openspecSpec-driven development with OpenSpec CLI. Use when building features, migrations, refactors, or any structured development work. Manages proposal ā specs ā design ā tasks ā implementation workflows. Supports custom schemas (TDD, rapid, etc.). Trigger on requests involving feature planning, spec writing, change management, or when /opsx commands are mentioned.
Install via ClawdBot CLI:
clawdbot install jcorrego/openspecOpenSpec structures AI-assisted development into trackable changes with artifacts (proposal, specs, design, tasks) that guide implementation.
# Install globally
npm install -g @fission-ai/openspec@latest
# Initialize in a project
cd /path/to/project
openspec init --tools claude
# Update after CLI upgrade
openspec updateEach change follows: new ā plan ā apply ā verify ā archive
# Create change folder with default schema
openspec new change <name>
# With specific schema
openspec new change <name> --schema tdd-drivenUse the CLI instructions command to get enriched prompts for each artifact:
# Get instructions for next artifact
openspec instructions --change <name> --json
# Check progress
openspec status --change <name> --jsonArtifact sequence (spec-driven schema):
proposal.md ā Why and what (intent, scope, approach)specs/ ā Requirements + scenarios (Given/When/Then)design.md ā Technical approach and architecture decisionstasks.md ā Implementation checklist with checkboxesRead tasks.md and work through items, marking [x] as complete.
openspec validate --change <name> --jsonChecks completeness, correctness, and coherence.
openspec archive <name> --yesMerges delta specs into main openspec/specs/ and moves change to archive.
When the user asks to build/migrate/refactor something with OpenSpec:
openspec list --json # Active changes
openspec list --specs --json # Current specs
openspec schemas --json # Available schemas
openspec new change <name> [--schema <schema>]
openspec instructions <artifact> --change <name> --json
openspec status --change <name> --json Then write the artifact file to openspec/changes/.
tasks.md.
openspec validate <name> --json
openspec archive <name> --yes| Command | Purpose |
|---------|---------|
| openspec list [--specs] [--json] | List changes or specs |
| openspec show | Show change/spec details |
| openspec status --change | Artifact completion status |
| openspec instructions [artifact] --change | Get enriched creation instructions |
| openspec validate [name] [--all] [--json] | Validate changes/specs |
| openspec archive | Archive completed change |
| openspec schemas [--json] | List available schemas |
| openspec templates [--json] | Show template paths |
| openspec config | View/modify settings |
Always use --json for programmatic/agent use.
Schemas define artifact sequences. Create custom ones for different workflows:
# Fork built-in schema
openspec schema fork spec-driven my-workflow
# Create from scratch
openspec schema init my-workflow
# Validate
openspec schema validate my-workflowSchema files live in openspec/schemas/ with templates in templates/.
For schema structure details, see references/schemas.md.
project/
āāā openspec/
ā āāā config.yaml # Project config (default schema, context, rules)
ā āāā specs/ # Source of truth ā current system behavior
ā āāā changes/ # Active changes (one folder each)
ā ā āāā <change-name>/
ā ā āāā .openspec.yaml
ā ā āāā proposal.md
ā ā āāā specs/ # Delta specs (what's changing)
ā ā āāā design.md
ā ā āāā tasks.md
ā āāā schemas/ # Custom schemas
āāā .claude/skills/ # Auto-generated Claude integrationSpecs use RFC 2119 keywords (SHALL/MUST/SHOULD/MAY) with Given/When/Then scenarios:
### Requirement: User Authentication
The system SHALL issue a JWT token upon successful login.
#### Scenario: Valid credentials
- GIVEN a user with valid credentials
- WHEN the user submits login form
- THEN a JWT token is returnedChanges don't rewrite specs ā they describe deltas (ADDED/MODIFIED/REMOVED) that merge into main specs on archive.
openspec/config.yaml sets defaults:
schema: spec-driven # or tdd-driven, rapid, custom
context: |
Tech stack: TypeScript, React, Node.js
Testing: Jest
rules:
proposal:
- Include rollback plan
specs:
- Use Given/When/Then formatGenerated Mar 1, 2026
A cross-functional team uses OpenSpec to manage feature development sprints. They create changes for each user story, generating structured artifacts like proposals and specs to ensure alignment before coding. This reduces rework and improves traceability from requirements to implementation.
A DevOps team adopts OpenSpec to plan and execute a cloud migration from on-premises servers. They define changes for each service migration, using design artifacts to document architecture decisions and tasks to track deployment steps, ensuring minimal downtime and compliance with security specs.
An e-commerce company uses OpenSpec to refactor its legacy checkout system. They create changes for modularizing components, with specs detailing new payment flows and tasks outlining incremental updates. This helps maintain business continuity while modernizing the codebase.
A healthcare software provider leverages OpenSpec to handle regulatory updates like HIPAA changes. They initiate changes for each compliance requirement, using proposal artifacts to justify changes and specs to define exact behaviors, ensuring audit trails and adherence to standards.
Agencies use OpenSpec to standardize client project workflows, charging per change or on a subscription basis for spec-driven development services. It improves project transparency and reduces scope creep, leading to higher client retention and predictable revenue.
Consultants integrate OpenSpec into digital transformation engagements, offering it as a value-add for structured change management. Revenue comes from licensing, training, and support services, helping large organizations streamline development processes and reduce risks.
Developers build and monetize custom schemas or plugins for OpenSpec, selling them through marketplaces or offering premium support. This fosters a community-driven model where revenue is generated from extensions, certifications, and enterprise features.
š¬ Integration Tip
Integrate OpenSpec into existing CI/CD pipelines by running validation commands in build stages to ensure spec compliance before deployment.
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
Provides a 7-step debugging protocol plus language-specific commands to systematically identify, verify, and fix software bugs across multiple environments.
A comprehensive skill for using the Cursor CLI agent for various software engineering tasks (updated for 2026 features, includes tmux automation guide).
Write, run, and manage unit, integration, and E2E tests across TypeScript, Python, and Swift using recommended frameworks.
Control and operate Opencode via slash commands. Use this skill to manage sessions, select models, switch agents (plan/build), and coordinate coding through Opencode.
Coding style memory that adapts to your preferences, conventions, and patterns for consistent coding.