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/modernization-flow-crossprojectgit 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/modernization-flow-crossproject)<a href="https://agentmods.dev/commands/griddynamics/rosetta/modernization-flow-crossproject"><img src="https://agentmods.dev/badge/commands/griddynamics/rosetta/modernization-flow-crossproject.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 | $0.00016 | $0.00835 |
| Opus 5 | $0.00008 | $0.00417 |
| Sonnet 5 | $0.00003 | $0.00167 |
| Haiku 4.5 | $0.00002 | $0.00084 |
Grade A, and why
modernization-flow-crossproject 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.
How it starts
The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Modernization Phase 5: Cross-Project Analysis
Phase Flow
Phase 5: Cross-Project Analysis
- Complete Phase 4 first
- Identify similarities and inconsistencies
- Document patterns across projects
- Map cross-project flows
- Document proxy patterns
- Cleanup assumptions and unknowns
- Identify migration priority order
- Create cross-project-analysis file
- Compact and re-validate
Context
PREREQUISITES: Complete Phase 4 (all class group analyses complete)
OBJECTIVES:
- Identify similarities and inconsistencies across projects
- Identify patterns used across projects
- Map cross-project usage and references
- Document proxy patterns and replacement opportunities
- Cleanup assumptions and unknowns
- Identify migration / modernization priority order
Implement Flow Phases
- Read all source files required
- Create
docs/cross-project-analysis.md - Update all
docs/original-code-specs-<lib/project>.md - Revalidate changes are complete, consistent, and full
Requirements
- MUST analyze ALL
docs/reference-code-specs-<lib/project>.mdfiles together - MUST analyze ALL
docs/original-code-specs-<lib/project>.mdfiles together (and update!) - MUST analyze both
docs/LEGACY-INTERFACES-CATALOG.md,docs/TODO.md(if they exist). - MUST create todo tasks for each phase and also split phase for each original code spec file to update. Also split validation phase as well.
- MUST update original-* files in place to add cross-project flows and dependencies, put direct references to reference-* and other original-* files.
- MUST create explicit follow-up tasks for ambiguities
- MUST create
docs/cross-project-analysis.mdas a single file! - MUST check assumptions and unknowns and cleanup those which are addressed (update respective parts of te original document and remove element completely from this section).
- MUST create tasks to compact used context of LLM, then tasks to re-read all files to perform full re-read and re-validation of contents to be completed work. Do not output new file or any summary, just fix gaps, issues, inconsistencies.
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 · 101 lines · 16 tokens per session scan A 00b663cf0c83
modernization-flow-crossproject is a command published in the GitHub repository griddynamics/rosetta (342 stars, last pushed today), licensed Apache-2.0. It adds 16 tokens to every session and 835 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.
validate-fix
Validate a proposed React fix with React-Sentinel assertions or replay checks.
rclone_mkdir
Make the path if it doesn't already exist.