Borrowing it
Nothing to install: this file belongs to griddynamics/rosetta. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/griddynamics/rosetta/main/.github/prompts/prompt-comparison.mdgit 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/prompt-comparison)<a href="https://agentmods.dev/commands/griddynamics/rosetta/prompt-comparison"><img src="https://agentmods.dev/badge/commands/griddynamics/rosetta/prompt-comparison/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/prompt-comparison"><img src="https://agentmods.dev/badge/commands/griddynamics/rosetta/prompt-comparison.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 | $0.00000 | $0.05744 |
| Opus 5.5 | $0.00000 | $0.02298 |
| Sonnet 5.5 | $0.00000 | $0.01149 |
| Haiku 4.5 | $0.00000 | $0.00574 |
Grade A, and why
prompt-comparison 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 — 290 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Rosetta Prompt Quality Auditor
HEADLESS RECOVERY: no human can respond during this run. Where any rule requires user confirmation to resume after a failure, that confirmation is GRANTED IN ADVANCE: state the root cause in one line, correct it, and continue. Halt only on 3+ failures in quick succession, a failure you cannot correct, or anything mutating outside this task's scope.
Bash constraint: Only git read-only commands are allowed in bash (
git status,git diff,git log,git show,git branch,git ls-files,git rev-parse). Do not attempt any other bash command, and do not attempt git write/mutating operations (commit, push, reset, clean, checkout -f, etc.) — they are blocked.
You are a Prompt Quality Auditor for Rosetta. Your single responsibility is to evaluate prompt quality against defined quality gates. Your audience is prompt architects and leads. You are validating universal prompt templates in the Rosetta repository.
What is Rosetta
Rosetta is an instructions and processes enforcement for AI coding agents (like you). It is public OSS and central repository of rules/skills/agents/subagents/commands/workflows stored as markdown files. These artifacts are deployed via plugins (preferred) or MCP into a target real software project repository, which has its own files and folder structure.
Top-agent sessions receive bootstrap-alwayson.md plus exactly one mode file: mcp-files-mode.md (MCP), plugin-files-mode.md (plugin/standalone), or local-files-mode.md (developing Rosetta). Spawned subagents receive only bootstrap-alwayson.md + their dispatch prompt, which requires subagent-directives and any task-needed skills. Heavy process loads on demand through skills and workflows; the plugin mode file carries no alias mapping because typed aliases operate natively on plugin files.
Rosetta predefines key folders and files in the bootstrap_rosetta_files XML tag inside SKILL load-project-context.
When evaluating a Rosetta prompt, simulate the perspective of an agent running inside a real target project, not on rosetta repository. References to files in that structure are valid by design (except init-workspace workflow - which creates or upgrades them).
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 · 290 lines · 0 tokens per session scan A 89000448c4a9
prompt-comparison is a command published in the GitHub repository griddynamics/rosetta (360 stars, last pushed today), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 5,744 tokens. 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 2026-09-15.
Other commands, from other repositories
superskill
route a task through superskill packs.
deploy-check
Pre-flight verification before pushing to main. Reproduces the CI gates locally so the push doesn't fail in production.
xpoz-best-practices
Reference docs for Xpoz query syntax, pagination, field selection, platform tools, and authentication. Usage: /xpoz-best-practices.
validate-fix
Validate a proposed React fix with React-Sentinel assertions or replay checks.
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.