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/testgen-flow-test-case-generationgit 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/testgen-flow-test-case-generation)<a href="https://agentmods.dev/commands/griddynamics/rosetta/testgen-flow-test-case-generation"><img src="https://agentmods.dev/badge/commands/griddynamics/rosetta/testgen-flow-test-case-generation.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 | $0.00017 | $0.03764 |
| Opus 5 | $0.00009 | $0.01882 |
| Sonnet 5 | $0.00003 | $0.00753 |
| Haiku 4.5 | $0.00002 | $0.00376 |
Grade A, and why
testgen-flow-test-case-generation 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 — 312 lines — stays where its author put it; the contents beside it link to each section on GitHub.
<testgen_flow_test_case_generation>
<description_and_purpose> Generate comprehensive test cases from the requirements document, covering all requirement types with appropriate test scenarios. Merge redundant cases via parameterization, build coverage matrix. </description_and_purpose>
<workflow_context>
- Phase 5 of 7 in
testgen-flow - Input:
requirements.mdfrom Phase 4 - Output:
test-scenarios.md— test cases - Required skills:
qa-knowledge(scenario_designmode + config-resolved TMS FORMAT binding) - Recommended skills:
coding(for any tracked write outside the ticket folder; read repo standards as authority) - Prerequisite: Phase 0-4 complete with validated requirements </workflow_context>
<phase_steps>
- Load requirements
- Identify test scenario types per requirement
- Generate test cases in TMS format
- Prioritize test cases
- Merge redundant test cases
- Build traceability and coverage
- Create test cases document
- Update traceability in requirements
- Update state file </phase_steps>
<load_requirements step="5.1">
- Read
plans/testgen-{TICKET-KEY}/requirements.md - Extract all user stories (US-N), functional requirements (FR-N), non-functional requirements (NFR-N) with acceptance criteria
- Extract constraints and dependencies that affect test design </load_requirements>
<identify_test_types step="5.2"> For each requirement, determine test scenario types needed:
- Happy Path: primary flow, all valid inputs, all preconditions met
- Edge Cases: boundary values (min, max, zero, empty), special characters, large data sets
- Negative Tests: invalid inputs, missing required fields, unauthorized access, timeouts
- Integration Tests: external system interactions, API calls, database operations
- Performance Tests (for NFRs): load, stress, concurrent users, response time
- Security Tests (for security NFRs): auth failures, authorization violations, injection, XSS
Scope guard: generate Performance and Security test types ONLY when the requirements / NFRs specify a constraint in that category — never invent injection / XSS / load tests without a source requirement (mirrors the Phase 4 NFR coverage-discipline: cover only what the sources specify, do not pad).
Common patterns for minimum coverage:
CRUD Operations (4+ scenarios):
- Create with valid data (Happy Path)
- Read existing record (Happy Path)
- Update existing record (Happy Path)
- Delete record (Happy Path)
- Create with invalid data (Negative)
- Read/Update/Delete non-existent record (Negative)
Authentication (5+ scenarios):
- Login with valid credentials (Happy Path)
- Login with invalid password (Negative)
- Login with non-existent user (Negative)
- Login after account locked (Negative)
- Logout successfully (Happy Path)
API Calls (4+ scenarios):
- Successful request with valid data (Happy Path)
- Request with invalid data (Negative)
- Request with missing auth token (Negative)
- Request with network timeout (Negative) </identify_test_types>
<generate_test_cases step="5.3" subagent="engineer" role="Test case design engineer">
Resolve the TMS FORMAT provider first (merge evidence — do NOT hardcode the vendor): read the TMS provider from plans/testgen-{TICKET-KEY}/testgen-project-config.md (data sources / provider fields written by Phase 0, prefilled from gain.json sdlc.test_management(_project)), explicit user input (wins for this run), or a recognizable TMS URL/handle; conflicting evidence → ask about the TMS only. The resolved provider (e.g. testrail, the canonical example) is passed to qa-knowledge (scenario_design mode) for the vendor-specific case format (the skill loads its own <vendor>-format binding internally). If no provider resolves but a TMS is clearly in scope, re-read config; if still absent, fall back to the inline <tc_schema> template below (record the fallback per <failure_handling>).
- USE SKILL
qa-knowledge(scenario_designmode) passing the resolved TMS provider for the test case format. - Create 2-5 test cases per requirement covering different test types from step 5.2.
- Apply
<format_rules>(forbidden fields),<tc_schema>(field-level template), and<title_quality>(naming) sub-blocks below.
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 · 312 lines · 17 tokens per session scan A 6c8cceb55489
testgen-flow-test-case-generation is a command published in the GitHub repository griddynamics/rosetta (342 stars, last pushed today), licensed Apache-2.0. It adds 17 tokens to every session and 3,764 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.