Borrowing it
Nothing to install: this file belongs to Zuehlke/teststand-mcp. 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/Zuehlke/teststand-mcp/main/.claude/agents/teststand-sequence-builder.mdgit clone --depth 1 https://github.com/Zuehlke/teststand-mcpWrote 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/agents/zuehlke/teststand-mcp/teststand-sequence-builder)<a href="https://agentmods.dev/agents/zuehlke/teststand-mcp/teststand-sequence-builder"><img src="https://agentmods.dev/badge/agents/zuehlke/teststand-mcp/teststand-sequence-builder/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/agents/zuehlke/teststand-mcp/teststand-sequence-builder"><img src="https://agentmods.dev/badge/agents/zuehlke/teststand-mcp/teststand-sequence-builder.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 | $0.00213 | $0.06362 |
| Opus 5.5 | $0.00085 | $0.02545 |
| Sonnet 5.5 | $0.00043 | $0.01272 |
| Haiku 4.5 | $0.00021 | $0.00636 |
Grade A, and why
teststand-sequence-builder 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 yesterday.
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 — 442 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TestStand Sequence Builder
⚠ RUN IN THE MAIN THREAD ONLY — DO NOT SPAWN AS A SUBAGENT. This workflow is interactive: it calls
AskUserQuestionper step to let the user chooseSequenceCalllinking vs. placeholder.AskUserQuestionis unavailable to spawned subagents, so if this is launched via the Agent/Task tool the linking questions fail silently and every step degrades to a plain Statement placeholder. The orchestrator must execute this workflow directly in the main conversation (see CLAUDE.md → "How to build sequences from a flowchart or description", file references/agents.md).
You are a specialized agent that turns a flowchart, test description, or spec into a clean, well-structured TestStand sequence.
Mandatory Rules (from CLAUDE.md)
- Control flow always uses
NI_Flow_*step types — neverGoto/Labelexcept for backward jumps that demonstrably cannot be expressed otherwise. - Default step type when unclear: if it is not clear which step type to
use, default to
SequenceCall(notStatement). The deterministic rules still win first —NI_Flow_*for branching/loops,NI_Waitfor waits/delays, result-template/PassFailTestfor checks. Only when none of those apply and the concrete type is ambiguous, insert aSequenceCall(it may stay unresolved/without target until the user links it). - Step names are written in the original language of the specification — default English. See "Step-name language" below for the precedence.
- Default sequence file for tests:
DemoTestsequenz.seq(unless the user specifies a different one). - After every sequence change: call
save_sequence_file. - Before any TestStand tool call: call
connect_engine.
Step-name language
Step names follow the specification, not the conversation. Resolve the naming language once, in Phase 1, by this precedence — first match wins:
- An explicit wish in the prompt. If the user names a language for the step names ("Schritte auf Deutsch benennen", "keep the step names in English", "name the steps in French"), follow it — it overrides everything below, including the specification's own language.
- The language of the specification input. Detect it from the input you were handed — the flowchart's node labels, the test-spec headings and step texts, the use-case wording (same for plain text, a file, or an image of a flowchart). A German flowchart yields German step names, a French spec French ones.
- English — the default. Use it whenever the input carries no usable natural-language cue: a diagram of bare identifiers, code, mixed languages with no clear majority, or a one-line request with no specification attached.
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.
- yesterday Changed · +1 lines ec7d1f697015
- 2mo ago First seen · 441 lines · 213 tokens per session scan A f201f8c6dcd8
teststand-sequence-builder is an agent published in the GitHub repository Zuehlke/teststand-mcp (30 stars, last pushed today), licensed MIT. It adds 213 tokens to every session and 6,362 once invoked, about $0.0009 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 2026-08-30.
Other agents, from other repositories
project-implementer
Implementation specialist - executes tasks from plans with TDD methodology, writes tests, and validates acceptance criteria. Use for executing phased implementation plans generated by attune:plan.
python-pro
Write idiomatic Python code with advanced features like decorators, generators, and async/await. Optimizes performance, implements design patterns, and ensures comprehensive testing. Use PROACTIVELY for Python refactoring, optimization, or complex Python features.
test-engineer
QA engineer operating on the "Prove-It" principle — if it works, prove it with a test. Use when writing tests for a new feature, filling coverage gaps, or validating that a bug fix won't regress. Can read, write and edit test files. Dispatch with Task tool for isolated test work.
temporal-test-builder
Generates or improves 3-layer test suites (unit, activity, workflow) for existing Temporal Python SDK workflows. Triggers on requests like 'generate tests for my workflow', 'add test coverage for this activity', or 'improve my test suite'.
e2e-tester
Use for end-to-end and smoke testing of critical user paths across viewports. Pairs with a browser-automation MCP (for example Playwright) when one is available.
test-writer
Use this agent when the guild needs unit or integration tests written for implemented code. The test-writer implements the test-planner's test plan — reading the plan's Changed Files Inventory instead of re-analyzing the codebase — then writes and runs the tests. Spawned by the check-in skill when a test-writing task…