lattice plugin
Composable AI skills covering the full software delivery lifecycle — for backend engineers, frontend engineers, QA, BAs, and more. Install once, invoke the skills you need.
How to install the lattice plugin
Run both commands inside Claude Code. The first adds the marketplace once; the second installs the plugin.
/plugin marketplace add techygarg/lattice
/plugin install lattice@latticeWhat's inside lattice
28 parts read from the plugin's own files.
Agents 1
Call as @agent-lattice:name- @agent-lattice:verifier
No description in the file.
Skills 27
Claude loads it when the task matches- architecture
Enforces architectural rules and validates design patterns during code generation and structural reviews.
- architecture-compass
Scans codebases to conduct architectural audits, identify drift or mismatches, and produce structured insights and recommended directions.
- architecture-refiner
Facilitates a structured conversation to define and document repository architecture principles and styles.
- bug-fix
Investigates, reproduces, and repairs software bugs using a structured workflow that prioritizes regression testing and architectural integrity.
- clean-code
Enforces coding standards such as single responsibility, naming clarity, and complexity management when generating or modifying implementation code.
- clean-code-refiner
Facilitates a structured interview to define and document repository-specific clean code principles and coding standards.
- code-forge
Generates implementation code from design blueprints or verbal requirements using an inside-out workflow focused on architecture and clean code.
- collaborative-judgment
Provides a protocol for agents to identify, surface, and resolve ambiguous decisions or conflicting information during technical tasks.
- context-anchoring
Manages per-feature living documents to capture technical decisions, constraints, and reasoning across AI development sessions.
- ddd-refiner
Facilitates a structured conversation to define Domain-Driven Design guardrails and generates a formal principles document for repository standards.
- design-blueprint
Executes a structured five-level design workflow from initial context establishment to an approved architectural blueprint.
- design-first
Guides structured design thinking through five progressive levels from capabilities to implementation to ensure architectural alignment before coding.
- domain-driven-design
Apply tactical DDD patterns to design and validate domain models, aggregates, entities, and value objects while preventing common anti-patterns.
- knowledge-priming
Loads project-specific context including tech stack, architecture, and directory layout to provide ambient awareness for all agent skills.
- knowledge-priming-refiner
Facilitates a structured conversation to create a project-specific knowledge base document that primes AI with technical context and architecture.
- language-idioms-refiner
Facilitates a structured interview to define language-specific idioms and patterns, producing a markdown document for project-wide standardization.
- lattice-init
Scans repositories to detect project stacks, identifies outdated configurations, and guides the setup or upgrade of Lattice project standards.
- learning-harvest
Manages the operational learnings lifecycle by loading prior insights, harvesting new patterns from sessions, and maintaining document density.
- refactor-safely
Restructures existing code safely using a characterization-first workflow to improve architecture and quality without changing observable behavior.
- refiners-update
Updates existing Lattice standards documents by coordinating refiner skills to revise content and recording git-native change notes.
- requirement-forge
Generates structured feature specifications through a collaborative product interview acting as a senior PM and business analyst.
- requirement-forge-refiner
Facilitates a structured interview to define project requirement standards and generates a markdown configuration file for automated enforcement.
- requirement-quality
Validates and generates feature specifications by enforcing completeness, scenario structure, and acceptance criteria verifiability.
- review
Performs structured code reviews by conditionally loading specialized validation frameworks based on the scope of code changes.
- review-refiner
Facilitates a structured conversation to configure review process standards, including atom loading, severity levels, and report formats.
- secure-coding
Enforces security-conscious coding practices including input validation, injection prevention, and secrets management during code generation.
- test-quality
Apply test quality principles when generating or reviewing test code. Enforces Arrange-Act-Assert structure, one behavior per test, assertion quality, test isolation, meaningful naming, and test data management. Use when writing tests, reviewing test code, or when the user mentions 'write tests', 'test this', 'test quality', 'test review', 'improve tests', or 'test structure'. Loaded automatically by the code-generating molecules (code-forge, refactor-safely, bug-fix). This skill governs the craft of writing individual test cases -- not what to test (that is driven by the code being implemented) but how to write tests that are reliable, readable, and maintainable.
Using lattice in Claude Code
Ask for an agent by name:
@agent-lattice:verifierSkills need no command. Claude reads them when your request matches what they describe.
Update, turn off or remove
- Update the plugin (shell)
- claude plugin update lattice@lattice
- Refresh the marketplace
- /plugin marketplace update lattice
- Turn it off for now
- /plugin disable lattice@lattice
- Remove it
- /plugin uninstall lattice@lattice
Skills in lattice
- architecturetechygarg/lattice
Enforces architectural rules and validates design patterns during code generation and structural reviews.
4 files211stars - architecture-compasstechygarg/lattice
Scans codebases to conduct architectural audits, identify drift or mismatches, and produce structured insights and recommended directions.
2 files211stars - architecture-refinertechygarg/lattice
Facilitates a structured conversation to define and document repository architecture principles and styles.
3 files211stars - clean-codetechygarg/lattice
Enforces coding standards such as single responsibility, naming clarity, and complexity management when generating or modifying implementation code.
2 files211stars - clean-code-refinertechygarg/lattice
Facilitates a structured interview to define and document repository-specific clean code principles and coding standards.
2 files211stars - context-anchoringtechygarg/lattice
Manages per-feature living documents to capture technical decisions, constraints, and reasoning across AI development sessions.
2 files211stars - ddd-refinertechygarg/lattice
Facilitates a structured conversation to define Domain-Driven Design guardrails and generates a formal principles document for repository standards.
2 files211stars - design-firsttechygarg/lattice
Guides structured design thinking through five progressive levels from capabilities to implementation to ensure architectural alignment before coding.
2 files211stars - domain-driven-designtechygarg/lattice
Apply tactical DDD patterns to design and validate domain models, aggregates, entities, and value objects while preventing common anti-patterns.
2 files211stars - knowledge-priming-refinertechygarg/lattice
Facilitates a structured conversation to create a project-specific knowledge base document that primes AI with technical context and architecture.
2 files211stars - language-idioms-refinertechygarg/lattice
Facilitates a structured interview to define language-specific idioms and patterns, producing a markdown document for project-wide standardization.
2 files211stars - lattice-inittechygarg/lattice
Scans repositories to detect project stacks, identifies outdated configurations, and guides the setup or upgrade of Lattice project standards.
2 files211stars - requirement-forgetechygarg/lattice
Generates structured feature specifications through a collaborative product interview acting as a senior PM and business analyst.
2 files211stars - requirement-forge-refinertechygarg/lattice
Facilitates a structured interview to define project requirement standards and generates a markdown configuration file for automated enforcement.
2 files211stars - requirement-qualitytechygarg/lattice
Validates and generates feature specifications by enforcing completeness, scenario structure, and acceptance criteria verifiability.
2 files211stars - review-refinertechygarg/lattice
Facilitates a structured conversation to configure review process standards, including atom loading, severity levels, and report formats.
2 files211stars - secure-codingtechygarg/lattice
Enforces security-conscious coding practices including input validation, injection prevention, and secrets management during code generation.
2 files211stars - test-qualitytechygarg/lattice
Apply test quality principles when generating or reviewing test code. Enforces Arrange-Act-Assert structure, one behavior per test, assertion quality, test isolation, meaningful naming, and test data management. Use when writing tests, reviewing test code, or when the user mentions 'write tests', 'test this', 'test quality', 'test review', 'improve tests', or 'test structure'. Loaded automatically by the code-generating molecules (code-forge, refactor-safely, bug-fix). This skill governs the craft of writing individual test cases -- not what to test (that is driven by the code being implemented) but how to write tests that are reliable, readable, and maintainable.
2 files211stars - bug-fixtechygarg/lattice
Investigates, reproduces, and repairs software bugs using a structured workflow that prioritizes regression testing and architectural integrity.
211stars - code-forgetechygarg/lattice
Generates implementation code from design blueprints or verbal requirements using an inside-out workflow focused on architecture and clean code.
211stars - collaborative-judgmenttechygarg/lattice
Provides a protocol for agents to identify, surface, and resolve ambiguous decisions or conflicting information during technical tasks.
211stars - design-blueprinttechygarg/lattice
Executes a structured five-level design workflow from initial context establishment to an approved architectural blueprint.
211stars - knowledge-primingtechygarg/lattice
Loads project-specific context including tech stack, architecture, and directory layout to provide ambient awareness for all agent skills.
211stars - learning-harvesttechygarg/lattice
Manages the operational learnings lifecycle by loading prior insights, harvesting new patterns from sessions, and maintaining document density.
211stars - refactor-safelytechygarg/lattice
Restructures existing code safely using a characterization-first workflow to improve architecture and quality without changing observable behavior.
211stars - refiners-updatetechygarg/lattice
Updates existing Lattice standards documents by coordinating refiner skills to revise content and recording git-native change notes.
211stars - reviewtechygarg/lattice
Performs structured code reviews by conditionally loading specialized validation frameworks based on the scope of code changes.
211stars
lattice plugin questions
How do I install the lattice plugin?
In Claude Code run /plugin marketplace add techygarg/lattice, then /plugin install lattice@lattice.
What does the lattice plugin include?
lattice bundles 1 agent, 27 skills.
Which agents come with lattice?
verifier. Call one with @agent-lattice:verifier.
How do I update or remove the lattice plugin?
Update it with claude plugin update lattice@lattice in your shell, or from the Installed tab of /plugin. Remove it with /plugin uninstall lattice@lattice.