Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/griddynamics/rosettaWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/griddynamics/rosetta/arrange-workspace-flow-choose-workspace-layout)<a href="https://agentmods.dev/commands/griddynamics/rosetta/arrange-workspace-flow-choose-workspace-layout"><img src="https://agentmods.dev/badge/commands/griddynamics/rosetta/arrange-workspace-flow-choose-workspace-layout/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/griddynamics/rosetta/arrange-workspace-flow-choose-workspace-layout"><img src="https://agentmods.dev/badge/commands/griddynamics/rosetta/arrange-workspace-flow-choose-workspace-layout.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00022 | $0.01752 |
| Opus 5 | $0.00011 | $0.00876 |
| Sonnet 5 | $0.00004 | $0.00350 |
| Haiku 4.5 | $0.00002 | $0.00175 |
Grade A, and why
arrange-workspace-flow-choose-workspace-layout scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.
<arrange_workspace_choose_workspace_layout>
<description_and_purpose> Show the workspace layout options verbatim, help the user pick one, and guide its setup actions. </description_and_purpose>
<phase_steps>
- Show layout options
- Ask the user to pick one
- Guide the picked option's setup actions
- Record the choice </phase_steps>
<present_layouts step="1.1">
- Show the user the content in
layout_guidanceEXACTLY as written. </present_layouts>
<layout_guidance compact="NEVER" summarize="AS-IS">
Choose a Workspace Layout
Pick the layout that fits your project. These options apply to any multi-repository project — regular development, microservices, or modernization:
- Single Repo Workspace is the most useful when changes are implemented independently on each repository: single code change, single PR.
- Composite Workspace is the most useful when changes are spread across multiple repositories (feature implementation end-to-end): multiple code changes, multiple PRs.
Option 1 — Single Repo Workspace. The workspace is a single, writable repository. AI agents can only write to this repository. All other codebases the agent needs to read are brought in via refsrc/ as read-only references. This is the simplest option and the recommended starting point.
<new git repo root>
├── docs/
│ ├── ARCHITECTURE.md # main service architecture and goals
│ └── CONTEXT.md # main service business context
├── refsrc/
│ ├── <old code>/ # read-only: legacy codebase
│ ├── microservice2/ # read-only: peer service API reference
│ ├── shared-lib/ # read-only: corporate shared library
│ └── frontend/ # read-only: UI codebase for reference
└── <new code>
Setup actions:
- Open the repository in your IDE.
- Clone any read-only reference codebases into
refsrc/as subfolders. - Initialize Rosetta.
Option 2 — Composite Workspace with Submodules. A top-level envelope repository holds each sub-repository as a git submodule. This integrates cleanly with standard git tooling and avoids manual gitignore maintenance. This layout needs the large-workspace-handling skill.
<workspace git repo>
├── docs/
│ ├── ARCHITECTURE.md # index: technical purpose of each sub-repo
│ └── CONTEXT.md # index: business purpose of each sub-repo
├── <old repo>/ # git submodule — e.g. old-app
│ ├── docs/ARCHITECTURE.md
│ ├── docs/CONTEXT.md
│ └── <source files>
├── <new repo>/ # git submodule — e.g. new-app
│ ├── docs/ARCHITECTURE.md
│ ├── docs/CONTEXT.md
│ └── <source files>
├── microservice1/ # git submodule
│ ├── docs/ARCHITECTURE.md
│ ├── docs/CONTEXT.md
│ └── <source files>
├── frontend/ # git submodule
│ ├── docs/ARCHITECTURE.md
│ ├── docs/CONTEXT.md
│ └── <source files>
└── shared-lib/ # git submodule
├── docs/ARCHITECTURE.md
├── docs/CONTEXT.md
└── <source files>
Setup actions:
- Create a new empty git repository to serve as the composite workspace envelope.
- Request AI to add each sub-repository (code, infra, QA, frontend, shared libraries, etc.) as a git submodule and clone them into the envelope.
- Initialize Rosetta in the envelope workspace, telling it this is a composite workspace and that
ARCHITECTURE.mdmust record that submodules are used for dynamic and optionally sparse-checkout. - Development teams can then use sparse-checkout on modules and/or they can select submodules they need.
- AI can dynamically check out a missing submodule at any point:
git submodule update --init <name>.
Option 3 — Composite Workspace with gitignore. A top-level folder holds all repositories as plain directories. Each sub-repo folder is excluded from the envelope's git tracking via .gitignore. The downsides: the workspace must be tracked in git, and .gitignore and doc routing need ongoing care. This layout needs the large-workspace-handling skill.
<workspace git repo>
├── docs/
│ ├── ARCHITECTURE.md # index: technical purpose of each sub-repo
│ └── CONTEXT.md # index: business purpose of each sub-repo
├── <old repo 1>/
│ ├── docs/ARCHITECTURE.md
│ ├── docs/CONTEXT.md
│ └── <source files>
├── <old repo 2>/
│ ├── docs/ARCHITECTURE.md
│ ├── docs/CONTEXT.md
│ └── <source files>
├── <new repo>/
│ ├── docs/ARCHITECTURE.md
│ ├── docs/CONTEXT.md
│ └── <source files>
├── microservice1/
│ ├── docs/ARCHITECTURE.md
│ ├── docs/CONTEXT.md
│ └── <source files>
├── frontend/
│ ├── docs/ARCHITECTURE.md
│ ├── docs/CONTEXT.md
│ └── <source files>
└── .gitignore # excludes the cloned repo folders
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 6d ago First seen · 163 lines · 22 tokens per session scan A 1f74db1fa5bf
arrange-workspace-flow-choose-workspace-layout is a command published in the GitHub repository griddynamics/rosetta (343 stars, last pushed 5d ago), licensed Apache-2.0. It adds 22 tokens to every session and 1,752 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other commands, from other repositories
taskstoissues
A command that turns structured tasks from project design documents into ordered GitHub Issues, written in simplified Chinese.
step6-ship
Pipeline Step 6 — Ship the completed phase: commit, update roadmap, capture postmortem, optionally push and create PR.
gentle-sdd-archive
Archive a completed SDD change — syncs specs and closes the cycle.
gentle-sdd-status
Show structured SDD status for an active change.
oneshot
Autonomous feature execution via sdp-orchestrate outer loop.
hybrid-complete
Complete Hybrid Ralph task in worktree, verify all stories complete, commit code changes (excluding planning files), merge to target branch, and cleanup worktree directory. Can be run from any directory.