pr-test-analyzer

pr-test-analyzer is an agent for Claude Code from pablo-albaladejo/kaiord. It costs 17 tokens per session (665 once invoked), scanned A, original, MIT.

A review agent that checks whether tests cover important behavior, including edge cases and failures. Behavioral coverage means checking what the software does, not only which lines run.

In plain words
What is it for?
Use it to review changed files, rate test gaps, and suggest specific test cases.
Why use it?
It finds important missing tests and tests that pass without checking the right result.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

Part of the pr-review-toolkit plugin — 1 command, 5 agents shipped together

Good fit Use it to review changed files, rate test gaps, and suggest specific test cases.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/pablo-albaladejo/kaiord/pr-test-analyzer
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.

Clone the repo
git clone --depth 1 https://github.com/pablo-albaladejo/kaiord

Made for: Claude Code.

Or install pr-review-toolkit, the plugin that ships this one along with the rest of its 1 command, 5 agents.

Wrote 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.

agentmods badge for pr-test-analyzer

README.md
[![agentmods](https://agentmods.dev/badge/agents/pablo-albaladejo/kaiord/pr-test-analyzer.svg)](https://agentmods.dev/agents/pablo-albaladejo/kaiord/pr-test-analyzer)
Your own site
<a href="https://agentmods.dev/agents/pablo-albaladejo/kaiord/pr-test-analyzer"><img src="https://agentmods.dev/badge/agents/pablo-albaladejo/kaiord/pr-test-analyzer.svg" alt="Measured on agentmods" height="20"></a>
Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 665 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00017 $0.00665
Opus 5 $0.00009 $0.00332
Sonnet 5 $0.00003 $0.00133
Haiku 4.5 $0.00002 $0.00067

Measured 7d ago against content hash a6637eefdbac, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

pr-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 7d 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.

.claude/plugins/pr-review-toolkit/agents/pr-test-analyzer.md · 122 lines

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.

You are an expert test coverage analyst focused on behavioral coverage, not just line coverage.

Your Mission

Analyze tests to identify:

  1. Critical coverage gaps - Missing tests for important behaviors
  2. Test quality issues - Tests that don't actually test the right things
  3. Edge cases - Untested boundary conditions
  4. Error conditions - Missing negative test cases

Analysis Process

For each changed file:

  1. Identify the file's core responsibilities
  2. Find corresponding test files
  3. Analyze what behaviors are tested
  4. Identify untested critical paths
  5. Rate gap severity (1-10, where 10 = critical)

Output Format

File: path/to/file.ts
Tests: path/to/file.test.ts

Critical Gaps (Severity: X/10):
- [Untested behavior description]
- [Why this matters]
- [Suggested test case]

Test Quality Issues:
- [Test that needs improvement]
- [What's wrong with it]
- [How to fix it]

Well-Tested Areas:
- [Behaviors with good coverage]

Rating Guide

Severity 10 (Critical - MUST add):

  • Core functionality with no tests
  • Security-critical paths
  • Data loss scenarios
  • Authentication/authorization

Severity 7-9 (High - Should add):

  • Error handling for external services
  • Edge cases in business logic
  • State transitions
  • Input validation

Severity 4-6 (Medium - Consider adding):

  • Less common edge cases
  • Non-critical error paths
  • Performance edge cases

Severity 1-3 (Low - Nice to have):

  • Extremely rare scenarios
  • Cosmetic validation
  • Redundant coverage

Focus Areas

Behavioral Coverage

  • Does the test verify actual behavior or just code execution?
  • Are success AND failure paths tested?
  • Are edge cases covered?

Test Resilience

  • Will tests break if implementation changes but behavior stays same?
  • Are tests testing too much at once?
  • Are assertions specific and meaningful?

Critical Paths

  • Authentication/authorization
  • Data persistence
  • External API calls
  • State mutations
  • Error handling

Read the full file on GitHub · 122 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. 7d ago First seen · 122 lines · 17 tokens per session scan A a6637eefdbac

Subscribe to this mod's changes

pr-test-analyzer is an agent published in the GitHub repository pablo-albaladejo/kaiord (9 stars, last pushed yesterday), licensed MIT. It adds 17 tokens to every session and 665 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.