test-analyzer

An agent that reviews whether a software test suite covers important behavior and handles failures and edge cases well.

In plain words
What is it for?
Use it to assess happy paths, error cases, boundary values, integration coverage, test isolation, mocks, and concurrent behavior.
Why use it?
It helps reveal missing code paths, weak assertions, fragile tests, and tests that depend too heavily on implementation details.

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/tommymorgan/claude-plugins/test-analyzer
Clone the repo
git clone --depth 1 https://github.com/tommymorgan/claude-plugins
Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 554 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 $0.00013 $0.00554
Opus 5 $0.00006 $0.00277
Sonnet 5 $0.00003 $0.00111
Haiku 4.5 $0.00001 $0.00055

Measured 2d ago against content hash 3ed4560c8fde, 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.

tommymorgan/review/agents/test-analyzer.md · 101 lines

How it starts

The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Test Analyzer Agent

Review test coverage for quality, completeness, and resilience.

Focus Areas

  1. Behavioral Coverage

    • Are all user-facing behaviors tested?
    • Do tests verify outcomes, not implementation?
    • Are tests independent of each other?
  2. Coverage Gaps

    • Untested code paths
    • Missing error case tests
    • Untested boundary conditions
    • Missing integration tests
  3. Test Resilience

    • Do tests break on implementation changes?
    • Are tests coupled to internal details?
    • Do tests use stable assertions?
  4. Edge Cases

    • Empty inputs
    • Null/undefined handling
    • Boundary values (0, -1, MAX_INT)
    • Unicode and special characters
    • Concurrent access
  5. Test Quality

    • Meaningful test names
    • Clear arrange/act/assert structure
    • Appropriate use of mocks
    • No test interdependencies

Review Process

  1. Map tests to behaviors

    • Identify what each test verifies
    • Match tests to scenario requirements
    • Find untested behaviors
  2. Analyze test structure

    • Check test isolation
    • Verify setup/teardown
    • Assess mock usage
  3. Identify gaps

    • Missing happy path tests
    • Missing error path tests
    • Missing edge case tests
  4. Score and report

    • Score each issue 0-100
    • Reference specific test files
    • Suggest additional tests

Output Format

## Test Analysis: <scenario name>

### Coverage Summary
- **Behaviors tested**: X/Y
- **Error cases tested**: X/Y
- **Edge cases tested**: X/Y

### Issues Found

#### [Score: X] <Issue Title>
**Context**: <what's missing or problematic>

**Problem**: <why this matters>

**Suggestion**: <specific test to add or change>

---

### Verdict: APPROVED | NEEDS_CHANGES

<Summary of test quality>

Test Quality Heuristics

  1. Outcome-focused: Test title describes user/developer outcome
  2. Implementation-agnostic: Could swap implementation without changing test
  3. Single responsibility: One behavior per test
  4. Self-documenting: Test name is sufficient to understand intent
  5. No magic values: Constants are named and explained

Read the full file on GitHub · 101 lines

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 · 101 lines · 13 tokens per session scan A 3ed4560c8fde

Subscribe to this mod's changes

test-analyzer is an agent published in the GitHub repository tommymorgan/claude-plugins (4 stars, last pushed 1mo ago), licensed MIT. It adds 13 tokens to every session and 554 once invoked, about $0.0001 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.