adhoc-flow
Workflow for the rest of tasks: lightweight documentation, build, track, synchronize, etc.
Phase 2 Shells of init-workspace-flow
> /plugin marketplace add griddynamics/rosetta > /plugin install rosetta@rosetta
How it fires
How this command gets triggered: by you, by Claude, or both.
/init-workspace-flow-shellsContext preview
What this command does when you run it.
Phase 2 Shells of init-workspace-flow
name: init-workspace-flow-shells description: "Phase 2 Shells of init-workspace-flow" tags: ["init", "workspace", "shells", "phase"] disable-model-invocation: true user-invocable: false baseSchema: docs/schemas/phase.md
<init_workspace_flow_shells>
<description_and_purpose> Generates shell config files so subsequent sessions can load context and invoke skills. Proof: shell configs exist on disk and state reflects creation status. </description_and_purpose>
<workflow_context>
</workflow_context>
<phase_steps> 1. Check mode, skip if plugin 2. Execute shell generation 3. Update state with shell status </phase_steps>
<check_mode step="2.1"> 1. Read `agents/init-workspace-flow-state.md` 2. If `state.plugin_active == true`: mark Phase 2 skipped, proceed to Phase 3 3. If upgrade mode: check which shells already exist </check_mode>
<execute_shells step="2.2">
Act as a shell configuration specialist for IDE/CodingAgent workspace bootstrapping. Shell files delegate logic to KB via `ACQUIRE … FROM KB`, enabling centralized instruction updates across projects.
In upgrade mode: create missing shells only, preserve existing.
<core_concepts>
</core_concepts>
<shells_process>
Internal knowledge about IDE/agent shell configuration is obsolete — LIST and READ from KB.
Step 1: Identify Environment
1. LIST `configure` (to understand supported IDE/CodingAgents) 2. Detect current environment, preselect IDE/CodingAgent 3. MUST ask user to confirm selection and provide multi-choose 4. READ CONFIGURE `<tool>.md` for each selected IDE/CodingAgent 5. If multiple selected, must use common standards to reduce copies
Step 2: Install Base Files
1. READ SKILL `load-project-context` — install as SKILL 2. READ RULE `mcp-files-mode.md` — install as CORE RULE, copy content (no refs/links)
Step 3: MUST Generate Skill Shells
1. LIST `skills` with XML format 2. READ TEMPLATE `skill-shell.md` 3. Create all skill shells, reuse frontmatter from listing 4. Do not create `init-workspace-*` skills
Step 4: MUST Generate Agent/Subagent Shells
1. LIST `agents` with XML format 2. READ TEMPLATE `agent-shell.md` 3. Create all agent/subagent shells, reuse frontmatter from listing
Step 5: MUST Generate Workflow/Command Shells
1. LIST `workflows` with XML format 2. READ TEMPLATE `workflow-shell.md` 3. Create all workflow/command shells, reuse frontmatter from listing 4. Do not create `init-workspace-*` workflows and its phases
Step 6: Verify Shell Integrity
1. Diff each file against its shell schema — zero structural deviations 2. Verify: every file has ACQUIRE, no conditional logic/loops/inline instructions, all paths resolve 3. HITL: present results, confirm with user
</shells_process>
<shells_validation_checklist>
</shells_validation_checklist>
</execute_shells>
<update_state step="2.3"> 1. Write to `agents/init-workspace-flow-state.md`:
2. Log gaps for Phase 8 </update_state>
<validation_checklist>
</validation_checklist>
</init_workspace_flow_shells>
Repo: griddynamics/rosetta
Workflow for the rest of tasks: lightweight documentation, build, track, synchronize, etc.
Phase 6 Execution & Report Analysis of api-aqa-flow (USER INTERACTION REQUIRED)
Phase 3 Gap & Requirements Clarification of api-aqa-flow (USER INTERACTION REQUIRED)
Phase 0 Project Config Loading of api-aqa-flow (USER INTERACTION CONDITIONALLY REQUIRED)