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-exportgit 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-export)<a href="https://agentmods.dev/commands/griddynamics/rosetta/testgen-flow-test-case-export"><img src="https://agentmods.dev/badge/commands/griddynamics/rosetta/testgen-flow-test-case-export.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 | $0.02875 |
| Opus 5 | $0.00009 | $0.01437 |
| Sonnet 5 | $0.00003 | $0.00575 |
| Haiku 4.5 | $0.00002 | $0.00287 |
Grade A, and why
testgen-flow-test-case-export 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 — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
<testgen_flow_test_case_export>
<description_and_purpose>
Export test cases from test-scenarios.md to a Test Management System (TMS) via MCP, mapping priorities, types, and structured steps. If TMS MCP unavailable, offer user alternatives (manual copy, CSV, etc.).
</description_and_purpose>
<workflow_context>
- Phase 6 of 7 in
testgen-flow - Input:
test-scenarios.mdfrom Phase 5 - Output: test cases created in TMS
- Prerequisite: Phase 5 complete, user reviewed test cases, TMS MCP configured
- HITL: user must provide target location in TMS (e.g., section, folder, suite)
- Required skills:
qa-knowledge(scenario_designmode) with the resolved TMS EXPORT provider (e.g.testrail, the canonical example) for connection, field mappings, and API details - Recommended skills:
coding(when updating tracked repository markdown such astest-scenarios.mdwith TMS IDs — read repo standards as authority),hitl(destructive-write confirmation) </workflow_context>
<phase_steps>
- Activate
coding(if updating tracked files) and resolve the TMS EXPORT vendor binding - Verify TMS connection via MCP
- Get target location from user
- Parse test cases from markdown
- Map to TMS format using skill mappings 5b. Destructive-write gate: dedup pre-scan + confirm-before-write (step 6.4b)
- Export test cases via TMS MCP (remember to put pre-conditions, if not possible - create zero step as pre-conditions)
- Update documents with TMS IDs
- Write
export-report.md(TMS IDs/URLs, per-case status, timestamp) - Update state file </phase_steps>
<identify_skill step="6.1">
This phase OWNS the export contract — what gets pushed (the approved case set from test-scenarios.md), ID handling (vendor-format case IDs written back per step 6.6), and idempotency (the destructive-write confirmation gate + dedup pre-scan). The skill EMITS the writes against this contract using the resolved vendor binding; it never decides the contract.
- If updating tracked repository files (for example embedding TMS IDs into
test-scenarios.mdunder version control): USE SKILLcodingfirst (read repo standards as authority; repo docs win). - Resolve the TMS EXPORT provider (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 fromgain.jsonsdlc.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 toqa-knowledge(scenario_designmode) for the vendor-specific export contract (the skill loads its own<vendor>-exportbinding internally). - If no provider resolves but a TMS is clearly in scope, re-read config; if still absent, the export cannot run on the integration path → fall through to the step 6.2 fallbacks (manual copy / CSV / defer).
- USE SKILL
qa-knowledge(scenario_designmode) passing the resolved EXPORT provider. All subsequent steps use the connection check, field mappings, API calls, and ID formats it defines for that provider. </identify_skill>
<verify_connection step="6.2">
- Test TMS MCP connection using the method defined in the resolved EXPORT binding
- On connection failure: inform user, verify MCP config and credentials. Retry once. On a second failure, present the documented alternatives below and let the user choose; do not silently abort:
- Manual copy: export the test cases as plain markdown for the user to paste into the TMS UI. Artifact: keep
plans/testgen-{TICKET-KEY}/test-scenarios.mdas-is; record the user's confirmation of manual export inexport-report.md(see step 6.6). - CSV export: generate
plans/testgen-{TICKET-KEY}/test-scenarios.csvwith one row per test case (columns:TC_ID,Title,Priority,Type,Source_Requirements,Preconditions,Steps,Expected_Result,Tags). Record the CSV path + row count inexport-report.md. - Defer: mark Phase 6 as
BLOCKED — TMS unavailableintestgen-state.mdand stop, awaiting user to fix MCP access.
- Manual copy: export the test cases as plain markdown for the user to paste into the TMS UI. Artifact: keep
- On chosen fallback: the corresponding artifact path becomes the on-disk evidence of Phase 6 (replacing the TMS-IDs receipt section of
export-report.md). Still writeexport-report.mdper the step 6.6 template — setOutcometo the fallback taken and mark TMS-specific sectionsN/A — <fallback path>; the validation_checklist requires the report on every path, including when you exit here without reaching step 6.6 on the happy path. </verify_connection>
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 · 159 lines · 17 tokens per session scan A 6f75c2ef8728
testgen-flow-test-case-export 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 2,875 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.