What is arrange-workspace-flow-configure-ecosystem?

A workflow phase for showing guidance about configuring the tools around a project, including MCPs, command-line tools, plugins, and AI coding agents. It guides installation only after the user chooses to proceed.

Use it to review ecosystem recommendations, choose MCPs or command-line tools, configure plugins and extensions, and set up AI coding-agent CLIs.

It helps teams decide which development tools to configure while keeping the user in control of installations and changes to the workspace.

arrange-workspace-flow-configure-ecosystem — Command for Claude Code b

Install

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.

Clone the repo

git clone --depth 1 https://github.com/griddynamics/rosetta

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/griddynamics/rosetta/arrange-workspace-flow-configure-ecosystem/github.svg)](https://agentmods.dev/commands/griddynamics/rosetta/arrange-workspace-flow-configure-ecosystem)

Your own site

<a href="https://agentmods.dev/commands/griddynamics/rosetta/arrange-workspace-flow-configure-ecosystem"><img src="https://agentmods.dev/badge/commands/griddynamics/rosetta/arrange-workspace-flow-configure-ecosystem/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.

Your own site · 80×15

<a href="https://agentmods.dev/commands/griddynamics/rosetta/arrange-workspace-flow-configure-ecosystem"><img src="https://agentmods.dev/badge/commands/griddynamics/rosetta/arrange-workspace-flow-configure-ecosystem.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,428 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.01428
Opus 5	$0.00011	$0.00714
Sonnet 5	$0.00004	$0.00286
Haiku 4.5	$0.00002	$0.00143

Measured 5d ago against content hash 735652317926, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

arrange-workspace-flow-configure-ecosystem 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 5d 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.

plugins/core-copilot-light/commands/arrange-workspace-flow-configure-ecosystem.md · 95 lines

How it starts

The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.

<arrange_workspace_configure_ecosystem>

<description_and_purpose> Show MCP/CLI/plugin recommendations verbatim; guide install only if the user decides to. </description_and_purpose>

<phase_steps>

Show ecosystem guidance
Guide user how to install only if user decides to </phase_steps>

<present_guidance step="6.1">

Show the user the content in ecosystem_guidance EXACTLY as written. </present_guidance>

<ecosystem_guidance compact="NEVER" summarize="AS-IS">

Configure the ecosystem

Install and configure MCPs and CLIs. Keep at most three MCPs enabled at a time, and prefer CLIs they are always available and do not consume context.
Install and configure plugins and extensions.
Install and configure AI coding agent CLIs (Copilot CLI, Claude, Codex, and so on).

Save cost — add the line below to your workspace AGENTS.md/CLAUDE.md to cut model output tokens:

MUST ALWAYS think, reason, plan, chat, document in compressed/terse/unicode chars/terms/always/no hieroglyphs; Exclude final artifacts, any tool calls, all code, etc.

Recommended CLIs

Prefer a CLI over the matching MCP when one exists — it costs no context.

gh — GitHub CLI: pull requests, issues, releases, and CI checks.
acli — Atlassian CLI: Jira and Confluence from the terminal.
rg - ripgrep - the most of new AI models prefer it over grep
rtk (github.com/rtk-ai/rtk) — CLI proxy that reduces LLM token consumption by 60–90% on common dev commands. MUST review with client! This can see the actual client IP!

Useful MCPs

MCPs are the eyes and hands of the AI — add them, but keep it balanced. Enable only what the task needs. MUST confirm with client!

Context7 (https://github.com/upstash/context7) — Up-to-date library documentation.
Playwright MCP (https://github.com/microsoft/playwright-mcp) — Drive web pages via accessibility snapshots — no screenshots or vision models needed.
Fetch (https://github.com/modelcontextprotocol/servers/tree/main/src/fetch) — Retrieve and process content from web pages and APIs.
Chrome DevTools (https://github.com/ChromeDevTools/chrome-devtools-mcp) — Full browser control: console, network tab, snapshots.
GitNexus (https://github.com/abhigyanpatwari/GitNexus) — Index a large codebase into a knowledge graph. Third-party tool will have access to IP. Review license and policy with your manager. Free for non-commercial or personal use; PAID for commercial or business use — see GitNexus Enterprise Licensing.
Graphify (https://github.com/safishamsi/graphify) — MIT-licensed alternative that turns a project into a queryable knowledge graph. Third-party tool will have access to IP. Review license and policy with your manager.
Figma MCP (https://github.com/GLips/Figma-Context-MCP) — Read designs directly from Figma.
Jira & Confluence MCP (https://www.atlassian.com/platform/remote-mcp-server) — Tickets, comments, and documentation.
Repomix MCP (https://repomix.com/guide/mcp-server) — Docs for using existing client libraries.
DeepWiki (https://docs.devin.ai/work-with-devin/deepwiki-mcp) — Up-to-date documentation.
Database MCPs (https://glama.ai/mcp/servers?attributes=category%3Adatabases) — Read schema and data.

Recommended Plugins

LSPs — language server plugins for code intelligence; support is IDE/agent-specific:
- Claude Code: install the LSP binary separately, then add via /plugin → Discover tab, search "lsp"; supported list + install links at https://raw.githubusercontent.com/Piebald-AI/claude-code-lsps/refs/heads/main/README.md.
- Codex: LSPs not supported.
- Copilot CLI: https://docs.github.com/en/copilot/how-tos/copilot-cli/set-up-copilot-cli/add-lsp-servers (CLI/CLI-mode only, not regular VS Code/JetBrains Copilot).
CTO Claude Marketplace (https://github.com/griddynamics/cto-claude-marketplace) — Grid Dynamics' internal Claude skills marketplace for GD workflows; zero-install via Claude Cowork with a GD account. Internal GD tooling — MUST confirm with client/manager.
Allium (https://github.com/juxt/allium) — MIT-licensed skill for spec-first, behavior-driven development; maintains a .allium spec alongside code (/elicit, /distill, /propagate, /tend, /weed) to catch spec/code drift and generate tests from behavior.

Read the full file on GitHub · 95 lines

Changes

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.

5d ago First seen · 95 lines · 22 tokens per session scan A 735652317926

Subscribe to this mod's changes

arrange-workspace-flow-configure-ecosystem is a command published in the GitHub repository griddynamics/rosetta (343 stars, last pushed 4d ago), licensed Apache-2.0. It adds 22 tokens to every session and 1,428 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.

Building agents Claude Code Project management arrange codex copilot cursor developer-tools ecosystem mcp-server phase workspace

gentle-sdd-archive

Archive a completed SDD change — syncs specs and closes the cycle.

Gentleman-Programming/gentle-ai · 14 tokens

gentle-sdd-status

Show structured SDD status for an active change.

Gentleman-Programming/gentle-ai · 9 tokens

plan-product

Generate comprehensive product planning documentation using a contract-first approach that establishes clear product vision, mission, and roadmap before creating any supporting files. This command eliminates assumptions by gathering complete product context through structured discovery, then creates a complete product…

devobsessed/code-captain · 0 tokens

arrange-workspace-flow-configure-ecosystem