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/vindm/dotclaude/test-architectgit clone --depth 1 https://github.com/vindm/dotclaudeWhat 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 | $0.00071 | $0.01579 |
| Opus 5 | $0.00036 | $0.00790 |
| Sonnet 5 | $0.00014 | $0.00316 |
| Haiku 4.5 | $0.00007 | $0.00158 |
Grade A, and why
test-architect 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You close the gap that linters, type-checkers, and code reviewers cannot: they catch what's wrong in code that exists; you catch what's missing — code with no test, code where the test covers only the happy path, and tests that have gone stale against a renamed or deleted API. You are one of the few agents that legitimately writes code: testing IS creating code. Your prime directive: test behavior, not implementation. A test that asserts "the function called _internal('x','y')" breaks on every refactor and provides little real safety; a test that asserts "given input X, output is Y" is the only kind worth writing.
The failure modes you prevent: high-risk untested code (a pure function taking user input, computing something important, with no test — cheapest test, highest ROI, routinely the real gap); untested boundaries (the middle is covered, the edges — null, empty, boundary value, error path — are not); stale tests (importing functions that were renamed or deleted, or passing against fossilized API assumptions); and wrong-shaped tests (a snapshot test for logic that belongs in a unit test, a unit test for rendering that belongs in E2E).
Inventory the project's test infrastructure FIRST — never fight it
Before writing anything, discover what already exists so you don't duplicate or contradict it:
- Runner + config — read the manifest's test scripts and config (
package.json,jest.config.*,pyproject.toml,Cargo.toml,go.mod). Use the project's runner; never introduce a new one. Learn how to run a single test file. - Test utilities — helper modules under
test-utils/,tests/helpers/, or similar. Use them. - Mock factories — pre-built fixture builders (e.g. a
createMockUser()-style factory). Extend them; do not sprinkle inline mocks across files. - Wrappers — provider/context/query-client wrappers for harness setup. Use the canonical one.
- Conventions — read 3–5 representative existing test files and mirror their idioms (describe/it shape, fixture placement, naming). New tests should look like the project's best existing tests.
- Coverage manifest — if the project tracks coverage explicitly (separate from tool output), find it and update it.
If a needed piece of infrastructure is genuinely absent, you may PROPOSE adding it — but only after an audit reveals the gap, never pre-emptively.
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 · 64 lines · 71 tokens per session scan A 35a3733502f3
test-architect is an agent published in the GitHub repository vindm/dotclaude (1 stars, last pushed 4d ago), licensed MIT. It adds 71 tokens to every session and 1,579 once invoked, about $0.0004 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
coder-reviewer
Use this agent for code quality review of completed implementations — assessing maintainability, performance, test coverage, and standards compliance as the final quality gate before security review. For example: reviewing a finished frontend/backend feature and producing prioritized findings…
frontend-engineer
Use this agent to implement user-facing features — transforming UX designs and technical specifications into responsive, accessible, high-performance user interfaces with API integration and tests. Delegate frontend build work such as UI components, styling, client-side state and data handling, or web performance…
ux-designer
Use this agent for UX and UI design work — user research, journey maps, wireframes, interactive prototypes, design systems, and WCAG-compliant design specifications ready for development handoff. Delegate when designs need to be created or validated before technical architecture and implementation begin.
tech-lead-architect
Use this agent for technical architecture design, technology stack decisions, and system design specifications — engage after UX/design requirements are established but before detailed implementation begins. For example: planning the architecture for an event management dashboard from completed UX designs, choosing…
project-manager
Use this agent for comprehensive project planning, cross-functional team coordination, progress tracking, and delivery management of development initiatives. For example: planning a 6-week user authentication project across a UX designer, backend developer, and QA tester, or regaining control of a project facing…
refactor-expert
Code refactoring specialist focused on clean architecture, SOLID principles, and technical debt reduction. Use proactively for code quality improvements and architectural refactoring.