init-workspace-flow-shells

init-workspace-flow-shells is a command for coding agents from griddynamics/rosetta. It costs 17 tokens per session (951 once invoked), scanned A, original, Apache-2.0.

Phase 2 Shells of init-workspace-flow.

Command

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.

agentmods
npx agentmods add commands/griddynamics/rosetta/init-workspace-flow-shells
Clone the repo
git clone --depth 1 https://github.com/griddynamics/rosetta

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.

agentmods badge for init-workspace-flow-shells

README.md
[![agentmods](https://agentmods.dev/badge/commands/griddynamics/rosetta/init-workspace-flow-shells.svg)](https://agentmods.dev/commands/griddynamics/rosetta/init-workspace-flow-shells)
Your own site
<a href="https://agentmods.dev/commands/griddynamics/rosetta/init-workspace-flow-shells"><img src="https://agentmods.dev/badge/commands/griddynamics/rosetta/init-workspace-flow-shells.svg" alt="Measured on agentmods" height="20"></a>
Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 951 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin unknown 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.

ModelPer sessionOnce invoked
Fable 5 $0.00017 $0.00951
Opus 5 $0.00009 $0.00476
Sonnet 5 $0.00003 $0.00190
Haiku 4.5 $0.00002 $0.00095

Measured today against content hash c67b8bee54fa, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

init-workspace-flow-shells 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 today.

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/init-workspace-flow-shells.md · 121 lines

What it actually says

<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>

  • Phase 2 of 9 in init-workspace-flow
  • Input: state.mode, state.plugin_active, IDEs
  • Output: shell configs, bootstrap rule, load-project-context shell
  • Prerequisite: Phase 1 complete, state.mode set
  • This is simple mechanical AND systematic phase (do not overthink) </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>

  • All Rosetta prep steps MUST be FULLY completed, load-project-context skill loaded and fully executed
  • Shell = frontmatter + single ACQUIRE instruction, zero inline logic
  • No absolute paths in generated shells

</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>

  • Every generated file: frontmatter + ACQUIRE only, zero inline logic
  • All paths resolve, extensions match IDE config
  • User confirmed verification results

</shells_validation_checklist>

</execute_shells>

<update_state step="2.3">

  1. Write to agents/init-workspace-flow-state.md:
    • Shell configs status (created | updated | skipped)
    • Bootstrap rule status
    • Phase 2 completion timestamp
  2. Log gaps for Phase 8 </update_state>

<validation_checklist>

  • Plugin mode: phase marked skipped, no shell files modified
  • Install mode: all expected shell files exist on disk
  • Upgrade mode: only missing shells created, existing preserved
  • Bootstrap rule file exists with a typed load instruction for load-project-context </validation_checklist>

</init_workspace_flow_shells>

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.

  1. today First seen · 121 lines · 17 tokens per session scan A c67b8bee54fa

Subscribe to this mod's changes

init-workspace-flow-shells is a command published in the GitHub repository griddynamics/rosetta (342 stars, last pushed today), licensed Apache-2.0. It adds 17 tokens to every session and 951 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.