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.
npx agentmods add commands/griddynamics/rosetta/init-workspace-flow-shellsgit 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/init-workspace-flow-shells)<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>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 | $0.00017 | $0.00951 |
| Opus 5 | $0.00009 | $0.00476 |
| Sonnet 5 | $0.00003 | $0.00190 |
| Haiku 4.5 | $0.00002 | $0.00095 |
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.
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>
- Check mode, skip if plugin
- Execute shell generation
- Update state with shell status </phase_steps>
<check_mode step="2.1">
- Read
agents/init-workspace-flow-state.md - If
state.plugin_active == true: mark Phase 2 skipped, proceed to Phase 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
- LIST
configure(to understand supported IDE/CodingAgents) - Detect current environment, preselect IDE/CodingAgent
- MUST ask user to confirm selection and provide multi-choose
- READ CONFIGURE
<tool>.mdfor each selected IDE/CodingAgent - If multiple selected, must use common standards to reduce copies
Step 2: Install Base Files
- READ SKILL
load-project-context— install as SKILL - READ RULE
mcp-files-mode.md— install as CORE RULE, copy content (no refs/links)
Step 3: MUST Generate Skill Shells
- LIST
skillswith XML format - READ TEMPLATE
skill-shell.md - Create all skill shells, reuse frontmatter from listing
- Do not create
init-workspace-*skills
Step 4: MUST Generate Agent/Subagent Shells
- LIST
agentswith XML format - READ TEMPLATE
agent-shell.md - Create all agent/subagent shells, reuse frontmatter from listing
Step 5: MUST Generate Workflow/Command Shells
- LIST
workflowswith XML format - READ TEMPLATE
workflow-shell.md - Create all workflow/command shells, reuse frontmatter from listing
- Do not create
init-workspace-*workflows and its phases
Step 6: Verify Shell Integrity
- Diff each file against its shell schema — zero structural deviations
- Verify: every file has ACQUIRE, no conditional logic/loops/inline instructions, all paths resolve
- 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">
- Write to
agents/init-workspace-flow-state.md:- Shell configs status (created | updated | skipped)
- Bootstrap rule status
- Phase 2 completion timestamp
- 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>
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.
- today First seen · 121 lines · 17 tokens per session scan A c67b8bee54fa
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.
Other commands, from other repositories
resolve-conflicts
Resolve merge conflicts on a GitHub PR by merging the base branch into the PR branch in an isolated git worktree, with JSON/markdown-aware conflict resolution.
xpoz-best-practices
Reference docs for Xpoz query syntax, pagination, field selection, platform tools, and authentication. Usage: /xpoz-best-practices.
align
Verify spec-vs-spec alignment and brevity across the intent tree. This is NOT QA — QA checks code against a spec; alignment checks whether specs are consistent with their ancestors and internally tight against the Brevity Contract. The aligner runs three passes per walk.
deploy-check
Pre-flight verification before pushing to main. Reproduces the CI gates locally so the push doesn't fail in production.
rclone_mkdir
Make the path if it doesn't already exist.
git
Git operations with intelligent commit messages and workflow optimization.