README.md
April 9, 2026 Β· View on GitHub
π Read in: English | EspaΓ±ol | PortuguΓͺs
Don Cheli β SDD Framework
Stop guessing. Start engineering.
The only framework where TDD is law, not a suggestion.
One command. Verified code.
/dc:auto "Implement JWT authentication with refresh tokens"
Don Cheli takes your idea and delivers tested, reviewed, verified code β automatically.
β
/dc:specify 8 Gherkin scenarios generated
β
/dc:clarify 2 ambiguities resolved
β
/dc:tech-plan Blueprint: 3-layer architecture
β
/dc:breakdown 7 TDD tasks created
β
/dc:implement 14 tests pass, 91% coverage
β
/dc:review 7/7 review dimensions passed
Result: ALL PASSED β Project updated with verified code
Your project is untouched until everything passes. If anything fails, nothing changes.
Install
npm install -g don-cheli-sdd
don-cheli install --global
Other install methods
# Git clone
git clone https://github.com/doncheli/don-cheli-sdd.git
cd don-cheli-sdd && bash scripts/instalar.sh
# One liner
curl -fsSL https://raw.githubusercontent.com/doncheli/don-cheli-sdd/main/scripts/instalar.sh | bash -s -- --global --lang en
# VS Code Extension
code --install-extension doncheli.don-cheli-sdd
The Runtime β Your code never breaks
Other frameworks give you prompts and hope the AI follows them. Don Cheli has a real TypeScript orchestrator that makes it impossible to skip rules.
How it works in 4 steps:
Step 1: The runtime creates a copy of your project (git worktree). Your real project is never touched.
Step 2: It spins up a Docker container and runs each /dc:* command inside β completely isolated.
Step 3: After each phase, real quality gates verify the output:
- Does the Gherkin spec exist? Does it have P1 scenarios?
- Do tests exist? Do they pass? Are there zero
// TODOstubs? - Is coverage >= 85%?
- Do your custom rules in
.dc/gates/*.ymlpass?
Step 4: Only when ALL 6 phases pass ALL gates does the code merge into your project. If anything fails β your project stays exactly as it was.
3 providers: Use your Claude Code subscription (free), OpenAI Codex, or Ollama for 100% free local execution.
How it works
flowchart LR
P["π PRD"] -.->|optional| B
A["π‘ Idea"] --> B["/dc:specify"]
B --> C["/dc:clarify"]
C --> D["/dc:tech-plan"]
D --> E["/dc:breakdown"]
E --> F["/dc:implement"]
F --> G["/dc:review"]
G --> H["β
Verified"]
style P fill:#2d3436,color:#dfe6e9,stroke:#6c5ce7,stroke-dasharray: 5 5
style F fill:#e17055,color:#fff
style H fill:#00b894,color:#fff
| Phase | Command | What happens |
|---|---|---|
| Specify | /dc:specify | Your idea β Gherkin specs with test scenarios |
| Clarify | /dc:clarify | QA finds ambiguities before you code |
| Plan | /dc:tech-plan | Architecture + API contracts + schema |
| Break Down | /dc:breakdown | TDD tasks with parallelism markers |
| Implement | /dc:implement | Test FIRST β code β refactor (Iron Law) |
| Review | /dc:review | 7-dimension peer review |
Each phase has a quality gate. You don't advance without passing. No shortcuts.
3 ways to use it
# Interactive β you drive each phase
/dc:start "JWT auth"
# Autonomous β runtime drives everything, Docker isolates
/dc:auto "JWT auth"
# Terminal β without AI agent open
don-cheli auto "JWT auth"
The Iron Laws
These are not suggestions. The runtime enforces them.
| Law | Rule | Enforcement |
|---|---|---|
| TDD | No code without tests | Blocks merge if tests don't exist |
| No Stubs | No // TODO in production | Scans and rejects |
| Evidence | Proof, not promises | Coverage >= 85% verified |
Why Don Cheli
93 commands Β· 51 skills Β· 15 reasoning models Β· 9 IDEs Β· 3 languages
The only SDD framework with all of these:
- β TDD as unbreakable law (not optional)
- β Autonomous mode with Docker isolation
- β OWASP security audit in the pipeline
- β 15 reasoning models (Pre-mortem, 5 Whys, Pareto, RLM...)
- β PRD Generator (reads Figma designs)
- β Pre-flight cost simulation
- β Crash recovery (resume where you left off)
- β Custom quality gates (YAML plugins)
- β Drift detection (spec vs code watcher)
- β SDD Certification badges
- β Works with Claude, Cursor, Gemini, Codex, OpenCode, Qwen, Amp, Windsurf
- β ES / EN / PT
Platforms
| Platform | Install | Details |
|---|---|---|
| Claude Code | --tools claude | 93 /dc:* commands (full native) |
| OpenCode | --tools opencode | 28 /doncheli-* slash commands + 28 skills |
| Antigravity | --tools antigravity | GEMINI.md + .agent/skills/ |
| Cursor | --tools cursor | .cursorrules |
| Codex / Qwen | --tools codex | AGENTS.md |
Community
License
Apache 2.0 β Copyright 2026 Jose Luis Oronoz Troconis (@DonCheli)
Made with β€οΈ in Latin America β Don Cheli SDD Framework