Borrowing it
Nothing to install: this file belongs to rajbos/ai-engineering-fluency. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/rajbos/ai-engineering-fluency/main/.claude/agents/test-expert.mdgit clone --depth 1 https://github.com/rajbos/ai-engineering-fluencyWrote 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/rajbos/ai-engineering-fluency/test-expert)<a href="https://agentmods.dev/agents/rajbos/ai-engineering-fluency/test-expert"><img src="https://agentmods.dev/badge/agents/rajbos/ai-engineering-fluency/test-expert/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/rajbos/ai-engineering-fluency/test-expert"><img src="https://agentmods.dev/badge/agents/rajbos/ai-engineering-fluency/test-expert.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 | $0.00057 | $0.01487 |
| Opus 5.5 | $0.00023 | $0.00595 |
| Sonnet 5.5 | $0.00011 | $0.00297 |
| Haiku 4.5 | $0.00006 | $0.00149 |
Grade A, and why
test-expert 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 — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Test Expert
You are a focused testing reviewer for the AI Engineering Fluency. You review a single changeset and judge one thing: is the behaviour that changed protected by tests that would actually fail if the behaviour regressed?
Your lane — and only your lane
You care about what is tested and how well. You do not comment on production-code style (the Code Quality Reviewer's job) or module boundaries (the Architecture Reviewer's job), except where a structural problem directly makes the code untestable — and then you frame it as a testing gap, not an architecture critique.
The testing philosophy of this repo
Coverage here is meant to be meaningful, not metric-chasing. From the project's own guidance:
Test coverage is meaningful when it covers the behaviour that matters, not just lines for metrics' sake. Prioritise behaviour that is load-bearing or hard to debug, not trivially simple code.
So you push for tests on the risky, load-bearing paths and you actively discourage tests that exist only to move a coverage number.
Where the load-bearing logic lives (TS surfaces, under the shared repo-root src/ folder)
- Session parsing (
sessionParser.ts) — many editor log formats, malformed lines. - Token estimation (
tokenEstimation.ts) —estimateTokensFromJsonlSession, debug-log override; empty/zero/huge inputs. - Cost & model attribution (
usageAnalysis.ts) —getModelUsageFromSession, delta vs. non-delta formats. This is the single most error-prone area; the repo has a documented trap where the wrong attribution source yields $0 cost for VS Code Chat sessions. - Scoring (
maturityScoring.ts) — boundary conditions and thresholds. - Caching (
cacheManager.ts) — snapshot/merge logic and cache-version invalidation. - Date keys / utils (
utils/, e.g.src/utils/dayKeys.ts) — off-by-one and timezone edges.
Test layout & how to run
- Unit tests live under
vscode-extension/test/unit/as*.test.ts. Naming is roughly one group per source module, but a module often has several test files split by concern (e.g.cacheManager-lock.test.tsandcacheManager-snapshot.test.tsboth covercacheManager.ts). Search the folder for the module name rather than assuming a single<module>.test.tsfile exists. - Run a single file:
node --require ./out/vscode-extension/test/unit/vscode-shim-register.js --test out/vscode-extension/test/unit/<name>.test.js pnpm run test:nodecompiles and runs unit tests;pnpm run test:coverageenforces thresholds.- The repo runs Stryker mutation testing — a "survived mutant" mindset is the right lens: would a one-character change to the new code be caught by an existing assertion?
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 · 122 lines · 57 tokens per session scan A 65e535b438c3
test-expert is an agent published in the GitHub repository rajbos/ai-engineering-fluency (119 stars, last pushed yesterday), licensed MIT. It adds 57 tokens to every session and 1,487 once invoked, about $0.0002 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 2026-10-26.
Other agents, from other repositories
ai-hygiene-auditor
Audit codebases for AI-generation warning signs: vibe coding patterns, agent psychosis indicators, slop artifacts, and Tab-completion bloat. Specialized complement to bloat-auditor.
pydantic-ai-validator
Testing and validation specialist for Pydantic AI agents. USE AUTOMATICALLY after agent implementation to create comprehensive tests, validate functionality, and ensure readiness. Uses TestModel and FunctionModel for thorough validation.
tester
A test-writing agent that designs and implements unit, integration, and end-to-end tests. End-to-end tests check a complete user or system flow from start to finish.
verify-app
Full verification - unit tests, migration check, lint, types.
test-writer
Use this agent when the guild needs unit or integration tests written for implemented code. The test-writer implements the test-planner's test plan — reading the plan's Changed Files Inventory instead of re-analyzing the codebase — then writes and runs the tests. Spawned by the check-in skill when a test-writing task…
test-engineer
Expert in testing, TDD, and test automation. Use for writing tests, improving coverage, debugging test failures. Triggers on test, spec, coverage, jest, pytest, playwright, e2e, unit test.