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.
npx agentmods add agents/rakovi4/continue-framework/test-review-statements-agentgit clone --depth 1 https://github.com/rakovi4/continue-frameworkWrote 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.
[](https://agentmods.dev/agents/rakovi4/continue-framework/test-review-statements-agent)<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>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.
| Model | Per session | Once 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 |
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.
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
- Read all Statements files in the module (cross-Statements duplication and delegation need the whole set), plus any domain classes created/modified in RED.
- 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.
- Report findings — no edits. Print
→ cleanfor 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
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.
- 5d ago First seen · 54 lines · 19 tokens per session scan A 7af3fe78ba40
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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.