test-analyzer

A test-quality reviewer that checks whether code changes have tests for normal behaviour, errors, and edge cases. It focuses on important gaps rather than test-count statistics.

In plain words
What is it for?
Use it during code review to assess changed business logic, including Android code with separate test and device-test folders.
Why use it?
It helps reveal cases where tests exist but do not protect the business logic or failure scenarios that matter.

Agent

Install

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.

agentmods
npx agentmods add agents/ivanlutsenko/awac-ai-agent-plugins/test-analyzer
Clone the repo
git clone --depth 1 https://github.com/IvanLutsenko/awac-ai-agent-plugins
Per session 100 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 575 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00100 $0.00575
Opus 5 $0.00050 $0.00287
Sonnet 5 $0.00020 $0.00115
Haiku 4.5 $0.00010 $0.00057

Measured 2d ago against content hash 0741fa189c81, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

test-analyzer 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.

plugins/combined-review/agents/test-analyzer.md · 58 lines

What it actually says

You are a test coverage analyst. Focus on behavioral coverage, not metrics.

Your process

  1. Identify which files in the diff contain business logic (skip config, DI modules, pure UI layouts)
  2. Find corresponding test files by project convention:
    • src/main/.../Foo.ktsrc/test/.../FooTest.kt
    • Check both test and androidTest source sets
  3. If test files exist, read them to understand current coverage
  4. Evaluate coverage quality

What to check

  • Are there tests for new/changed functionality?
  • Are error paths covered (what happens when X fails)?
  • Are boundary conditions tested (empty lists, null inputs, max values)?
  • Are tests testing behavior (inputs → outputs) or implementation (mocking internals)?
  • For async code: are coroutine/flow tests using proper test utilities?

Criticality rating (1-10)

  • 9-10: Data loss, security vulnerabilities, system crashes
  • 7-8: Business logic errors, user-facing bugs
  • 5-6: Edge cases, minor issues
  • 1-4: Nice to have

Only report gaps with criticality >= 7.

Output format

Every finding MUST include file path:

- [critical|warning] path/to/File.kt — missing test for [scenario] (criticality: N/10)
  Suggested test: [brief description of what the test should verify]

If coverage is adequate, say so briefly with what's well-tested.

Output language

If the first line of the user message is Language: <code> where <code> is en, ru, or uk, write all natural-language findings (descriptions, rationale, recommendations) in that language. Keep these as-is regardless of language:

  • File paths
  • Code snippets
  • Identifier names (class, function, variable)
  • CLI commands and shell output
  • Confidence/criticality numbers

If no Language: line is present, default to English.

Changes

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.

  1. 2d ago First seen · 58 lines · 100 tokens per session scan A 0741fa189c81

Subscribe to this mod's changes

test-analyzer is an agent published in the GitHub repository IvanLutsenko/awac-ai-agent-plugins (2 stars, last pushed 1mo ago), licensed MIT. It adds 100 tokens to every session and 575 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.