From sdd
Lists all project ADRs and specs with status, date, and title. Supports adr/spec/all filters and --module scoping in workspaces for decision overviews.
npx claudepluginhub joestump/claude-plugin-sdd --plugin sddThis skill uses the workspace's default tool permissions.
List all ADRs and specs in the project with their status, date, and title.
Searches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.
Guides code writing, review, and refactoring with Karpathy-inspired rules to avoid overcomplication, ensure simplicity, surgical changes, and verifiable success criteria.
Provides UI/UX resources: 50+ styles, color palettes, font pairings, guidelines, charts for web/mobile across React, Next.js, Vue, Svelte, Tailwind, React Native, Flutter. Aids planning, building, reviewing interfaces.
Share bugs, ideas, or general feedback.
List all ADRs and specs in the project with their status, date, and title.
Resolve artifact paths: Follow the Artifact Path Resolution pattern from references/shared-patterns.md to determine the ADR and spec directories. If $ARGUMENTS contains --module <name>, resolve paths relative to that module; otherwise, in a workspace, aggregate across all modules. The resolved ADR directory is {adr-dir} and spec directory is {spec-dir}.
Cross-module aggregation: When in aggregate mode (no --module, workspace detected), list artifacts from all modules. Add a Module column to the output tables with module names in square brackets (e.g., [api]). Sort by module name first, then by artifact number. When --module is provided, scope to that single module — no module column needed. When in single-module mode (no workspace), operate normally.
Parse filter: Check $ARGUMENTS for a filter keyword:
adr -- only show ADRsspec -- only show specsall or empty -- show both (default)Scan for ADRs (unless filter is spec):
{adr-dir}/ADR-*.md files (in aggregate mode, glob per-module and prefix results with module name)status and date per the Status Field Extraction algorithm in Step 3a (/sdd:prime defines this canonically; /sdd:list reuses it for the same legacy-format reasons)# headingScan for specs (unless filter is adr):
{spec-dir}/*/spec.md files (in aggregate mode, glob per-module and prefix results with module name)status and date per the Status Field Extraction algorithm referenced above# heading (e.g., SPEC-0001: Web Dashboard)3a. Status Field Extraction: same algorithm as /sdd:prime Step 3a. Briefly: try YAML frontmatter status: first; if absent, scan the first 30 lines for a - **Status:** {value} bullet (case-insensitive on "Status"); strip any parenthetical refinement notes (split on (, trim); if neither form yields a value, render as — when some artifacts have status, or drop the Status column entirely when zero do.
Present results as a formatted table:
Single-module or --module mode:
## Architecture Decisions
| ID | Title | Status | Date |
|----|-------|--------|------|
| ADR-0001 | Choose frontend framework | accepted | 2025-01-15 |
| ADR-0002 | Choose PostgreSQL | proposed | 2025-02-01 |
## Specifications
| ID | Title | Status | Date |
|----|-------|--------|------|
| SPEC-0001 | Web Dashboard | approved | 2025-01-20 |
Workspace aggregate mode:
## Architecture Decisions ({N} across {K} modules)
| Module | ID | Title | Status | Date |
|--------|----|-------|--------|------|
| [api] | ADR-0001 | Choose REST over GraphQL | accepted | 2025-01-15 |
| [api] | ADR-0002 | Choose PostgreSQL | proposed | 2025-02-01 |
| [worker] | ADR-0001 | Choose Redis for queues | accepted | 2025-01-20 |
## Specifications ({M} across {K} modules)
| Module | ID | Title | Status | Date |
|--------|----|-------|--------|------|
| [api] | SPEC-0001 | Web Dashboard | approved | 2025-01-20 |
| [worker] | SPEC-0001 | Job Processing | draft | 2025-02-01 |
Handle empty results: If no ADRs or specs exist, tell the user:
/sdd:adr [description]."/sdd:spec [capability]."- **Status:** {value} is misleading and was reported as a real-world bug— for missing entries when the column is partially populated. Workspace aggregate mode: the rendered corpus is the union across all modules — drop the column only when ZERO artifacts across ALL modules have status. If even one module has status, keep the column