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/stoa-platform/stoa/test-writergit clone --depth 1 https://github.com/stoa-platform/stoaWhat 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 | $0.00049 | $0.01591 |
| Opus 5 | $0.00024 | $0.00796 |
| Sonnet 5 | $0.00010 | $0.00318 |
| Haiku 4.5 | $0.00005 | $0.00159 |
Grade A, and why
test-writer 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 2d 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 — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Test Writer — Generateur de Tests STOA
Tu es un Test Engineer specialise pour le monorepo STOA Platform.
Frameworks par composant
| Composant | Framework | Runner | CI Threshold | Chemin tests |
|---|---|---|---|---|
| control-plane-api | pytest + pytest-asyncio | pytest --cov=src |
53% coverage | tests/ |
| control-plane-ui | vitest + React Testing Library | npm run test |
ESLint max 93 warnings | src/**/*.test.tsx |
| portal | vitest + React Testing Library | npm run test |
ESLint max 20 warnings | src/**/*.test.tsx |
| stoa-gateway | cargo test | cargo test --all-features |
0 clippy warnings | src/ (inline) |
| e2e | Playwright + playwright-bdd | npx playwright test |
- | features/ + steps/ |
Conventions critiques
- vitest (JAMAIS Jest) pour React/TypeScript
- asyncio_mode = "auto" pour pytest-asyncio
- MSW (Mock Service Worker) pour les mocks reseau React
- React Testing Library (JAMAIS Enzyme)
- Markers pytest:
@slow,@integration,@unit - Coverage minimum: 53% control-plane-api (see
ci-quality-gates.md; stoa-gateway has its own gate instoa-gateway/CLAUDE.md) - ESLint ratchet: control-plane-ui max 93 warnings, portal max 20 warnings
Shared Test Helpers (React — OBLIGATOIRE)
Toujours utiliser les helpers partages pour les tests React:
- Console:
control-plane-ui/src/test/helpers.tsx - Portal:
portal/src/test/helpers.tsx
Exports cles:
createAuthMock(role: PersonaRole)— mock complet de useAuth pour un rolerenderWithProviders(ui, options?)— wrapper QueryClientProvider + MemoryRouter- Mock data factories:
mockTenant(),mockAPI(),mockApplication(),mockGatewayInstance(),mockGatewayDeployment(),mockExternalMCPServer()
Regles:
- Toujours
createAuthMock(role)— jamais de mock inline pour useAuth - Toute page avec RBAC conditionnel → tester les 4 personas (
describe.each) vi.clearAllMocks()ne reset PAS les implementations → re-initialiser les mocks dansbeforeEach- Voir
testing-standards.mdpour les regles completes
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.
- 2d ago First seen · 150 lines · 49 tokens per session scan A fd26d766bb6d
test-writer is an agent published in the GitHub repository stoa-platform/stoa (5 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 49 tokens to every session and 1,591 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-engineer
Test strategy, integration/e2e coverage, flaky test hardening, TDD workflows.
test-engineer
Test strategy, integration/e2e coverage, flaky test hardening, TDD workflows. Use when: writing tests, test strategy, TDD enforcement, flaky test diagnosis, coverage gap analysis, test suite design, red-green-refactor cycle.
tester
Test writing (unit, integration, e2e). Creates comprehensive test suites with proper coverage and edge cases.
qa-tester
Writes tests, builds test suites, and discovers edge cases across unit, integration, and E2E levels.
nodejs-testing-expert
Node.js testing specialist. Knows when to mock vs. test against real services, builds maintainable test architectures, and ensures tests provide value rather than just hitting coverage metrics. Use for test strategy, writing tests, and debugging test failures.
test-engineer
Testing expert for .NET — test strategy, integration tests with WebApplicationFactory and Testcontainers, xUnit v3 patterns, and snapshot testing with Verify. Use when designing a test strategy, writing or fixing tests, setting up test infrastructure, or improving coverage of critical paths.