--- title: "spec-plugin" description: "Spec-driven project execution pipeline, from ideation to verified deliverables, orchestrated by AI agents. Works with any project type. Built on a team of subagents plus a tool-use hook, so it needs an agent that can run" canonical: https://agentpluginsdirectory.com/plugins/spec-plugin last-updated: 2026-09-22 --- # spec-plugin Spec-driven project execution pipeline, from ideation to verified deliverables, orchestrated by AI agents. Works with any project type. Built on a team of subagents plus a tool-use hook, so it needs an agent that can run plugin-provided subagents and hooks. - Slug: spec-plugin - Publisher: Jaison Erick - Repository: https://github.com/nexaedge/nexaedge-marketplace - Manifest: plugins/spec-plugin/plugin.json - Version: v15 - Category (editorial): agent-tooling - Skills: 15 (architect-version, architect, assess-effectiveness, audit-dod, build-stories, execute-task, explore-conventions, ideate, orchestrate, plan, probe-contract, setup-env, trace-flow, validate-execution, verify-symbol) - MCP servers: 0 - Stars: 1 - Repository created: 2026-03-05 - Repository last pushed: 2026-09-16 - Publisher type: Organization - Listing: https://agentpluginsdirectory.com/plugins/spec-plugin - Schema: https://agent-plugins.org/schemas/1.0.0/plugin.schema.json ## What spec-plugin does, in the publisher's words A Claude Code plugin for spec-driven project execution. Provides a complete pipeline from ideation to verified, shipped deliverables, orchestrated by AI agents. Works with any project type: code, business, research, consulting. The orchestrator coordinates a living team per version: - A fresh, independent auditor gates the Definition of Done before any story is built, so a version isn't built against a DoD that measures the wrong thing. - The product-owner and a single QA stay live the whole session; engineers are spawned fresh per story (re-warmed by a preloaded story + context.md + lessons.md, not carried context). - A setup-playbook, shared context.md, and a running lessons.md are prepared up front, so engineers read those instead of re-loading the full architecture. A version ships when the human confirms its Definition of Done is met. From the project README, punctuation lightly normalized. Full text: https://raw.githubusercontent.com/nexaedge/nexaedge-marketplace/HEAD/plugins/spec-plugin/README.md ## Skills - architect-version: Deep-dive architecture for a single version. Reads the version spec, overall architecture, roadmap, and related versions, then produces a comprehensive architecture document with specific implementation choices. Adapts to project type. Use before /build-stories. - architect: Create the implementation approach for a project. For code projects: technology stack, schemas, API contracts, system design. For non-code projects: delivery approach, document structure, resource plan. Adapts based on the project spec. Use after /ideate. - assess-effectiveness: Assess how the LATEST spec-plugin version is performing across every previous session that invoked it, aggregate run efficiency (thinking%, compactions, exploration-vs-skills, preload firing, fresh-per-story), process adherence, and recurring spec-quality issues, then propose concrete, evidence-b… - audit-dod: Independently audit a version's Definition of Done, does it measure behavior or an artifact, before any code is built. Reads the version's DoD and intent fresh, scores it against a 5-point rubric, and reports PASS or specific gaps. - build-stories: Break down a single version into executable story files. Reads the version spec, architecture, and roadmap, then creates ordered stories. Adapts to project type: code stories for engineers, deliverable stories for any project type. Use after /architect-version. - execute-task: Execute a single task end-to-end: either a new story or a fix from validation findings. Reads the task context and architecture, then produces working output that meets all acceptance criteria. Adapts to project type: writes code for code projects, writes deliverables for non-code projects. - explore-conventions: Find the established sibling pattern for a thing you're about to write, how this codebase already does registration, error shapes, serializers, factories, test setup, so new code matches instead of inventing. Returns the pattern + a concrete example to copy. - ideate: Build a comprehensive project specification through conversational refinement. Adapts to any project type: code, business, research, consulting. Reads workspace context to understand where it is and what kind of project this is. Use at the very start of a new project or major initiative. - orchestrate: Execute a version end-to-end with a coordinated agent team. Cycles through architect-version → DoD gate → build-stories → execute → validate until the version ships. A version is shipped when the human signs off. - plan: Design an evolutionary delivery roadmap through conversational refinement. Defines version progression where each version delivers tangible value. Adapts to project type: code releases, consulting milestones, research phases. Use after /ideate and /architect. - probe-contract: Find out how code ACTUALLY behaves by executing the real classes in a REPL, the real request/response shape, the real return value, without relying on a live staging environment. Beats writing a test for 'how does this behave?'. - setup-env: Bring a fresh worktree/checkout to a runnable state, verify base HEAD, copy gitignored files (.env), allocate per-agent DB/test env, install deps, run the smoke gate. Deterministic, mechanical. Reports a single ready/blocked verdict. - trace-flow - validate-execution - verify-symbol Descriptions come from the frontmatter of each SKILL.md, punctuation lightly normalized.