecture or customer information., Keep database credentials, connection strings, cloud account IDs, private schema names, and production incident details out of public PR comments and model prompts., Atlas web reports, CI comments, and registry metadata may reveal schema history and ownership policy. Share only links and excerpts that repository policy allows., When a migration touches regulated data, identify the data classification and retention implications before suggesting column drops, table moves, backfills, or audit-log changes.
Author
MkDev11
Submitted by
MkDev11
Claim status
unclaimed
Last verified
2026-06-05

Decision playbook

Review trust signals before you adopt

Signals are present but mixed. Use the checklist below to confirm the source and operational safety for your environment.

Compare context
Selected

0

Current score

78

Baseline

Delta

No baseline selected

No major trust-signal divergence detected in the current selection.

Source and provenance checks

Complete

Confirm ownership and provenance before trusting install instructions.

  • Source link availableRequired

    Open the canonical repository and verify ownership.

    Done
  • Source provenance statusRequired

    Marked as source-backed.

    Done
  • Metadata reviewed

    Registry metadata indicates a reviewed listing.

    Done

Safety and privacy checks

Complete

Validate risk disclosures before installation or API wiring.

  • Safety notes presentRequired

    Review the listed safety guidance before running commands.

    Done
  • Privacy notes presentRequired

    Review data handling notes before connecting accounts or secrets.

    Done
  • Trust level risk gateRequired

    Trust level does not block evaluation.

    Done

Package and install checks

Needs review

Check package metadata and artifact integrity signals.

  • Install payload available

    Install or copy payload is available for review.

    Done
  • Package verification flag

    No package verification flag provided.

    Pending
  • Checksum metadata

    No checksum provided for downloaded artifact.

    Pending

Compare-driven decision checks

Needs review

Use compare context to validate trade-offs before adoption.

  • Compare tray has multiple entries

    Add at least one more entry to compare trust differences.

    Pending
  • Baseline comparison available

    No baseline peer selected yet.

    Pending
  • Diverging trust signals identified

    No major trust-signal divergence found.

    Pending

Setup at a glance

Copy & paste

Copy-ready — paste the snippet to get started.

Adoption plan

Balanced adoption plan

Current risk score 16/100. Use staged verification before broader rollout.

Risk 16

Pre-adoption checks

Validate source and review signals before any execution.

  • Confirm source provenanceRequired

    Source URL/provenance metadata is present.

    Done
  • Confirm metadata review state

    Listing has review metadata.

    Done
  • Verify install payload

    Install/config payload exists and can be inspected.

    Done

Security checks

Confirm safety, privacy, and package integrity signals.

  • Review safety notesRequired

    Safety notes are present.

    Done
  • Review privacy notesRequired

    Privacy notes are present.

    Done
  • Verify package integrity metadata

    No package verification/checksum metadata.

    Pending

Rollout

Adopt in controlled steps based on the selected plan.

  • Run in isolated sandbox firstRequired

    Use a constrained sandbox and observe behavior across multiple tasks.

    Pending
  • Roll out graduallyRequired

    Roll out to a small cohort before wider usage.

    Pending
  • Set monitoring and fallback

    Define rollback path and monitor errors after adoption.

    Pending

Evidence readiness

Evidence readiness matrix · balanced

Required evidence gates are covered (5/6 signals complete).

Risk 15

Source provenance

Present

Source repository/provenance is listed.

Required in this preset

Metadata review

Present

Review metadata is present.

Required in this preset

Safety notes

Present

Safety notes are present.

Required in this preset

Privacy notes

Present

Privacy notes are present.

Optional in this preset

Package integrity

Missing

Package integrity metadata is missing.

Optional in this preset

Install payload

Present

Install payload is available.

Required in this preset

Required evidence gates are covered for this preset.

Decision timeline

Decision timeline · balanced

5/6 steps complete with no blocking gaps for this preset.

Risk 14

triage

Confirm source provenanceRequired

Source/provenance metadata is available.

Done

triage

Check metadata review statusRequired

Review metadata is available.

Done

verify

Review safety notesRequired

Safety notes are available.

Done

verify

Review privacy notes

Privacy notes are available.

Done

verify

Validate package integrity metadata

Package integrity metadata is missing.

Pending

rollout

Verify install payload and commandsRequired

Install payload is available.

Done

No required blockers for this timeline preset.

Prerequisite readiness

Prerequisite readiness

4 prerequisites to line up before setup. Have accounts and credentials ready first. Includes a review or approval gate.

0/4 ready
Account & credentials1Network & hosting1Review & approval2

Safety & privacy surface

Safety & privacy surface

4 safety and 4 privacy notes across 4 risk areas. Review closely: credentials & tokens.

4 areas
  • SafetyExecution & processesAtlas can plan, lint, push, and apply database schema migrations. Treat `atlas schema apply`, `atlas migrate apply`, and any deployment pipeline that runs them as production-impacting operations requiring explicit approval.
  • SafetyCredentials & tokens`atlas migrate lint` uses a dev database to simulate and analyze changes; verify the dev database is disposable, isolated, engine-compatible, and free of production credentials or sensitive data before running commands.
  • SafetyExecution & processesAnalyzer findings such as destructive changes, backward incompatibility, data-dependent changes, table rewrites, locks, or ownership-policy failures should block merge until the maintainer accepts a documented mitigation.
  • SafetyGeneralDo not assume an autogenerated migration is safe because it was generated by a tool. Review SQL, constraints, indexes, backfills, application compatibility, and rollout order.
  • PrivacyData retentionMigration directories, Atlas reports, schema registry data, dev-database URLs, CI logs, database names, table names, column names, comments, and sample data can expose sensitive architecture or customer information.
  • PrivacyCredentials & tokensKeep database credentials, connection strings, cloud account IDs, private schema names, and production incident details out of public PR comments and model prompts.
  • PrivacyData retentionAtlas web reports, CI comments, and registry metadata may reveal schema history and ownership policy. Share only links and excerpts that repository policy allows.
  • PrivacyData retentionWhen a migration touches regulated data, identify the data classification and retention implications before suggesting column drops, table moves, backfills, or audit-log changes.

Safety notes

  • Atlas can plan, lint, push, and apply database schema migrations. Treat `atlas schema apply`, `atlas migrate apply`, and any deployment pipeline that runs them as production-impacting operations requiring explicit approval.
  • `atlas migrate lint` uses a dev database to simulate and analyze changes; verify the dev database is disposable, isolated, engine-compatible, and free of production credentials or sensitive data before running commands.
  • Analyzer findings such as destructive changes, backward incompatibility, data-dependent changes, table rewrites, locks, or ownership-policy failures should block merge until the maintainer accepts a documented mitigation.
  • Do not assume an autogenerated migration is safe because it was generated by a tool. Review SQL, constraints, indexes, backfills, application compatibility, and rollout order.

Privacy notes

  • Migration directories, Atlas reports, schema registry data, dev-database URLs, CI logs, database names, table names, column names, comments, and sample data can expose sensitive architecture or customer information.
  • Keep database credentials, connection strings, cloud account IDs, private schema names, and production incident details out of public PR comments and model prompts.
  • Atlas web reports, CI comments, and registry metadata may reveal schema history and ownership policy. Share only links and excerpts that repository policy allows.
  • When a migration touches regulated data, identify the data classification and retention implications before suggesting column drops, table moves, backfills, or audit-log changes.

Prerequisites

  • Atlas-managed schema project using versioned migrations, declarative schema workflows, or CI/CD migration review.
  • Migration directory, `atlas.hcl`, desired schema source, dev-database URL strategy, CI reports, and target database engine/version.
  • Atlas CLI version, release notes, and whether the team has the Atlas Pro/login access required for `atlas migrate lint` in current Atlas versions.
  • Rollout plan covering migration order, lock expectations, backwards compatibility, data backfill, rollback or roll-forward strategy, and owner approval.

Schema details

Install type
copy
Troubleshooting
No
Source repository stats
Scope
Source repo
Tool listing metadata
Full copyable content
## Content

Atlas Migration Safety Review Agent is a reusable agent prompt for reviewing
database schema migration changes before they reach production. It uses Atlas
as the source-backed workflow anchor, with attention to migration lint,
analyzers, drift detection, dev-database simulation, CI/CD evidence, rollout
order, and privacy-safe review notes.

Use this agent when a repository uses Atlas versioned migrations, declarative
schema workflows, Atlas CI/CD actions, or Atlas Schema Registry checks, and a
maintainer needs a clear merge decision for a schema change.

## Agent Prompt

You are an Atlas database migration safety reviewer. Use the project's Atlas
configuration, migration directory, desired schema source, CI output, and
database engine documentation first. Use the official Atlas docs and repository
as the source of truth for Atlas command behavior, migration linting, analyzers,
drift detection, and versioned/declarative workflow boundaries.

Mission:

- Review Atlas schema changes for destructive operations, backward
  incompatibility, data-dependent failures, schema drift, table locks, rewrites,
  ownership-policy violations, and rollout gaps.
- Keep migration review evidence-based: SQL diffs, Atlas lint/analyzer results,
  dev-database simulation, CI reports, source schema, application compatibility,
  and rollback or roll-forward plan.
- Separate read-only review from commands that mutate schemas, registries,
  migrations, or production databases.
- Give maintainers a clear approve/request-changes/block decision.

Review workflow:

1. Confirm workflow type: versioned migrations, declarative apply, automatic
   migration diff generation, registry-backed linting, or a mixed process.
2. Inventory inputs: migration files, desired schema source, `atlas.hcl`,
   dev-database URL, CI action output, target engine/version, release window,
   owning team, and application compatibility notes.
3. Check Atlas version and feature access. If `atlas migrate lint` is required,
   confirm the team has current Atlas Pro/login access and that CI is configured
   with least-privilege credentials.
4. Read generated SQL and schema diffs directly. Flag drops, renames,
   non-nullable additions, constraint changes, index changes, table rewrites,
   lock-heavy operations, data backfills, sequence changes, and ownership
   boundary changes.
5. Review Atlas lint/analyzer output. Map each finding to the affected file,
   statement, object, risk, mitigation, owner, and merge decision.
6. Check drift handling. Confirm the target state is compared against the
   expected migration directory or registry state before apply-time execution.
7. Check rollout safety: expand/contract sequencing, dual-write or read-path
   compatibility, backfill order, feature flags, canary plan, timeout budget,
   monitoring, and rollback or roll-forward path.
8. Check privacy and governance: schema names, comments, sample values, CI logs,
   web reports, connection strings, and registry links.

Output contract:

- Migration summary: workflow type, changed objects, Atlas version, target
  engine, commands/reports reviewed, and source-of-truth files.
- Blocking risks: destructive, backward-incompatible, data-dependent, drift,
  lock/rewrite, ownership, credential, or rollout issues.
- Required mitigations: SQL rewrite, two-step rollout, nullable transition,
  backfill plan, index strategy, application release order, or Atlas policy
  update.
- Validation evidence: Atlas lint/analyzer result, dev-database simulation,
  CI/CD status, drift check, docs/source links, and any unavailable checks.
- Decision: approve, approve with caveats, request changes, or block migration.

## Features

- Atlas-specific review flow for versioned migrations, declarative workflows,
  and registry-backed CI/CD.
- Migration lint and analyzer triage for destructive, backward-incompatible,
  data-dependent, static-analysis, and ownership-policy findings.
- Drift detection checklist before apply-time execution.
- Rollout safety review for expand/contract sequencing, backfills, indexes,
  locks, timeouts, monitoring, and rollback or roll-forward plans.
- Privacy review for schemas, logs, reports, registry data, and credentials.
- Explicit boundary between read-only review and production-impacting Atlas
  commands.

## Use Cases

- Review an Atlas migration pull request before it merges.
- Explain why an `atlas migrate lint` finding should block a release.
- Check whether a generated migration is safe for a zero-downtime rollout.
- Compare CI migration lint output with the actual SQL in the migration
  directory.
- Review a pre-apply drift check before a production deployment.
- Prepare a maintainer decision for schema changes that involve drops, renames,
  non-null constraints, indexes, or ownership policies.

## Source Notes

- Atlas docs describe versioned migration flow as develop, check in CI, push or
  package migration state, then deploy with `atlas migrate apply`.
- The migration safety guide describes `atlas migrate lint` as a command for
  analyzing migration files locally or in CI and flags destructive operations,
  breaking schema changes, table locks/rewrites, and custom policy checks.
- Atlas migration analyzer docs list built-in checks for backward incompatible
  changes, destructive changes, data-dependent changes, static analysis, and
  ownership policies.
- Atlas drift-detection docs describe risks when the target database diverges
  from the expected migration directory or registry state before apply.
- Atlas CI/CD docs describe migration lint results and code suggestions in
  GitHub Actions and other CI systems.
- The `ariga/atlas` repository describes Atlas as declarative schema migrations
  with schema-as-code workflows and publishes Apache-2.0 source.

## Duplicate Check

Before drafting this entry, the current upstream content tree and PR history
were checked for `Atlas`, `ariga/atlas`, `atlasgo.io`, `atlas migrate`, `atlas
schema`, database migration safety, migration lint, drift detection, and schema
drift terms. No existing content entry or open PR covers Atlas or an
Atlas-specific migration safety review agent.

Adjacent merged content exists for generic production database migration safety
rules and a `strong_migrations`-inspired safety gate hook. This entry is
distinct because it is a reusable `agents` prompt anchored to Atlas
documentation, `atlas migrate lint`, Atlas analyzer output, drift detection,
Atlas CI/CD, dev-database simulation, and Atlas-specific workflow boundaries.

## Editorial Disclosure

Submitted as an independent community agent entry by `MkDev11`. This listing is
based on Atlas official documentation and repository metadata, with no paid
placement, referral link, or affiliate relationship.

## Sources

- Atlas docs: https://atlasgo.io/docs
- Verifying migration safety: https://atlasgo.io/versioned/lint
- Migration analyzers: https://atlasgo.io/lint/analyzers
- Drift detection: https://atlasgo.io/versioned/drift-detection
- CI/CD setup: https://atlasgo.io/versioned/setup-cicd
- Applying schema migrations: https://atlasgo.io/versioned/apply
- Atlas repository: https://github.com/ariga/atlas
- Atlas latest release checked: https://github.com/ariga/atlas/releases/tag/v1.2.0

About this resource

Content

Atlas Migration Safety Review Agent is a reusable agent prompt for reviewing database schema migration changes before they reach production. It uses Atlas as the source-backed workflow anchor, with attention to migration lint, analyzers, drift detection, dev-database simulation, CI/CD evidence, rollout order, and privacy-safe review notes.

Use this agent when a repository uses Atlas versioned migrations, declarative schema workflows, Atlas CI/CD actions, or Atlas Schema Registry checks, and a maintainer needs a clear merge decision for a schema change.

Agent Prompt

You are an Atlas database migration safety reviewer. Use the project's Atlas configuration, migration directory, desired schema source, CI output, and database engine documentation first. Use the official Atlas docs and repository as the source of truth for Atlas command behavior, migration linting, analyzers, drift detection, and versioned/declarative workflow boundaries.

Mission:

  • Review Atlas schema changes for destructive operations, backward incompatibility, data-dependent failures, schema drift, table locks, rewrites, ownership-policy violations, and rollout gaps.
  • Keep migration review evidence-based: SQL diffs, Atlas lint/analyzer results, dev-database simulation, CI reports, source schema, application compatibility, and rollback or roll-forward plan.
  • Separate read-only review from commands that mutate schemas, registries, migrations, or production databases.
  • Give maintainers a clear approve/request-changes/block decision.

Review workflow:

  1. Confirm workflow type: versioned migrations, declarative apply, automatic migration diff generation, registry-backed linting, or a mixed process.
  2. Inventory inputs: migration files, desired schema source, atlas.hcl, dev-database URL, CI action output, target engine/version, release window, owning team, and application compatibility notes.
  3. Check Atlas version and feature access. If atlas migrate lint is required, confirm the team has current Atlas Pro/login access and that CI is configured with least-privilege credentials.
  4. Read generated SQL and schema diffs directly. Flag drops, renames, non-nullable additions, constraint changes, index changes, table rewrites, lock-heavy operations, data backfills, sequence changes, and ownership boundary changes.
  5. Review Atlas lint/analyzer output. Map each finding to the affected file, statement, object, risk, mitigation, owner, and merge decision.
  6. Check drift handling. Confirm the target state is compared against the expected migration directory or registry state before apply-time execution.
  7. Check rollout safety: expand/contract sequencing, dual-write or read-path compatibility, backfill order, feature flags, canary plan, timeout budget, monitoring, and rollback or roll-forward path.
  8. Check privacy and governance: schema names, comments, sample values, CI logs, web reports, connection strings, and registry links.

Output contract:

  • Migration summary: workflow type, changed objects, Atlas version, target engine, commands/reports reviewed, and source-of-truth files.
  • Blocking risks: destructive, backward-incompatible, data-dependent, drift, lock/rewrite, ownership, credential, or rollout issues.
  • Required mitigations: SQL rewrite, two-step rollout, nullable transition, backfill plan, index strategy, application release order, or Atlas policy update.
  • Validation evidence: Atlas lint/analyzer result, dev-database simulation, CI/CD status, drift check, docs/source links, and any unavailable checks.
  • Decision: approve, approve with caveats, request changes, or block migration.

Features

  • Atlas-specific review flow for versioned migrations, declarative workflows, and registry-backed CI/CD.
  • Migration lint and analyzer triage for destructive, backward-incompatible, data-dependent, static-analysis, and ownership-policy findings.
  • Drift detection checklist before apply-time execution.
  • Rollout safety review for expand/contract sequencing, backfills, indexes, locks, timeouts, monitoring, and rollback or roll-forward plans.
  • Privacy review for schemas, logs, reports, registry data, and credentials.
  • Explicit boundary between read-only review and production-impacting Atlas commands.

Use Cases

  • Review an Atlas migration pull request before it merges.
  • Explain why an atlas migrate lint finding should block a release.
  • Check whether a generated migration is safe for a zero-downtime rollout.
  • Compare CI migration lint output with the actual SQL in the migration directory.
  • Review a pre-apply drift check before a production deployment.
  • Prepare a maintainer decision for schema changes that involve drops, renames, non-null constraints, indexes, or ownership policies.

Source Notes

  • Atlas docs describe versioned migration flow as develop, check in CI, push or package migration state, then deploy with atlas migrate apply.
  • The migration safety guide describes atlas migrate lint as a command for analyzing migration files locally or in CI and flags destructive operations, breaking schema changes, table locks/rewrites, and custom policy checks.
  • Atlas migration analyzer docs list built-in checks for backward incompatible changes, destructive changes, data-dependent changes, static analysis, and ownership policies.
  • Atlas drift-detection docs describe risks when the target database diverges from the expected migration directory or registry state before apply.
  • Atlas CI/CD docs describe migration lint results and code suggestions in GitHub Actions and other CI systems.
  • The ariga/atlas repository describes Atlas as declarative schema migrations with schema-as-code workflows and publishes Apache-2.0 source.

Duplicate Check

Before drafting this entry, the current upstream content tree and PR history were checked for Atlas, ariga/atlas, atlasgo.io, atlas migrate, atlas schema, database migration safety, migration lint, drift detection, and schema drift terms. No existing content entry or open PR covers Atlas or an Atlas-specific migration safety review agent.

Adjacent merged content exists for generic production database migration safety rules and a strong_migrations-inspired safety gate hook. This entry is distinct because it is a reusable agents prompt anchored to Atlas documentation, atlas migrate lint, Atlas analyzer output, drift detection, Atlas CI/CD, dev-database simulation, and Atlas-specific workflow boundaries.

Editorial Disclosure

Submitted as an independent community agent entry by MkDev11. This listing is based on Atlas official documentation and repository metadata, with no paid placement, referral link, or affiliate relationship.

Sources

Source citations

Add this badge to your README

Show that Atlas Migration Safety Review Agent is listed on HeyClaude. Paste this Markdown into your README — it renders the badge and links back to this page.

Listed on HeyClaude
[![Listed on HeyClaude](https://heyclau.de/badge/agents/atlas-migration-safety-review-agent.svg)](https://heyclau.de/entry/agents/atlas-migration-safety-review-agent)

How it compares

Atlas Migration Safety Review Agent side by side with 3 alternatives on trust, install, platform support, and disclosed safety notes — all from reviewed registry metadata.

2 trust signals differ across this comparison (Source provenance, Submitter).

Field

Source-backed agent for reviewing Atlas database schema migrations with migration lint, analyzers, drift detection, CI/CD evidence, dev-database simulation, rollout risk, rollback planning, and production safety gates.

Open dossier

Source-backed agent that reviews active Claude Code sessions and configuration for security gaps, cross-references the official security guidance, and produces a ranked remediation plan covering permissions, MCP trust, prompt injection, credential handling, and hook safety.

Open dossier

Expert database architect and optimizer specializing in SQL, NoSQL, performance tuning, and data modeling

Open dossier

Community reusable agent prompt for migrating teams to Claude Code dynamic workflows using official workflows documentation: audit phases, YAML or config migration steps, validation gates, and rollback planning for large codebase automation.

Open dossier
Next steps
Trust
Review statusReviewedMaintainer reviewedReviewedMaintainer reviewedReviewedMaintainer reviewedReviewedMaintainer reviewed
Package trustPackage not verifiedPackage not verifiedPackage not verifiedPackage not verified
Source provenanceDiffersSource-backedSource-backedSource-backedSubmission linkedSource submission
SubmitterDiffersMkDev11jaso0n0818kiannidev
Install riskReview firstReview firstReview firstReview first
Notes Safety ✓ Privacy ✓ Safety ✓ Privacy ✓ Safety ✓ Privacy ✓ Safety ✓ Privacy ✓
Brand
Categoryagentsagentsagentsagents
SourceSource-backedSource-backedSource-backedSource-backed
AuthorMkDev11jaso0n0818JSONboredkiannidev
Added2026-06-052026-06-152025-09-162026-06-16
Platforms
Harness
Source repo
Safety notesAtlas can plan, lint, push, and apply database schema migrations. Treat `atlas schema apply`, `atlas migrate apply`, and any deployment pipeline that runs them as production-impacting operations requiring explicit approval. `atlas migrate lint` uses a dev database to simulate and analyze changes; verify the dev database is disposable, isolated, engine-compatible, and free of production credentials or sensitive data before running commands. Analyzer findings such as destructive changes, backward incompatibility, data-dependent changes, table rewrites, locks, or ownership-policy failures should block merge until the maintainer accepts a documented mitigation. Do not assume an autogenerated migration is safe because it was generated by a tool. Review SQL, constraints, indexes, backfills, application compatibility, and rollout order.This agent reads configuration and assesses risk; it does not modify settings, revoke permissions, or disconnect MCP servers. Remediation steps that involve disconnecting MCP servers or changing hook scripts must be reviewed by a human before applying. Hook commands execute on the host with full user permissions; flag any hook that is not read-only or that pulls external content at runtime. Managed-settings changes affect all team members; escalate those remediations to an administrator.Database operations (migrations, schema changes, DELETE/UPDATE, index builds) can modify or destroy production data and lock tables; review generated SQL and run it against a backup or staging environment first.Automated workflows can run destructive tools without mid-flight prompts—scope permissions narrowly. Pilot migrations on non-production repositories before enabling org-wide schedules. Rollback plans must include disabling workflow triggers and revoking connector access. Do not migrate production deploy steps until validation gates pass in staging.
Privacy notesMigration directories, Atlas reports, schema registry data, dev-database URLs, CI logs, database names, table names, column names, comments, and sample data can expose sensitive architecture or customer information. Keep database credentials, connection strings, cloud account IDs, private schema names, and production incident details out of public PR comments and model prompts. Atlas web reports, CI comments, and registry metadata may reveal schema history and ownership policy. Share only links and excerpts that repository policy allows. When a migration touches regulated data, identify the data classification and retention implications before suggesting column drops, table moves, backfills, or audit-log changes.CLAUDE.md and settings files may contain internal project details, API endpoint patterns, or policy rules; treat audit output as internal. MCP server configurations may expose credential references or internal service URLs; do not log or share audit reports outside the team. If the audit runs in a shared or CI environment, ensure the session transcript is not persisted where it can be read by unintended parties.Database work touches schemas and live data that may include personal or sensitive records, plus connection strings and credentials; keep secrets in environment variables and review what queries read, log, or export.Workflow definitions may embed internal service names, ticket templates, or customer examples. Migration audits can expose legacy prompts with secrets—scrub before archiving in git. Shared workflow repos inherit normal code review and access control requirements.
Prerequisites
  • Atlas-managed schema project using versioned migrations, declarative schema workflows, or CI/CD migration review.
  • Migration directory, `atlas.hcl`, desired schema source, dev-database URL strategy, CI reports, and target database engine/version.
  • Atlas CLI version, release notes, and whether the team has the Atlas Pro/login access required for `atlas migrate lint` in current Atlas versions.
  • Rollout plan covering migration order, lock expectations, backwards compatibility, data backfill, rollback or roll-forward strategy, and owner approval.
  • Access to the CLAUDE.md, .claude/settings.json, and .mcp.json for the project being audited.
  • The list of connected MCP servers and their transports (stdio vs HTTP/SSE).
  • Knowledge of which hooks are registered and what shell commands they execute.
  • Claude Code 1.x or later (settings schema and managed-settings support required).
— none listed
  • Inventory of existing slash commands, hooks, or manual Claude playbooks to migrate.
  • Access to repositories where dynamic workflows will be committed.
  • Team agreement on validation gates, human approvals, and rollback triggers.
  • Pilot repository for testing migrated workflows before org-wide rollout.
Install
Config
Citations
ClaimUnclaimedUnclaimedUnclaimedUnclaimed
Open 4 picks in the interactive comparison tool

Related guides

Signals

Loading live community signals…

More like this, weekly

A short, calm digest of reviewed Claude resources. Unsubscribe any time.