A guardian's song for your code — orchestrating workflows so nothing is left behind.
Define multi-stage delivery pipelines as declarative YAML. A 4-layer agent hierarchy watches over every task with quality gates, so your code is never unprotected.
# Cursor (project-local)
curl -fsSL https://raw.githubusercontent.com/YoRHa-Agents/DevolaFlow/main/scripts/install.sh | bash -s cursor
# Cursor (user-global, shared across all projects)
curl -fsSL https://raw.githubusercontent.com/YoRHa-Agents/DevolaFlow/main/scripts/install.sh | bash -s cursor --global
# Claude Code (user-global)
curl -fsSL https://raw.githubusercontent.com/YoRHa-Agents/DevolaFlow/main/scripts/install.sh | bash -s claude --global
# Update existing install to latest version
curl -fsSL https://raw.githubusercontent.com/YoRHa-Agents/DevolaFlow/main/scripts/install.sh | bash -s update
Also:
... | bash -s claude ·
... | bash -s claude --global ·
... | bash -s copilot ·
... | bash -s all ·
... | bash (auto-detect)
Or just download MVP-SKILL.md and drop it into your tool.
Pick the right workflow for your task. Each is a different composition of the same 13 stage primitives.
| Workflow | When to use | Stages |
|---|---|---|
| full-pipeline | New feature, greenfield project | design - plan - impl - review - test - refine - gate - release |
| hotfix | Production bug, urgent fix | triage - fix - test - release |
| refactoring | Tech debt, restructure | scope - plan - impl - test - review |
| research-only | Compare alternatives, survey | research - compare - report |
| design-only | Architecture, API design | research - design - review |
| migration | Upgrade, port systems | assess - plan - impl - validate - cutover |
| spike-poc | Prototype, experiment | research - prototype - evaluate |
| documentation | Docs, guides, API refs | survey - author - review |
| security-audit | Vulnerability scan | threat - scan - analyze - remediate - verify |
| feature-enhancement | Extend existing features | scope - design - plan - impl - review - test - release |
| RDRR | Design with research | research - design - review - refine (loop) |
| demo-showcase | Build demo, presentation, pitch | research - storyboard - build - review - polish - package |
| performance-optimization | Profile, benchmark, optimize speed | profile - design - optimize - benchmark - validate |
| dependency-setup | Environment, install, configure tools | research - plan - configure - verify |
| onboarding | New contributor, codebase survey | analyze - document - setup - verify |
| skill-optimization | Optimize agent skill, benchmark context | survey - profile - optimize - benchmark - iterate - document |
| self-update | Skill refresh, upstream sync | check-refs - research-updates - decompose - integrate - test - evaluate |
NineS CLI integration, self-improvement loops, and Karpathy-inspired behavioral norms bring DevolaFlow to a new level of autonomous quality.
Full CLI migration with 6 breaking changes resolved. Self-improvement loop infrastructure: self-eval, iterate, and benchmark in a unified pipeline.
GitHub →NineS-guided complexity reduction brought select_context cyclomatic complexity from 23 to 7. NineS findings reduced from 7 to 0 across the codebase.
View Results →Explicit assumptions documentation, simplicity review gates, and anti-complexity checks inspired by Andrej Karpathy's software engineering principles.
Read More →25 EvoBench scenarios (avg 99.50), 18 context profiles, 18 reference dependencies tracked. Quality gates hold the line — just as Devola would.
View Results →DevolaFlow adapts to four AI coding tools from a single source. Run make build-skill and copy the output.
Full SKILL.md + references + rules. Copy dist/cursor/ to .cursor/skills/devola-flow/
SKILL.md with inline rules + openai.yaml. Copy dist/codex/ to ~/.codex/skills/
Compressed CLAUDE.md (<200 lines). Copy dist/claude/CLAUDE.md to project root.
Copilot instructions (<4K chars). Copy dist/copilot/.github/ to your repo.