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/self-help-flow)<a href="https://agentmods.dev/commands/griddynamics/rosetta/self-help-flow"><img src="https://agentmods.dev/badge/commands/griddynamics/rosetta/self-help-flow/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/self-help-flow"><img src="https://agentmods.dev/badge/commands/griddynamics/rosetta/self-help-flow.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 | $0.00017 | $0.01972 |
| Opus 5.5 | $0.00007 | $0.00789 |
| Sonnet 5.5 | $0.00003 | $0.00394 |
| Haiku 4.5 | $0.00002 | $0.00197 |
Grade A, and why
self-help-flow 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 1mo 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.
This is a copy
89% identical to help-flow — 12 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
<self_help_flow>
<description_and_purpose>
Audience: developers and orchestrators exploring Rosetta-powered workspaces. Use when: "what can you do", "how do I use X", "how to develop with Rosetta", "what workflows are available", or any capability discovery question. Provides: guides user on how to use Rosetta and its capabilities; live overview of available skills, workflows, and agents; detailed guidance on matched capabilities; seamless handoff to any discovered workflow within the same session; Consider user sees this first time, you must explain, be clear, specific, non-ambiguous, user should just be able to follow it. REMIND USERS: use /help-flow instead of /self-help-flow. self-help-flow is deprecated.
</description_and_purpose>
<invocation_guidance>
When presenting capabilities to users, always show concrete slash command examples following this pattern:
/[command-name] [request in natural language]
QUICKSTART REFERENCE PATTERN — use this exact style for all examples shown to users:
/coding-flow Implement side bar on the home page, ...
/coding-flow Identify and implement fix, ...
/coding-flow Improve unit tests coverage to 85% for ...
/requirements-authoring-flow Extract detailed business and technical requirements from ... using subagents.
/modernization-flow Perform modernization phase 1 to reuse library refsrc/... using subagents.
/research-flow Investigate OAuth 2.0 implementation options for our stack
/ui-aqa-flow Create UI test automation for the checkout flow
/api-aqa-flow Automate backend API tests for TC-1234 with Swagger: https://api.example.com/swagger.json
HOW WORKFLOWS EXECUTE: Workflows are multi-phase pipelines. The AI guides the user through each phase automatically — HITL gates pause for user review and approval at critical decisions. Users invoke the workflow once with a slash command and follow AI guidance; they do not manage phases manually.
DIRECT SKILL INVOCATION (also supported):
Skills can be invoked directly. Slash command = folder name of the skill.
Naming rule: skills/[folder-name]/SKILL.md → /[folder-name] [request]
WHAT MAKES A VALID DIRECT SKILL EXAMPLE — a valid request must have all three:
- Specific artifact or target (not "this error" or "the tests" — name the file, log, or exact thing)
- Explicit method or action (not "investigate" alone — state what to produce and how)
- Explicit scope constraint (state what NOT to do, or what the boundary is)
WORKFLOWS ARE SELF-CONTAINED — they invoke skills internally:
coding-flow handles all coding tasks and invokes debugging, testing, and other skills itself as needed. Similarly, every other workflow invokes its own skills internally. Users should never manually invoke /debugging, /testing, /coding, or similar skills for work that belongs inside a workflow — the workflow handles that automatically.
BAD examples (do NOT show these — they are wrong):
/coding Debug this error in auth.py—/codingis an IMPLEMENTATION skill invoked internally bycoding-flow, not a standalone tool; andcoding-flowinvokes/debuggingitself when needed/debugging Investigate why payment tests fail— too vague: no specific artifact, no expected output, no constraint; and if a fix is needed afterward, this belongs incoding-flowentirely/research Compare event sourcing vs CRUD for our order service— this IS what/research-flowis for; using the skill directly bypasses the structured research workflow; PRIORITY RULE applies
GOOD examples:
/natural-writing Rewrite the executive summary in docs/CONTEXT.md — remove AI clichés, max 4 sentences, audience is a new engineer joining the project/debugging Read the stack trace in agents/TEMP/error.log — identify root cause only, do NOT propose fixes, report findings
DIRECT SUBAGENT INVOCATION (also supported):
Subagents can be invoked directly. Slash command = file name without .md.
Naming rule: agents/[name].md → /[name] [request]
Same rule applies — each example must specify the artifact, method, and constraints. Vague requests like "Design the auth module" or "Implement the payment service" require a full workflow, not direct subagent invocation.
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.
- 1mo ago First seen · 149 lines · 17 tokens per session scan A 8d22baf20a9b
self-help-flow is a command published in the GitHub repository griddynamics/rosetta (360 stars, last pushed today), licensed Apache-2.0. It adds 17 tokens to every session and 1,972 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 89% identical to help-flow, differing in 12 lines, and is treated as a copy.
Other commands, from other repositories
OPSX: Propose
Propose a new change - create it and generate all artifacts in one step.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.