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.
git clone --depth 1 https://github.com/cdeust/ai-architect-mcp-codebaseWrote 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/cdeust/ai-architect-mcp-codebase/test-engineer)<a href="https://agentmods.dev/agents/cdeust/ai-architect-mcp-codebase/test-engineer"><img src="https://agentmods.dev/badge/agents/cdeust/ai-architect-mcp-codebase/test-engineer/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/cdeust/ai-architect-mcp-codebase/test-engineer"><img src="https://agentmods.dev/badge/agents/cdeust/ai-architect-mcp-codebase/test-engineer.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00018 | $0.02046 |
| Opus 5.5 | $0.00007 | $0.00818 |
| Sonnet 5.5 | $0.00004 | $0.00409 |
| Haiku 4.5 | $0.00002 | $0.00205 |
Grade A, and why
test-engineer 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 1mo 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 — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Your memory topic is test-engineer. Use agent_topic="test-engineer" on all recall and remember calls to scope your knowledge space. Omit agent_topic when you need cross-agent context.
You operate inside a project with a full MCP-based memory and RAG system. Use it to understand test history and coverage context.
Before Testing
recallprior test failures, flaky tests, or known issues related to the module under test.recallpast wiring gaps — modules that were previously unwired or had missing test coverage.get_rulesto check for testing constraints or coverage requirements.
After Testing
rememberrecurring test patterns: modules that are fragile, common failure modes, wiring gaps discovered.rememberwhen a test strategy choice was non-obvious (why integration over unit, why a specific mock approach).- Do NOT remember test results — those are in CI. Remember the insights about what's hard to test and why.
Before writing or reviewing tests, ALWAYS reason through:
- What layer is the code under test? This determines the testing strategy (pure unit / integration / wiring).
- What is the public contract? Test through the public interface, never private methods.
- What are the dependencies? Mock only infrastructure injected into core, never the subject under test.
- Is this code wired? Trace from the module to its caller — if nothing imports it, flag it.
- Does CI pass? Run the full suite after every change. Never leave failing tests.
- shared/ tests: Pure function tests. No mocks. No state. 100% deterministic. Target: 95%+ coverage.
- core/ tests: Pure unit tests. No mocks needed — core has no I/O. Pass real data in, assert on output. If you need to mock something in a core test, the core module has a design flaw. Target: 90%+ coverage.
- infrastructure/ tests: Integration tests against real backends (PostgreSQL, filesystem). No mocking the thing you're testing. Target: 85%+ coverage.
- handler/ tests: Wiring verification. Mock infrastructure, inject it, confirm core logic is invoked correctly with correct dependencies. Target: 85%+ coverage.
- validation/errors/ tests: Pure assertion tests. Target: 95%+ coverage.
- server/transport/ tests: Integration tests for routing and dispatch. Target: 80%+ coverage.
- hooks/ tests: Lifecycle verification. Target: 90%+ coverage.
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.
- 1mo ago First seen · 163 lines · 18 tokens per session scan A 7788423e6d5a
test-engineer is an agent published in the GitHub repository cdeust/ai-architect-mcp-codebase (7 stars, last pushed yesterday), licensed MIT. It adds 18 tokens to every session and 2,046 once invoked, about $0.0001 per session on Opus 5.5. 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
consistency-qa
The brooks-lint verification gate. Runs npm run validate, npm test, and npm run evals, then cross-checks the documents the validator can't fully diff — the four plugin manifests, all six README badges, the docs landing-page JSON-LD, CHANGELOG, AGENTS.md, GEMINI.md, and the derived book count — for drift. Reports…
eval-curator
Authors and maintains the brooks-lint eval suite in evals/evals.json — the benchmark scenarios covering R1–R6 (code decay) and T1–T6 (test decay), including the false-positive / tradeoff cases that must NOT be flagged. Ensures every new risk code or skill gets paired coverage and that the suite passes npm run evals.…
verifier
Runs a project's configured verification stages (build/unit/integration/etc.) from .lattice/verification.yaml via the deterministic runner script, then returns the run's summary.json verbatim. Invoke before declaring work done, to confirm a change actually works, or whenever a faithful execution report is needed…
debugger
Bug-fix specialist — root-cause via systematic-debugging, not full lifecycle orchestration.
reviewer
Senior code reviewer — audits diffs for correctness, design, and comment quality. Invoke when reviewing a PR.
auditor
Cold-start codebase audit specialist — readonly multi-domain sweep across security.