JSPM

Context Engineering & Harness Engineering Toolkit for Claude Code

Structured prompts, agent orchestration, and automated pipelines — debugging, code review, UI design, product specs, and more.

Get Started · Commands · Skills · Workflows · Optional Packs · Contributing

Why devlyn-cli?

Claude Code is powerful out of the box — but teams need consistent, repeatable workflows. Without shared conventions, every developer prompts differently, reviews differently, and debugs differently.

devlyn-cli solves this with two complementary engineering approaches:

Context Engineering

Structured prompts and role-based instructions that shape what the AI knows and how it thinks for each task.

• 16 slash commands for debugging, code review, UI design, documentation, and more
• 5 core skills that activate automatically based on conversation context
• Agent team workflows that spawn specialized AI teammates with role-specific expertise
• Product & feature spec templates for structured planning

Harness Engineering

Pipeline orchestration that controls how agents execute — permissions, state management, multi-phase workflows, and cross-model evaluation.

• /devlyn:auto-resolve — 9-phase automated pipeline (build → browser validate → evaluate → fix loop → simplify → review → security → clean → docs)
• /devlyn:browser-validate — feature verification in a real browser with tiered fallback (Chrome MCP → Playwright → curl)
• bypassPermissions mode for autonomous subagent execution
• File-based state machine — agents communicate via .devlyn/done-criteria.md, EVAL-FINDINGS.md, and BROWSER-RESULTS.md
• Git checkpoints at each phase for rollback safety
• Cross-model evaluation via --with-codex flag (OpenAI Codex as independent evaluator)

Zero dependencies. One command. Works with any project.

Get Started

npx devlyn-cli

The interactive installer walks you through setup — select optional skills, choose community packs, done.

# Non-interactive install (CI/CD friendly)
npx devlyn-cli -y

# Update to the latest version
npx devlyn-cli@latest

# See everything that's included
npx devlyn-cli list

What Gets Installed

your-project/
├── .claude/
│   ├── commands/              # 16 slash commands
│   ├── skills/                # 5 core skills + any optional addons
│   ├── templates/             # Product spec, feature spec, prompt templates
│   ├── commit-conventions.md  # Commit message standards
│   └── settings.json          # Agent teams enabled
└── CLAUDE.md                  # Project-level AI instructions

Commands

Slash commands are invoked directly in Claude Code conversations (e.g., type /devlyn:resolve).

Debugging & Resolution

Code Review & Quality

UI Design & Implementation

Product & Planning

Documentation

Skills

Skills are not invoked manually — they activate automatically when Claude Code detects a relevant conversation context. Think of them as always-on expertise that shapes how the AI approaches specific types of work.

Workflows

Commands are designed to compose. Pick the right tool based on scope, then chain them together.

Automated Pipeline (Recommended)

One command runs the full cycle — no human intervention needed:

/devlyn:auto-resolve fix the auth bug where users see blank screen on 401

Each phase runs as a separate subagent (fresh context), communicates via files, and commits a git checkpoint for rollback safety. Skip phases with flags: --skip-browser, --skip-review, --skip-clean, --skip-docs, --max-rounds 3, --with-codex (cross-model evaluation via OpenAI Codex).

Manual Workflow

For step-by-step control between phases:

Steps 5-6 are optional — run them periodically rather than on every PR.

Scope matching matters. For a simple one-file bug, /devlyn:resolve + /devlyn:review (solo) is fast. For a multi-module feature, /devlyn:auto-resolve handles everything. Don't over-tool simple changes.

UI Design Pipeline

A full explore → extract → build pipeline:

For design exploration with a full creative team, use /devlyn:team-design-ui instead of step 1.

After building, follow the recommended workflow starting from step 2 (simplify) to review and polish the implementation.

Standalone Tools

These commands work independently, outside of the main workflow:

Optional Skills & Packs

During installation, the interactive selector lets you add optional skills and community packs.

Skills

Copied directly into your .claude/skills/ directory.

Community Packs

Installed via the skills CLI (npx skills add). These are maintained by their respective communities.

MCP Servers

Installed via claude mcp add during setup.

Want to add a pack? Open a PR adding your pack to the OPTIONAL_ADDONS array in bin/devlyn.js.

How It Works

1. Run npx devlyn-cli in your project root
2. The CLI copies config files into .claude/ and CLAUDE.md to the project root
3. Claude Code automatically reads .claude/commands/ and .claude/skills/ on startup
4. Invoke commands like /devlyn:resolve in your Claude Code session — skills activate on their own

The installation is idempotent — run it again anytime to update to the latest config.

Creating Your Own Skills

Want to author custom skills for your team or the community?

1. During install, select the generate-skill optional skill — or —
2. Install the official Anthropic skill-creator pack:

   npx skills add anthropics/skills

Both provide structured templates, best practices, and eval frameworks for writing high-quality Claude Code skills.

See the Claude Code skills documentation for the full specification.

Requirements

• Node.js 18+
• Claude Code CLI installed and configured

Contributing

Contributions are welcome! Here are some ways to get involved:

• Add a command — Create a new .md file in config/commands/
• Add a skill — Create a new directory in config/skills/ with a SKILL.md
• Add an optional skill — Add to optional-skills/ and the OPTIONAL_ADDONS array
• Suggest a community pack — Open a PR to add it to the pack list

Development

1. Fork the repository
2. Create your branch (git checkout -b feat/my-feature)
3. Commit your changes following the included commit conventions
4. Push to the branch (git push origin feat/my-feature)
5. Open a Pull Request

Star History

License

MIT — Donut Studio