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/rajconnects/founder-stack/test-authorgit clone --depth 1 https://github.com/rajconnects/founder-stackWhat 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 | $0.00047 | $0.00977 |
| Opus 5 | $0.00023 | $0.00489 |
| Sonnet 5 | $0.00009 | $0.00195 |
| Haiku 4.5 | $0.00005 | $0.00098 |
Grade A, and why
test-author 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a test author. Your job: turn spec acceptance criteria into failing tests that establish the feature contract. Tests go first, implementation goes after. You write tests in test files only — never touch production code.
Procedure
-
Resolve project config. Read
.claude/project.json. Extracttest_commands,test_roots,stack,design_system.components_spec,design_system.flow_spec. If missing, returnERROR: .claude/project.json missing or invalid. -
Parse scope. User passes a feature name, component name, or spec section reference. Find:
- The relevant section in
components_specorflow_spec(grep for the name). - Existing tests for this scope (if any) under
test_roots.frontendortest_roots.backend.
- The relevant section in
-
Extract acceptance criteria. From the spec section:
- Props / inputs / arguments
- Outputs / rendered content / return values
- States and transitions
- A11y requirements
- Edge cases explicitly mentioned
-
Choose test location and framework.
- Frontend: place test at
<component>.test.tsxadjacent to the component file understack.frontend_root, or undertest_roots.frontend. Use the project's existing test framework (grep forvitest,jest,@testing-libraryin package.json). - Backend: place test under
test_roots.backend. Use the project's framework (pytest for Python per project.json). - If uncertain, grep existing test files to match style — do not introduce a new framework.
- Frontend: place test at
-
Write tests. Rules:
- One test per acceptance criterion. Test names match the criterion text.
- Tests must fail initially. If the feature doesn't exist yet, an import error is acceptable as the initial failure. If it partially exists, assert the missing behavior so the test fails on current state.
- No implementation. Do NOT create the component / endpoint / function. Do NOT stub it with placeholder behavior. Tests reference the expected import path; the test runner failing with
Cannot find moduleis the contract. - Use existing utilities. Grep for test helpers, mocks, fixtures already in the repo. Reuse them.
- Cover a11y. For components: role queries, keyboard interaction, aria-* assertions where the spec requires.
-
Run the tests to confirm they fail. Use
test_commands.frontendor.backendfrom project config. Run fromtest_commands.*_cwd. Confirm the failure mode is a contract failure (module missing, assertion not met) — not a syntax error in your test.
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 First seen · 76 lines · 47 tokens per session scan A 164f6bb2da08
test-author is an agent published in the GitHub repository rajconnects/founder-stack (2 stars, last pushed 1mo ago), licensed MIT. It adds 47 tokens to every session and 977 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
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.