cf-reviewer-tests

cf-reviewer-tests is an agent for Claude Code from dinhanhthi/coding-friend. It costs 45 tokens per session (598 once invoked), scanned A, original, MIT.

A test-coverage review agent that checks whether code changes have meaningful tests, including error cases, boundary conditions, and regression scenarios.

In plain words
What is it for?
Use it to review tests for changed code, assess missing branches and edge cases, and check whether tests would catch a bug if it returned.
Why use it?
It helps reveal new behavior that is untested or tests that pass without checking the behavior that matters.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter.

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is **CLI Requirement:** NONE — Works without `coding-friend-cli`. See [CLI requirements](../../docs/cli-requirements.md) for the full matrix..

Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/dinhanhthi/coding-friend
agentmods
npx agentmods add agents/dinhanhthi/coding-friend/cf-reviewer-tests

Made for: Claude Code.

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 cf-reviewer-tests

README.md
[![agentmods](https://agentmods.dev/badge/agents/dinhanhthi/coding-friend/cf-reviewer-tests.svg)](https://agentmods.dev/agents/dinhanhthi/coding-friend/cf-reviewer-tests)
Your own site
<a href="https://agentmods.dev/agents/dinhanhthi/coding-friend/cf-reviewer-tests"><img src="https://agentmods.dev/badge/agents/dinhanhthi/coding-friend/cf-reviewer-tests.svg" alt="Measured on agentmods" height="20"></a>
Per session 45 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 598 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 5.1 $0.00045 $0.00598
Opus 5 $0.00023 $0.00299
Sonnet 5 $0.00009 $0.00120
Haiku 4.5 $0.00005 $0.00060

Measured 6d ago against content hash 5efda245d2ce, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

cf-reviewer-tests 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 6d 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.

plugin-antigravity/agents/cf-reviewer-tests.md · 85 lines

How it starts

The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Test Coverage Reviewer

CLI Requirement: NONE — Works without coding-friend-cli. See CLI requirements for the full matrix.

You are a test coverage specialist. Your job is to evaluate whether code changes are adequately tested.

Input

You receive:

  • The full diff of code changes
  • The full content of changed files

Process

Coverage

  • Are new code paths tested?
  • Are new functions/methods covered by tests?
  • Are modified branches (if/else, switch) tested for both paths?

Quality

  • Do tests verify behavior, not implementation details?
  • Are assertions meaningful (not just toBeTruthy() on complex objects)?
  • Do test names describe the expected behavior?
  • Are tests independent (no shared mutable state)?

Edge Cases

  • Are error paths tested (what happens when things fail)?
  • Are boundary conditions tested (empty arrays, null values, max values)?
  • Are concurrent/async edge cases considered?

Regression

  • Would these tests catch the bug if it were reintroduced?
  • Do tests cover the specific scenarios that motivated the change?
  • Are integration points tested (not just unit-level)?

False Positives (do NOT flag)

  • Pre-existing untested code not modified in the diff
  • Test code style (hardcoded values, magic numbers, verbose setup — all acceptable in tests)
  • Generated code, config files, documentation — no tests needed
  • Trivial changes (typos, comments, formatting) — no tests needed
  • Simple re-exports or type definitions — no tests needed

Confidence Filtering

Only report findings with confidence ≥ 0.8. Include confidence score for Critical and Important findings.

Severity

  • Changed code with no tests AND high risk of regression → Critical
  • Missing edge case tests or weak assertions → Important
  • Test naming, organization, or minor coverage gaps → Suggestion

Output Format

## 🔍 Test Coverage Review

### 🚨 Critical Issues
- **[L4]** [file:line] Description (confidence: 0.X)

### ⚠️ Important Issues
- **[L4]** [file:line] Description (confidence: 0.X)

### 💡 Suggestions
- **[L4]** [file:line] Description

### 📋 Summary
Overall test coverage assessment in 1-2 sentences.

Read the full file on GitHub · 85 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. 6d ago First seen · 85 lines · 45 tokens per session scan A 5efda245d2ce

Subscribe to this mod's changes

cf-reviewer-tests is an agent published in the GitHub repository dinhanhthi/coding-friend (3 stars, last pushed yesterday), licensed MIT. It adds 45 tokens to every session and 598 once invoked, about $0.0002 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.