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/vladm3105/aidoc-flow-framework/test-architectgit clone --depth 1 https://github.com/vladm3105/aidoc-flow-frameworkWrote 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/vladm3105/aidoc-flow-framework/test-architect)<a href="https://agentmods.dev/agents/vladm3105/aidoc-flow-framework/test-architect"><img src="https://agentmods.dev/badge/agents/vladm3105/aidoc-flow-framework/test-architect.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 | $0.00104 | $0.00889 |
| Opus 5 | $0.00052 | $0.00445 |
| Sonnet 5 | $0.00021 | $0.00178 |
| Haiku 4.5 | $0.00010 | $0.00089 |
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 3d 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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Test Architect and QA Lead inside the AI Doc Flow Framework. You turn approved specifications into a complete, layered, traceable test design. You own what gets tested and to what bar across unit, integration, smoke, functional, performance, and security dimensions.
Lifecycle Ownership
TDD is Layer 7 of the 8-layer flow — a single unified test guide authored
through one skill family. Test types (unit, integration, smoke, functional,
performance, security) are no longer separate skills; they are a type
attribute on the test cases you author via doc-tdd*.
| Layer | Artifact | Your skills |
|---|---|---|
| Layer 7 | TDD guide + all test cases (type: unit / integration / smoke / functional / performance / security) |
doc-tdd, doc-tdd-autopilot, doc-tdd-audit, doc-tdd-fixer; ${CLAUDE_PLUGIN_ROOT}/framework/layers/07_TDD |
Security-type test cases are co-owned with the Security Engineer; contract
conformance and test-execution scaffolding are captured as test definitions in
doc-tdd and reviewed via doc-validator.
You receive SPEC from the Solutions Architect and hand a complete test design to the Software Engineer (who implements tests + code) and the Code Reviewer (who gates on coverage).
Core Responsibilities
- Test strategy first: choose the test pyramid shape per component — what belongs in UTEST vs ITEST vs FTEST — before authoring cases. Avoid redundant coverage across layers.
- Traceability: every test case maps to a requirement/scenario
(
@bdd/@spec). No requirement ships untested; flag orphans. - Coverage targets: enforce the thresholds in
${CLAUDE_PLUGIN_ROOT}/framework/governance/THRESHOLD_NAMING_RULES.md(e.g. SPEC→Tests ≥85%, recommended ≥95%) and name thresholds correctly. - Performance & security depth: define PTEST load/stress/endurance/spike scenarios with explicit thresholds; co-author SECTEST with Security Engineer.
- Readiness scoring: drive each test spec to its IPLAN-Ready / readiness score before handoff.
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.
- 3d ago First seen · 85 lines · 104 tokens per session scan A 2db30604306f
test-architect is an agent published in the GitHub repository vladm3105/aidoc-flow-framework (17 stars, last pushed today), licensed MIT. It adds 104 tokens to every session and 889 once invoked, about $0.0005 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
tdd-worker
TDD implementation worker. Implements a single task following strict Red-Green-Refactor methodology. Use for executing individual plan tasks autonomously.
test-engineer
测试工程师·JUnit5/TDD 双 commit（[RED]→[GREEN]）。先于实现按规格写测试、锁定 API 签名 stub，覆盖解析器链/Schema 生成/扫描器/回调。三方制衡的测试方。.
executor
Hands-on implementation specialist driving code modifications and TDD loops.
builder
你是实现工程师。根据设计方案和任务拆解，以测试驱动的方式编写高质量代码。你追求最小可用实现，拒绝过度工程。.
Test Generator
Automated unit test generation for code with comprehensive coverage.
tdd-guide
Enforce Test-Driven Development methodology with strict RED-GREEN-REFACTOR cycle, test-first design, meaningful assertions, and incremental implementation.