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-business-context)<a href="https://agentmods.dev/commands/griddynamics/rosetta/arrange-workspace-flow-business-context"><img src="https://agentmods.dev/badge/commands/griddynamics/rosetta/arrange-workspace-flow-business-context.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 5.1 | $0.00018 | $0.00740 |
| Opus 5 | $0.00009 | $0.00370 |
| Sonnet 5 | $0.00004 | $0.00148 |
| Haiku 4.5 | $0.00002 | $0.00074 |
Grade A, and why
arrange-workspace-flow-business-context 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.
How it starts
The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
<arrange_workspace_business_context>
<description_and_purpose>
Interview user to gather non-technical and engineering behavior facts about the project not yet in docs/CONTEXT.md.
</description_and_purpose>
<phase_steps>
- Interview user about what's missing in
docs/CONTEXT.md— usestarter_topics. Follow Questioning process inhitlSKILL. - Record confirmed answers to
docs/CONTEXT.mdpercontext_contract. Unconfirmed inferences →docs/ASSUMPTIONS.md. - Update
arrange-state.md. </phase_steps>
<starter_topics> Starter topics (add project-specific questions as needed):
- Its overall goal.
- What it does in the client's wider ecosystem.
- The source and the target of the work.
- The issue tracker you use.
- How a story goes from ticket to implemented.
- Who the users and key stakeholders are.
- Core business rules and domain constraints.
- Any compliance or regulatory requirements.
- Accepted SDLC, DoD, and processes related to the project.
- References to documentation and ways to access it (example, acli or mcp for atlassian).
Universal Starter Definition of Done
Outcome
- Intent, ACs, and expected outcomes met
- User and business value proven end to end
- Scope complete with no known regressions
Verification
- Build, lint, type, and static checks pass without errors or warnings
- Relevant unit + integration + E2E tests created and pass; changed code coverage ≥85%
- Affected components start and pass direct functional checks fully
- Fresh AI subagent completed direct manual QA and pass
- Security and privacy checks pass with no medium or higher findings
- Performance and reliability meet best practices
- UX and accessibility meet applicable standards
- Applicable laws, regulations, standards, policies, and licenses met
- Specific to project area, domain, technology best practices pass
Delivery
- Data and schema changes correct; migrations tested, safe, and reversible
- Dependencies, configuration, infrastructure, CI/CD, and deployment assets updated
- Observability, documentation, runbooks, and release notes updated
- Compatibility, deployment, rollback, and recovery verified
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 · 86 lines · 18 tokens per session scan A 5d2dd4a324af
arrange-workspace-flow-business-context is a command published in the GitHub repository griddynamics/rosetta (343 stars, last pushed 4d ago), licensed Apache-2.0. It adds 18 tokens to every session and 740 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
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.
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…
status
A command that provides developers with a comprehensive status report when starting work or switching context. Analyzes current git state, active work, and project health to orient developers and suggest next actions.
sdd-continue
Continue the next SDD phase in the dependency chain.
sdd-apply
Implement SDD tasks — writes code following specs and design.