Skip to content
DevSquad Copilot
This project is under active development and subject to breaking changes. See the changelog for release notes.

Glossary

A

Section titled “A”

ADR (Architecture Decision Record) A document that records a significant technical decision, including context, priorities, options evaluated, and the chosen approach with trade-offs. ADRs follow the lifecycle: Proposed, then Accepted, then Superseded by NNNN. See Decisions.

C

Section titled “C”

Comprehension Checkpoint A verification step triggered before medium or high impact tasks. The agent asks the developer to describe what will happen in their own words, ensuring active understanding rather than passive delegation. Generic responses (“ok”, “go”) trigger deeper questions. See Comprehension Checkpoints.

Conductor The central devsquad agent that detects user intent and delegates to specialist agents. It contains no domain logic, only routing and orchestration. See Conductor.

Conformance Criteria Testable conditions (identified by CC-XXX format) that verify a specification requirement is met. Each includes a scenario, input, and expected output.

Coordinator Agent A specialist agent that delegates internally to focused worker sub-agents with isolated context. The framework has four coordinators: plan, implement, review, and refine.

D

Section titled “D”

Disk Artifacts Versioned files on disk that serve as the source of truth for the framework. Includes spec.md, plan.md, tasks.md, and ADRs. Session context is ephemeral; artifacts persist via git.

H

Section titled “H”

Handoff Envelope A structured context-passing contract between agent phases (ADR 0003). Contains four sections: relevant artifacts, inherited assumptions, pending decisions, and discarded information. See Reasoning and Handoff.

I

Section titled “I”

IDD (Intent-Driven Development) The methodology that structures vision, specification, and architecture decisions before code generation. Built on three pillars: Intent (Why), Specification (What), and Architecture Decisions (How). IDD is the overarching methodology. SDD (Spec-Driven Development) describes the execution model within it, where specifications drive all downstream work.

Impact Classification A three-level system for classifying changes before acting. Low (typo, log) means direct action. Medium (function change) means plan + confirm. High (service, API, schema) means ADR + explicit approval. See Impact Classification.

M

Section titled “M”

MCP (Model Context Protocol) A protocol for providing tools to AI agents. MCP servers expose capabilities (GitHub, Azure DevOps, Azure, Microsoft Learn, Draw.io) that agents call to interact with external systems. See MCP Servers.

O

Section titled “O”

OWASP Open Worldwide Application Security Project. The framework references OWASP guidelines for code-level security assessment.

Q

Section titled “Q”

Quality Gate An automated validation checkpoint that verifies artifact completeness and consistency before delivery. Applied to specs, ADRs, task decompositions, and code implementations.

R

Section titled “R”

Reasoning Log A record of decisions made during agent execution. Each entry includes: the decision, principles applied, alternatives considered, justification, and confidence level (High/Medium/Low). Used for auditability and handoff between phases. See Reasoning and Handoff.

S

Section titled “S”

SDD (Spec-Driven Development) The development approach where specifications drive all downstream work: planning, decomposition, implementation, and review. Specifications define WHAT and WHY; implementation artifacts define HOW.

Socratic AI An adaptive approach where agents ask clarifying questions, surface trade-offs, and present options rather than making autonomous decisions. Low-impact tasks are fast-tracked; high-impact tasks require comprehension verification. Based on ADR 0005.

Specialist Agent An agent that owns the logic for a specific delivery phase (e.g., devsquad.specify for specifications, devsquad.implement for code). Can be invoked directly or through the conductor.

STRIDE A threat modeling methodology (Spoofing, Tampering, Repudiation, Information Disclosure, Denial of Service, Elevation of Privilege) used by the security review process.

T

Section titled “T”

Tool Extension A mechanism for injecting MCP server tools into existing plugin agents via YAML patches (Preview, ADR 0010). Consumer creates .github/devsquad/tool-extensions/*.yml, and a sync script generates workspace-level agent overrides.

W

Section titled “W”

Worker Sub-agent A specialized agent invoked by a coordinator agent to perform a focused subtask in an isolated context window. Workers return results to the coordinator and do not interact with the user directly.

Section titled “What to Read Next”