devpace
Bridges business objectives to engineering execution by mapping goals through code changes, reducing misalignment between product roadmaps and actual delivery.
Claude Code plugin that adds a development harness — rules, schemas, quality gates, and feedback loops — to keep AI-assisted development traceable and measurable. It builds a goal-to-code traceability chain: every change links back to a business goal, quality gates require human approval, requirement changes trigger automatic impact analysis, and interrupted sessions auto-resume from state stored as plain Markdown in .devpace/. Nineteen /pace-* commands cover init, dev, status, review, planning, business alignment, and release.
- Trace feature request from product roadmap to merged pull requests
- Identify sprints where velocity dropped to diagnose process friction
- Validate that engineering effort matches business priority weighting
Bridges business objectives to engineering execution by mapping goals through code changes, reducing misalignment between product roadmaps and actual delivery. Surfaces velocity patterns that expose bottlenecks in planning or execution.
Engineering leads and architects who need to validate that sprint work tracks against quarterly OKRs and want visibility into delivery cadence across teams.
https://github.com/arch-team/devpace
By arch-team
How to Get It
/plugin marketplace add arch-team/devpace-marketplace /plugin install devpace@devpace
After installing, paste this into Claude:
Help me trace feature request from product roadmap to merged pull requests
Trust Signals Auto-scanned
Reviewer notes
Auto-scanned review. These are observations, not a security certification.
catalog_hygiene stale-eval refresh: Scored from trust signals (evidence-eval-v1): 73 GitHub stars; 1 contributors; last commit 120d ago; license MIT.
Things to check
- Scanned, not hands-on tested — this entry was auto-scanned from public metadata (GitHub metrics, license, security flags). No reviewer has run it, and no tool-specific limitations have been documented yet.
- 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.
Evaluation
catalog_hygiene stale-eval refresh: Scored from trust signals (evidence-eval-v1): 73 GitHub stars; 1 contributors; last commit 120d ago; license MIT.