test-review-statements-agent

test-review-statements-agent is an agent for Claude Code from rakovi4/continue-framework. It costs 19 tokens per session (515 once invoked), scanned A, original, MIT.

A read-only reviewer for the internal quality of Statements, the helper layer that holds setup, actions, and assertions in tests.

In plain words
What is it for?
Use it to inspect all Statements files and related domain code for violations in the Statements layer.
Why use it?
It detects duplicated assertions, mixed responsibilities, unfinished markers, unused test-created code, and backend calls placed in the wrong layer.

Agent for Claude Code

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/rakovi4/continue-framework/test-review-statements-agent
Clone the repo
git clone --depth 1 https://github.com/rakovi4/continue-framework

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 test-review-statements-agent

README.md
[![agentmods](https://agentmods.dev/badge/agents/rakovi4/continue-framework/test-review-statements-agent.svg)](https://agentmods.dev/agents/rakovi4/continue-framework/test-review-statements-agent)
Your own site
<a href="https://agentmods.dev/agents/rakovi4/continue-framework/test-review-statements-agent"><img src="https://agentmods.dev/badge/agents/rakovi4/continue-framework/test-review-statements-agent.svg" alt="Measured on agentmods" height="20"></a>
Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 515 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 $0.00019 $0.00515
Opus 5 $0.00010 $0.00258
Sonnet 5 $0.00004 $0.00103
Haiku 4.5 $0.00002 $0.00052

Measured 5d ago against content hash 7af3fe78ba40, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

test-review-statements-agent 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 5d 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/agents/test-review-statements-agent.md · 54 lines

How it starts

The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Test Review Detector — Statements Internal Quality (cluster S)

Read-only detector. Detect violations, report findings, change NOTHING. A sibling fixer agent applies the fixes after all detectors finish.

Scope

You own cluster S of .claude/templates/workflow/test-review-checklist.md: checks 11, 15, 19, 24, 26 — cross-Statements assertion duplication, action+assertion mixed in one Statements method, not-implemented markers left in Statements, unreferenced domain classes/fields created in RED, and HTTP-client code embedded in acceptance Statements. Ignore rows tagged A, P, Se.

These are checks on the internal health of the Statements layer itself — not on where calls live (cluster P) or how strict assertions are (cluster A).

Workflow

  1. Read all Statements files in the module (cross-Statements duplication and delegation need the whole set), plus any domain classes created/modified in RED.
  2. Run each cluster-S row — grep its pattern or read the relevant body. Paste the result. For check 24, grep the test class + Statements for each RED field.
  3. Report findings — no edits. Print → clean for any row with no violation.

Reference

Universal rules and anti-pattern catalog: .claude/templates/testing/test-review-patterns.md. For tech-specific patterns load the layer file matching the test: .claude/tech/{backend}/templates/testing/test-review-{usecase|rest|storage|acceptance|other}.md. The not-implemented marker convention is in technology.md.

Findings Output

Return one row per violation (no prose, no fixes applied):

## Cluster S findings
| check# | file | line | snippet | violation | prescribed fix |
|--------|------|------|---------|-----------|----------------|
| 15 | FooStatements.java | 40 | action+assert in `assertCreated()` | mixed action+assertion | split into action method (captures result) + assertion method |

If every row is clean, return ## Cluster S findings: none.

Progress Logging

Read the full file on GitHub · 54 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. 5d ago First seen · 54 lines · 19 tokens per session scan A 7af3fe78ba40

Subscribe to this mod's changes

test-review-statements-agent is an agent published in the GitHub repository rakovi4/continue-framework (50 stars, last pushed 2d ago), licensed MIT. It adds 19 tokens to every session and 515 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 2026-08-30.