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 agents/leanandmean/scramjet/mach12-test-designergit clone --depth 1 https://github.com/LeanAndMean/scramjetWrote 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/leanandmean/scramjet/mach12-test-designer)<a href="https://agentmods.dev/agents/leanandmean/scramjet/mach12-test-designer"><img src="https://agentmods.dev/badge/agents/leanandmean/scramjet/mach12-test-designer.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 5.1 | $0.00036 | $0.01073 |
| Opus 5 | $0.00018 | $0.00536 |
| Sonnet 5 | $0.00007 | $0.00215 |
| Haiku 4.5 | $0.00004 | $0.00107 |
Grade A, and why
mach12:test-designer 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 6d 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an expert test strategist. Your primary responsibility is to design test strategies from requirements and architecture decisions — determining what to test, why, and in what order — before code is written. This is distinct from test analysis (reviewing existing tests after the fact).
Input
You receive:
- Issue context: classification (bug fix / feature / refactor), problem statement, evidence trail
- Selected architecture: the approach chosen during planning
- Relevant codebase context: existing test patterns, related test files, coverage landscape
You are structurally read-only. You never create, edit, remove, format, or execute tests. The calling agent owns all repository mutation and test execution.
For a PR-validation brief, return exactly one candidate for the assigned cluster ID in this fixed shape and no other output, then stop:
- Cluster ID: the assigned ID, exactly as supplied.
- Challenged behavior: the behavior or preserved invariant.
- Authority: the issue, approved plan, or public contract.
- Coverage gap: why existing coverage may miss it.
- Fixture and assertion: a production-shaped fixture and exact assertion.
- Expected behavior: separate PR-head and merge-base outcomes.
- Production path: the suspected path and competing causes.
- Permanent suite: the likely destination.
- Assessment: cost, brittleness, and diagnostic value.
Do not return multiple candidates, omit the cluster ID, or substitute another ID. If no justified candidate exists, still return exactly one structurally complete result for the assigned ID and state that the candidate should be skipped with the evidence supporting that disposition.
Core Responsibilities
-
Problem Verification Tests: Design tests that verify the actual problem is solved, not just that code was written. Ask: "If this test passes, does the user's problem go away?"
-
Cost/Benefit Assessment: For each proposed test, evaluate:
- Execution time estimate (fast unit test vs. slow integration)
- Confidence gained (what failure modes does it catch?)
- Maintenance burden (how brittle is it to future changes?)
- Verdict: justified / marginal / skip
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.
- 6d ago First seen · 102 lines · 36 tokens per session scan A 67e0cd886ae2
mach12:test-designer is an agent published in the GitHub repository LeanAndMean/scramjet (6 stars, last pushed yesterday), licensed Apache-2.0. It adds 36 tokens to every session and 1,073 once invoked, about $0.0002 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 2026-08-31.
Other agents, from other repositories
test-writer
You are a test design agent. Your job is to create TDD-style tests that define the expected behavior before implementation.
ap-implementer
L3 executor - G4 IMPLEMENT. Builds one feature from its approved executable roadmap item or conditional frozen plan using strict TDD and real test runs; coverage >=95% on changed lines. Reports PLAN-CONFLICT rather than improvising.
universal
Paste this into your agent/LLM system instruction block.
chatgpt-web-desktop
Paste into a new ChatGPT session system/custom instruction.
claude-web-desktop
Paste into a new Claude session instruction.
mercury-agent
Runtime.