sd0x-dev-flow
Prevents AI-generated code from bypassing safety gates during review cycles; enforces dual approval and state persistence across context windows, reducing de…
The harness layer for Claude Code — a reference implementation of harness engineering with hook-enforced dual review, state-machine gates that survive context compaction, and fail-closed safety where it counts. Quality gates that AI can't skip.
- Require dual code review before AI-generated changes merge
- Maintain approval state across Claude context resets
- Block deployment of code failing security gates
Prevents AI-generated code from bypassing safety gates during review cycles; enforces dual approval and state persistence across context windows, reducing deployment risk from incomplete or unvetted changes.
Engineering teams integrating Claude Code into CI/CD pipelines requiring enforced peer review and audit trails.
https://github.com/sd0xdev/sd0x-dev-flow
By sd0xdev
How to Get It
/plugin marketplace add sd0xdev/sd0x-dev-flow then /plugin install sd0x-dev-flow@sd0xdev-marketplace (inside Claude Code); then /project-setup
Tip: Paste this into a Claude Code conversation. Verify command matches your Claude Code version.
After installing, paste this into Claude:
Help me require dual code review before AI-generated changes merge
Trust Signals Reviewed
Community Pulse New
No community discussions found yet. This doesn't mean the tool isn't good — it may be new or serve a niche use case.
Reviewer notes
Reviewed review. These are observations, not a security certification.
Auto-assessment from April sweep — baseline scores pending hands-on review.
2026-04-18: Approved in April sweep: Solid community adoption with a clear description and active maintenance.
Things to check
- Requires integration into existing CI/CD and code review workflows; effectiveness depends on humans actually enforcing gates rather than rubber-stamping approvals. Not a substitute for code review discipline.
- Single maintainer. Consider the risk if this person stops maintaining the project.
How to evaluate tools before deploying →
Data shown here comes from public APIs and automated scanning. Reviewer notes reflect one person's experience. This is not a security certification or legal recommendation. Always evaluate tools according to your own organization's policies.