Slash Command

/init-workspace-flow-documentation

Creates five workspace documentation files—CONTEXT.md, ARCHITECTURE.md, IMPLEMENTATION.md, ASSUMPTIONS.md, AGENT MEMORY.md—synthesizing tech stack, code map, dependencies, and source code.

documentation

npx claudepluginhub griddynamics/rosetta --plugin core

Prompt Preview

<init_workspace_flow_documentation>

<description_and_purpose>
Agents without workspace documentation re-discover facts, repeat mistakes, and make incorrect assumptions every session. This phase creates the shared understanding layer all subsequent agent work depends on. Proof: five doc files exist and every prepped-workspace skill reads them.
</description_and_purpose>

<workflow_context>
- Phase 6 of 8 in init-workspace-flow
- Input: TECHSTACK, CODEMAP, DEPENDENCIES, source code, PATTERNS, state.file_count, state.mode, state.composite
- Output: CONTEXT.md, ARCHITECTURE.md, IMPLEMENTATION....

Command Content

Other plugins with /init-workspace-flow-documentation

/documents

Audits, creates, and updates project documentation according to monorepo standards, using phase-focused or full audit modes.

apex-spec

/flow-docs

Runs Flow project documentation lifecycle: validate quality gates, capture knowledge from PRDs, archive completed items, cleanup artifacts, or full cycle. Produces reports and updated knowledge base.

6 tools

flow

/index

3.6k

claude-scholar

/init

444

Initializes or re-boots llmdoc/ directory structure, runs multi-themed project investigations with investigator, and generates initial stable docs via recorder.

llmdoc

/sc-index

/map-codebase

Surveys project and generates missing CLAUDE.md, ARCHITECTURE.md, CODE-PATTERNS.md for SoloFlow agent shared context. Idempotent; supports skip flags.

soloflow

Stats

Parent Repo Stars15

Parent Repo Forks6

Last CommitMar 25, 2026

Actions

View Source View Plugin View on GitHub View README

Help us improve

Share bugs, ideas, or general feedback.

<init_workspace_flow_documentation> <description_and_purpose> Agents without workspace documentation re-discover facts, repeat mistakes, and make incorrect assumptions every session. This phase creates the shared understanding layer all subsequent agent work depends on. Proof: five doc files exist and every prepped-workspace skill reads them. </description_and_purpose> <workflow_context> - Phase 6 of 8 in init-workspace-flow - Input: TECHSTACK, CODEMAP, DEPENDENCIES, source code, PATTERNS, state.file_count, state.mode, state.composite - Output: CONTEXT.md, ARCHITECTURE.md, IMPLEMENTATION....

<init_workspace_flow_documentation>

<description_and_purpose> Agents without workspace documentation re-discover facts, repeat mistakes, and make incorrect assumptions every session. This phase creates the shared understanding layer all subsequent agent work depends on. Proof: five doc files exist and every prepped-workspace skill reads them. </description_and_purpose>

<workflow_context>

Phase 6 of 8 in init-workspace-flow
Input: TECHSTACK, CODEMAP, DEPENDENCIES, source code, PATTERNS, state.file_count, state.mode, state.composite
Output: CONTEXT.md, ARCHITECTURE.md, IMPLEMENTATION.md, ASSUMPTIONS.md, AGENT MEMORY.md
Prerequisite: Phases 3 and 5 complete </workflow_context>

<phase_steps>

Read state and prerequisites
Acquire documentation skill
Execute documentation creation
Update state, log gaps </phase_steps>

<read_state step="6.1">

Read agents/init-workspace-flow-state.md
Confirm Phase 3 complete (TECHSTACK, CODEMAP, DEPENDENCIES exist)
Read state.mode, state.composite, state.file_count </read_state>

<acquire_skills step="6.2">

ACQUIRE init-workspace-documentation/SKILL.md FROM KB </acquire_skills>

<execute_documentation step="6.3" subagent="built-in" role="Senior technical writer synthesizing workspace documentation" subagent_recommended_model="claude-opus-4-6,gpt-5.4-high,gemini-3.1-pro-preview">

Execute skill with state.mode, state.composite, state.file_count as inputs </execute_documentation>

<update_state step="6.4">

Write Phase 6 completion to agents/init-workspace-flow-state.md
Update file inventory for CONTEXT, ARCHITECTURE, IMPLEMENTATION, ASSUMPTIONS, AGENT MEMORY
Log gaps identified for Phase 7 </update_state>

<validation_checklist>

All 5 doc files exist and are non-empty
If composite: top-level docs are registries with sub-repo references
If upgrade mode: human-added content preserved
State file shows Phase 6 complete with per-file status </validation_checklist>

- AGENT MEMORY.md is for agent operational notes, not a duplicate of CONTEXT.md

</init_workspace_flow_documentation>