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 skills add griddynamics/rosetta --skill modernization-flowgit 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/skills/griddynamics/rosetta/modernization-flow)<a href="https://agentmods.dev/skills/griddynamics/rosetta/modernization-flow"><img src="https://agentmods.dev/badge/skills/griddynamics/rosetta/modernization-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/skills/griddynamics/rosetta/modernization-flow"><img src="https://agentmods.dev/badge/skills/griddynamics/rosetta/modernization-flow.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00036 | $0.01602 |
| Opus 5.5 | $0.00014 | $0.00641 |
| Sonnet 5.5 | $0.00007 | $0.00320 |
| Haiku 4.5 | $0.00004 | $0.00160 |
Grade A, and why
modernization-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.
How it starts
The opening of the file, as written. The whole thing — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Modernization Flow - Execute Phases Sequentially
Context
This modernization process is designed to systematically analyze, specify, and implement code modernization/migration projects. The process is divided into phases that MUST be executed one-by-one.
Critical Requirements
- ONE PHASE AT A TIME: Read one phase file, execute it completely, update state file, then move to next phase.
- DO NOT SKIP PHASES: Each phase builds on the previous one.
- STATE TRACKING: After each phase, update
agents/modernization-flow-state.mdwith completion status, keep this document concise. - USER CONFIRMATION: Wait for user confirmation before proceeding to next phase.
- Make sure to have todo tasks for each phase! Do not skip phases!
- REMEMBER Do not put decisions/recommendations/suggestions/implementation code for the next phases in the output documents! The decisions are made at phase 6 and review at phase 7 AFTER full analysis. Respect that.
- MUST Create and update files that ARE EXPLICITLY stated here, ASK for permission to create any other file!
- MUST use grep/search on large files to read "table of contents" and then use line ranges to read what is needed.
- MUST use only applicable phases according to the target of the modernization (acquire user approval first and store it in state), as those phases are for multi-project cross-tech modernization. Do not take shortcuts within the phase!
- Prioritize ACCURACY over SPEED!
- THIS is very large workflow: MUST use best matching available separate subagents for each phase, top level agent is orchestrator, orchestrator must be smart with reading/writing files (avoid, fallback to grep and reading line-ranges, as those are very large)
- Phase subagents must contain additionally: "MUST APPLY PHASE <phase.md> — FULLY EXECUTE ALL STEPS", goal, context, original user request, inputs, expected outputs, and summary in the format useful for orchestrator, subagents must be informed they are used as subagents.
What ships with it
8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- phases/modernization-flow-analysis.md 5.8 KB
- phases/modernization-flow-crossproject.md 3.4 KB
- phases/modernization-flow-grouping.md 2.6 KB
- phases/modernization-flow-implement.md 4.3 KB
- phases/modernization-flow-mapping.md 5.3 KB
- phases/modernization-flow-reuse.md 3.8 KB
- phases/modernization-flow-review.md 2.3 KB
- phases/modernization-flow-testing.md 4.6 KB
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 · 133 lines · 36 tokens per session scan A 74cc5b07e540
modernization-flow is a skill published in the GitHub repository griddynamics/rosetta (360 stars, last pushed today), licensed Apache-2.0. It adds 36 tokens to every session and 1,602 once invoked, about $0.0001 per session on Opus 5.5. 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 skills, from other repositories
memorix-memory
Use when prior workspace context, past decisions, solved bugs, handoff state, or durable project knowledge would help a coding task.
Agent Browser Automation
Fast Rust-based headless browser automation CLI with Node.js fallback for AI agents, featuring navigation, clicking, typing, snapshots, and structured commands optimized for agent workflows.
memorix
Use when Claude Code needs Memorix shared memory, reasoning, Git Memory, mini-skills, session handoff, orchestration coordination, or integration troubleshooting.
memorix-mini-skills
Use when durable project knowledge, gotchas, workflows, or repeated fixes should become reusable agent guidance instead of ordinary memory.
memorix-orchestrate
Use when a main agent needs Memorix to coordinate explicit subagent work through tasks, handoffs, messages, file locks, or the orchestrate CLI.
memorix-reasoning
Use when a technical decision, trade-off, rejected alternative, architecture rationale, or design risk should be recorded or recovered.