context
Analyze and optimize Claude Code's context configuration (analyze, optimize, or reset).
Implement tasks from a conversation's specs (Experimental)
> /plugin marketplace add komluk/scaffolding > /plugin install scaffolding@komluk-scaffolding
How it fires
How this command gets triggered: by you, by Claude, or both.
/applyContext preview
What this command does when you run it.
Implement tasks from a conversation's specs (Experimental)
name: "Specs: Apply" description: Implement tasks from a conversation's specs (Experimental) category: Workflow tags: [workflow, artifacts, experimental]
Implement tasks from a conversation's specs.
**Input**: Optionally specify a conversation_id (e.g., `/specs:apply <conversation_id>`). If omitted, use the current conversation's UUID. If vague or ambiguous, list conversations that have specs directories.
**UUID Enforcement**: The conversation_id MUST be a UUID (format: `xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx`). NEVER use descriptive names.
**Steps**
1. **Locate the specs directory**
Use the current conversation's UUID or the provided one to find: `.scaffolding/conversations/{conversation_id}/specs/`
If no specs directory exists, inform the user and suggest `/specs:new` or `/specs:ff`.
Always announce: "Using specs from conversation: <conversation_id>"
2. **Read context files**
Read the available spec files from the specs directory:
**Handle states:**
3. **Show current progress**
Display:
4. **Implement tasks (loop until done or blocked)**
For each pending task:
**Pause if:**
5. **On completion or pause, show status**
Display:
**Output During Implementation**
## Implementing from specs Working on task 3/7: <task description> [...implementation happening...] Task complete Working on task 4/7: <task description> [...implementation happening...] Task complete
**Output On Completion**
## Implementation Complete **Conversation:** <conversation_id> **Progress:** 7/7 tasks complete ### Completed This Session - [x] Task 1 - [x] Task 2 ... All tasks complete! You can archive with `/specs:archive`.
**Output On Pause (Issue Encountered)**
## Implementation Paused **Conversation:** <conversation_id> **Progress:** 4/7 tasks complete ### Issue Encountered <description of the issue> **Options:** 1. <option 1> 2. <option 2> 3. Other approach What would you like to do?
**Guardrails**
Spec-driven multi-agent orchestration for Claude Code — pure markdown, zero backend, runs on the stock runtime. 13 agents, 36 skills, 19 commands, 15 hooks, per-phase model tiers, opt-in lifecycle hooks, optional cross-device semantic memory.
Repo: komluk/scaffolding
Analyze and optimize Claude Code's context configuration (analyze, optimize, or reset).
Scaffold a new scaffolding-compatible skill: an interactive flow that creates `skills/<name>/SKILL.md` from the canonical template, composes a `TRIGGER`/`SKIP`…
Health-check the scaffolding install and report install problems plus exact fixes (diagnose-only, never mutates).
Initialize OpenSpec in a project directory with the scaffolding-workflow schema.
Scaffold opt-in path-scoped nested CLAUDE.md rule files into the project to lazy-load per-area conventions while keeping routing always-loaded.
Bootstrap a new project with the scaffolding CLAUDE.md, settings.json, and `.scaffolding/` directory structure.