Claude Code
Anthropic's agentic coding tool with a managed GitHub PR review service, local review commands, and security-scanning plugins.
Deployment
Cloud · Self-Hosted (partial)
Languages
Any (no fixed list)
Pricing model
Per developer seat, Usage-based credits, Quote-based
Free plan
No
Partial means the documentation covers only part of a capability, a related capability, or a beta. The description next to it says what is covered.
Workflow coverage
Where in the development lifecycle Claude Code operates.
5 yes 1 partial 2 no
| Feature | Availability | Description |
|---|---|---|
| Real-Time IDE Feedback | Partial | Security guidance plugin pattern-checks each file edit Claude makes; no linting as a human types. |
| AI Agent Guardrails | Yes | Security guidance plugin reviews Claude's edits, end-of-turn diffs and commits, then re-prompts Claude to fix. |
| Local Analysis (Pre-Commit) | Yes | /code-review and /security-review run in the terminal; /claude-security local scan needs a paid plan. |
| Inline PR Comments | Yes | Managed Code Review posts severity-tagged inline GitHub comments plus a check run; Team/Enterprise only. |
| Quality Gates (Merge Blocking) | No | Check run always completes neutral by design; gating requires parsing the JSON summary line in your own CI. |
| Full Repo Scan | Yes | /claude-security plugin scans a whole codebase; verifier agents confirm findings before reporting. |
| Scheduled Rescans | Yes | Managed Claude Security continuously monitors repositories on a schedule; cron runs also possible via GitHub Actions. |
| Runtime Monitoring | No | Not offered in vendor documentation reviewed as of 2026-09-05. |
Security scanning
1 yes 1 partial 11 no
| Feature | Availability | Description |
|---|---|---|
| SAST | Yes | Agentic security review statically finds injection, SSRF, auth bypass, IDOR and weak crypto in code. |
| Taint Analysis (Data-Flow) | Partial | Managed Claude Security "traces data flows across files" per vendor docs; beta, Enterprise plan only. |
| Secrets Detection | No | Not mentioned in Claude Security, security-guidance, /security-review, or Code Review vulnerability checklists. |
| Secrets Validation | No | Not mentioned anywhere; no capability to verify whether a found secret still works. |
| SCA | No | No native dependency scanning; Anthropic's plugin docs defer supply-chain checks to your existing scanners. |
| Reachability Analysis | No | Not mentioned in any Claude Code security-scanning documentation checked. |
| Malicious Package Detection | No | Claude Security plugin explicitly delegates "supply-chain checks" to external dependency scanners. |
| License Compliance | No | Not documented in Claude Code's security scanning or legal-and-compliance docs. |
| SBOM Generation | No | Not documented in any Claude Code security-scanning page checked. |
| IaC Scanning | No | No Terraform, Kubernetes, or Dockerfile scanning mentioned in any Claude Code security docs. |
| Container Scanning | No | Not documented in any Claude Code security-scanning page checked. |
| CSPM | No | No live cloud-account configuration scanning mentioned in any Claude Code docs. |
| DAST | No | Docs state reviews read "source code in your checkout, not a running site or deployed service." |
Code quality
1 yes 8 no
| Feature | Availability | Description |
|---|---|---|
| Code Smell Detection | Yes | /code-review reports reuse, simplification and efficiency cleanups; managed PR review excludes formatting and style. |
| Complexity Metrics | No | Code Review scopes explicitly to correctness bugs and cleanup suggestions only, per its docs. |
| Duplication Detection | No | Not documented as clone detection; /code-review "reuse" cleanups are adjacent but different. |
| Dead Code Detection | No | Not mentioned in any Claude Code review-product documentation checked. |
| Test Coverage Tracking | No | Code Review explicitly does not flag missing test coverage by default; no coverage measurement documented. |
| Diff Coverage (New Code) | No | Code Review docs explicitly exclude "missing test coverage" from its default checks. |
| Architecture Governance | No | No module-boundary or dependency-direction enforcement mentioned in any Claude Code docs. |
| Technical Debt Quantification | No | No remediation-effort or cost quantification feature mentioned in any Claude Code docs. |
| Behavioral Code Analysis | No | No git-history hotspot, change-coupling, or bus-factor analytics product exists in the docs. |
AI review & fixes
5 yes
| Feature | Availability | Description |
|---|---|---|
| AI Logic Bug Detection | Yes | Parallel agents hunt correctness bugs; a verification step checks findings against actual code behavior. |
| PR Summaries & Walkthroughs | Yes | Review body summary plus severity-sorted check-run Details; REVIEW.md can reshape its format. |
| Autofix Suggestions | Yes | /code-review --fix edits the working tree; /claude-security drafts F<n>.patch files for manual git apply. |
| Autofix Pull Requests | Yes | Opens fix PRs on request; the GitHub Action can commit fixes automatically. |
| AI Triage (False-Positive Filtering) | Yes | Independent verifier agents reproduce findings before reporting, in Code Review, ultrareview and Claude Security. |
Rules & repo support
2 yes
| Feature | Availability | Description |
|---|---|---|
| Custom Rule Authoring | Yes | REVIEW.md, hierarchical CLAUDE.md, and up to 50 custom regex patterns in security-patterns.yaml. |
| Monorepo Support | Yes | Dedicated docs cover per-package CLAUDE.md, sparse worktrees, and per-directory skills for monorepos. |
AI capabilities
4 yes 2 partial 1 no
| Feature | Availability | Description |
|---|---|---|
| AI Code Review | Yes | Entire product is agent-based: parallel reviewer agents on Anthropic infrastructure with independent verification. |
| Bring Your Own Model | Yes | Bring your own key via Console, Bedrock, Vertex, Foundry or LLM gateways; Claude models only. |
| MCP Server | Partial | Consumes MCP servers with first-use trust verification; no MCP server exposing review findings documented. |
| AI Code Governance | No | No AI-generated-code inventory; org analytics cover usage, per-repo cost and spend caps instead. |
| Conversational Review | Yes | Web/desktop diff comments get responses; replying to GitHub Code Review comments does not prompt a reply. |
| Learning From Feedback | Yes | Thumbs up/down reaction counts collected post-merge to tune the reviewer; no immediate re-review. |
| Code Excluded From Training | Partial | Zero Data Retention for qualified Enterprise accounts; no explicit training-exclusion statement in Anthropic's documentation. |
Models used
Claude Opus 4.7
Compliance & governance
3 yes 1 no
| Feature | Availability | Description |
|---|---|---|
| Audit Logs | Yes | Audit logging listed among cloud/web session execution safeguards for Anthropic-managed VMs. |
| SSO (SAML) | Yes | Enterprise plans include SSO identity federation via OIDC. |
| Role-Based Access Control | Yes | Owner/Primary Owner roles gate setup; PR triggers require owner, member or collaborator access. |
| Compliance Reporting & Exports | No | Not offered in vendor documentation reviewed as of 2026-09-05. |
Certifications
SOC 2 Type 2ISO 27001Zero Data Retention (qualified Enterprise accounts)HIPAA compliance configuration (customer-enabled, not a certification)HackerOne vulnerability disclosure program
Integrations
3 yes 5 partial 2 no
| Git provider | Availability |
|---|---|
| GitHub | Yes |
| GitHub Enterprise Server | Yes |
| GitLab | Partial |
| GitLab Self-Managed | Partial |
| Bitbucket | Partial |
| Bitbucket Data Center | No |
| Azure DevOps | No |
| API & CLI | Availability |
|---|---|
| REST API | Partial |
| CLI | Yes |
| Webhooks | Partial |
CI/CD systems
GitHub Actions (anthropics/claude-code-action)GitLab CI/CD (beta, GitLab-maintained)
IDEs
VS CodeIntelliJ IDEAPyCharm
Issue trackers
GitHub Issues
Chat & notifications
Slack (Claude Code in Slack)
Languages
Not limited to a fixed list: Claude Code works with any language its underlying model can read.
Pricing & plans
$17/user/month billed annually ($200 billed upfront) ($20/user/month if billed monthly)
Minimum seats: Not applicable — Pro is an individual plan; Team plan requires 2-150 seats
Free$0Individual, no subscription
- Security guidance plugin not stated as restricted
- Code Review not available
- Ultrareview not available (requires claude.ai account plus plan)
- Claude Security plugin not available (paid plan required)
- Managed Claude Security not available
- Self-hosted environments not available
- Analytics dashboard not available
ProSee claude.com/pricingIndividual subscriber
- Local /code-review and /security-review commands
- Security guidance plugin (all plans)
- Claude Security plugin local scans (Dynamic workflows must be enabled in /config)
- Ultrareview with 3 free one-time runs, then usage credits
- GitHub Actions with Claude subscription auth
- Managed Code Review not available (Team/Enterprise only)
- Managed Claude Security not available
- Self-hosted environments not available
- No analytics dashboard or API
MaxSee claude.com/pricingPower-user individual subscriber
- Everything in Pro
- Higher shared usage allowance on rolling five-hour and weekly windows
- Ultrareview with 3 free one-time runs, then usage credits
- Managed Code Review not available (Team/Enterprise only)
- Managed Claude Security not available
- Self-hosted environments not available
TeamSee claude.com/pricingSmall and mid-size organizations
- Managed Code Review, enabled org-wide by an Owner
- Org-wide GitHub Actions rollout with org-level app install and shared secrets
- Claude Security plugin local scans
- Security guidance plugin
- Self-hosted environments (public beta)
- Code Review analytics dashboard
- Managed Claude Security is Enterprise-gated
- Enterprise Analytics API not included (dashboard only)
- Code Review unavailable if Zero Data Retention is enabled
- Code Review billed via usage credits on top of the subscription
EnterpriseSee claude.com/pricingLarge organizations
- Managed Code Review
- Managed Claude Security continuous repository monitoring
- GitHub Actions with SSO/OIDC federation options
- Self-hosted environments (public beta)
- Code Review dashboard plus Enterprise Analytics API
- Zero Data Retention available for qualified accounts
- Enabling Zero Data Retention disables Code Review, ultrareview and self-hosted environments
- Code Review and ultrareview still bill against usage credits
- HIPAA configuration disables voice dictation and some desktop features
Anthropic Console (API key)standard per-token API ratesAPI-billed organizations and developers
- GitHub Actions
- Claude Security plugin
- Security guidance plugin
- Console dashboard/API for cost tracking
- Code Review not available (requires a claude.ai subscription)
- Ultrareview not available
- No Code Review analytics
Cloud providers (Amazon Bedrock, Claude Platform on AWS, Google Cloud's Agent Platform, Microsoft Foundry)provider per-token ratesCloud-native enterprise deployments
- GitHub Actions on Bedrock, Google Cloud and Foundry
- GitLab CI/CD on Bedrock, Claude Platform on AWS and Google Cloud
- Security guidance plugin
- OIDC workload identity federation, no long-lived cloud credentials
- Code Review not available
- Ultrareview not available
- GitHub Actions unavailable specifically on Claude Platform on AWS
- GitLab CI/CD not available on Microsoft Foundry
- Self-hosted environments not available
Who it's for
Best for teams that write code with Claude and want it reviewed while it is written, before a pull request exists.
A good fit if
- Your developers already work in Claude Code
- You want findings checked by verifier agents before they are reported
- You want review rules written in plain language in a REVIEW.md file
Consider alternatives if
- You need review results to block merges without extra CI work
- Your code is on Bitbucket or Azure DevOps
- You need dependency scanning
Similar tools
Other AI Coding Agent tools in the directory.
FAQ
When should you choose Claude Code?
Claude Code is best for teams that write code with Claude and want it reviewed while it is written, before a pull request exists. It's a good fit if:
- Your developers already work in Claude Code
- You want findings checked by verifier agents before they are reported
- You want review rules written in plain language in a REVIEW.md file
Consider alternatives if:
- You need review results to block merges without extra CI work
- Your code is on Bitbucket or Azure DevOps
- You need dependency scanning
What languages does Claude Code support?
Claude Code isn't limited to a fixed list of languages. It works with any language its underlying model can read.
What does Claude Code integrate with?
Claude Code integrates with:
- Source control: GitHub, GitHub Enterprise Server, GitLab (partial), GitLab Self-Managed (partial) and Bitbucket (partial)
- CI systems: GitHub Actions and GitLab CI/CD
- IDEs: VS Code, IntelliJ IDEA and PyCharm
What tools are similar to Claude Code?
Other AI coding agents tracked here:
What are Claude Code's plans and pricing?
Claude Code's paid plans start at $17/user/mo. Enterprise pricing is by quote.
Opens www.claude.com in a new tab. Review Radar is not affiliated with Anthropic.