claude

Spec-Driven Development

Spec-Driven Development for AI assistants — requirements, RFC-2119 specs, and ADRs with stable identifiers, machine-checked traceability, and the delivery pipeline that runs on them: workers, review into a findings file, close-out; two profiles.

1 on GitHubby Cadasto B.V.v0.18.0MITupdated 13 days agodevelopment
/

Plugin sdd from marketplace cadasto in Cadasto/plugin-marketplace. Commands read from the repo's manifest — 12 days ago.

This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.

What it installs

Skills (8)

  • sdd-close

    This skill should be used when the user asks to "close out REQ-…", "close out PR N", "write the PR body", "mark the PR ready", "the PR is merged, clean up", or "remove the merged branch and its worktree". Closes out a delivered change in its pull request, fixes the small outside defects and carries

  • sdd-deliver

    This skill should be used when the user asks to "deliver REQ-…", "run the delivery pipeline", "take this REQ to a pull request", "build this requirement end to end", or "resume the delivery of PR N". Drives one change from the dispatch gate through workers, gates and the first review pass to a ready

  • sdd-review

    This skill should be used when the user asks to "run the SDD review", "review this branch", "review this PR", or "give a second opinion". Reviews the whole branch, or only what is new with --since-last, with the reviewers the profile, lane and changed files call for, writes the findings into the bra

  • sdd-scaffold

    This skill should be used when the user asks to "set up SDD", "initialize spec-driven development", "scaffold the docs tree", "add SDD structure to this repo", "upgrade the SDD scaffold", or "re-vendor sdd-check". Creates the docs/ tree, the .sdd.yaml descriptor, AGENTS.md, the process docs and the

  • sdd-specify

    This skill should be used when the user asks to "add a requirement", "retire a requirement", "write, extend, or amend a spec", "make this behaviour normative", "record an ADR", "resolve a STRAND", "amend the constitution", or "write a knowledge-base page". Authors the REQ, the RFC-2119 SPEC §, the A

  • sdd-trace

    This skill should be used when the user asks to "show traceability for REQ-X", "what implements or tests this requirement", "give me the context for REQ-X", "are there orphan requirements", "run a quick drift scan", "run the drift gate", or "audit the traceability" (`--audit`). Report-only — prints

  • sdd-triage

    This skill should be used when the user asks to "triage the review", "work through the findings", "fix what the reviewers found", "address the review comments", "resolve the open findings", or "harvest the merged suggestions into the backlog" (`--backlog`). Works a branch's open findings to the end

  • spec-driven-development

    This skill should be used when the user asks "what is SDD", "explain spec-driven development", "how does the spec workflow work here", "which /sdd command do I use", or asks to implement, build, or add behaviour in a repository with docs/.sdd.yaml before a REQ or spec exists. Explains the methodolog

Subagents (4)

  • sdd-doc-reviewer

    Use this agent when a change wrote or reworded a normative sentence, a requirement or an ADR and the changed hunks need checking against the document-kind contract: two homes for one rule, a sentence that contradicts the code on a contract, an ADR that decides twice. Read-only; returns findings-file

  • sdd-implementer

    Use this agent when one bounded task from a delivery brief needs implementing: test first with a can-fail proof for a new obligation, committed by path, small defects in its own files fixed, with En-route findings for anything wrong outside its scope. Typical triggers include one task dispatched by

  • sdd-spec-conformance-reviewer

    Use this agent when changed code must be judged against the binding sentences it claims to implement — the SPEC § and REQ acceptance criteria, clause by clause, with the tests run as evidence. Report-only; returns findings-file lines; never edits the branch. Typical triggers include a pre-merge conf

  • sdd-traceability-auditor

    Use this agent when an SDD repository's whole traceability chain needs auditing for drift and orphans in isolated context: the drift gate's findings by family, a hand check of what it skipped, and the judgement no family can make. Report-only. Typical triggers include a pre-release chain check, a pe

Hooks (3)

  • SessionStart

    bash "${CLAUDE_PLUGIN_ROOT}/hooks/session-start.sh"

  • PostToolUse

    bash "${CLAUDE_PLUGIN_ROOT}/hooks/spec-edit-reminder.sh"

  • Stop

    bash "${CLAUDE_PLUGIN_ROOT}/hooks/session-stop.sh"

View source on GitHub cadasto.github.io

More from Cadasto/plugin-marketplace

All 7 plugins →

openEHR clinical modeling for AI assistants — archetypes, templates, compositions, AQL, CKM reuse search, and specification lookup.

8 skills · 3 commands · 3 agents · 1 MCP server · hooks

1

Human-facing documentation and content standards for AI assistants: technical writing, copy editing, AI-tell cleanup, marketing copy, SEO and AI citability, with claims grounded in cited evidence.

8 skills · 2 agents · hooks

1

PostgreSQL coding standards for AI assistants: queries, jsonb, schema, indexing, performance analysis, safe migrations. PostgreSQL 18 and later.

8 skills · 2 agents · hooks

1

Idiomatic Go coding standards for AI assistants — formatting, errors, concurrency, testing, layout.

7 skills · 1 agent · hooks

1

Maintainer plugin for developing the openEHR Assistant MCP server and plugin — authoring guides, prompts, MCP tools, examples, and managing releases

4 skills · 1 agent · hooks

1

Idiomatic PHP coding standards for AI assistants — PHP 8.4+, PER Coding Style, PHPStan level 8.

2 skills · 1 agent · hooks

1

Similar plugins

superpowers

claudecodex

Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques

15 skills · hooks

obra/superpowers 316,836

context7

claudecodex

Up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your coding agent's context.

1 MCP server

upstash/context7 64,709

Build powerful, stateful CLI interfaces for any GUI application using the cli-anything harness methodology.

5 commands

HKUDS/CLI-Anything 58,665

Automates browser interactions for web testing, form filling, screenshots, and data extraction

12 skills

vercel-labs/agent-browser 50,373

Use Alibaba Open Code Review from local Codex.

2 skills

alibaba/open-code-review 50,068

slidev

claude

Claude Code skill for creating and presenting Slidev slidedecks

1 skill

slidevjs/slidev 49,452

Maintain Spec-Driven Development?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex plugins7 plugins