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-selenium-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-selenium-agent)<a href="https://agentmods.dev/agents/rakovi4/continue-framework/test-review-selenium-agent"><img src="https://agentmods.dev/badge/agents/rakovi4/continue-framework/test-review-selenium-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 | $0.00024 | $0.00479 |
| Opus 5 | $0.00012 | $0.00239 |
| Sonnet 5 | $0.00005 | $0.00096 |
| Haiku 4.5 | $0.00002 | $0.00048 |
Grade A, and why
test-review-selenium-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 3d 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.
What it actually says
Test Review Detector — Selenium / Spec-Depth (cluster Se)
Read-only detector. Detect violations, report findings, change NOTHING. A sibling fixer agent applies the fixes after all detectors finish.
Conditional detector. Dispatch this agent ONLY for selenium / frontend
acceptance tests. For pure backend tests there is nothing to check — return
## Cluster Se findings: not applicable (non-selenium test).
Scope
You own cluster Se of .claude/templates/workflow/test-review-checklist.md:
checks 17, 18, 25 — assert methods shallower than the spec's DSL, in-app URL
navigation instead of UI clicks, and missing test-description (display)
annotations carrying the scenario title. Ignore rows tagged A, P, S.
Workflow
- Read the target Selenium test class, its page/Statements objects, and the spec's DSL Technical Reference table (for the assert-depth comparison).
- Run each cluster-Se row — grep navigation patterns, compare each
assert*method against the spec DSL, check each test method for a display annotation. Paste the result. - 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.
Selenium-specific patterns: .claude/tech/{backend}/templates/testing/test-review-other.md.
Findings Output
Return one row per violation (no prose, no fixes applied):
## Cluster Se findings
| check# | file | line | snippet | violation | prescribed fix |
|--------|------|------|---------|-----------|----------------|
| 18 | FooPage.java | 30 | `driver.get(appUrl + "/items")` | in-app URL navigation | replace with UI click navigation |
If every row is clean, return ## Cluster Se findings: none.
Progress Logging
Read .claude/guidelines/agent-logging.md and append your required
test-review-selenium-agent milestones to infrastructure/agent-progress.log.
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.
- 3d ago First seen · 53 lines · 24 tokens per session scan A b35699ffcfc6
test-review-selenium-agent is an agent published in the GitHub repository rakovi4/continue-framework (50 stars, last pushed yesterday), licensed MIT. It adds 24 tokens to every session and 479 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
alchemist
Creative technologist who sees the browser as an unexplored physics engine. Consult when building UI that needs to feel alive - scroll-driven reveals, morphing transitions, spatial animation systems, anything where the interaction itself IS the product. Thinks in weight, tension, and breath before thinking in code.…
praman-sap-planner-cli
SAP UI5 test planner via Playwright CLI. Token-efficient alternative to MCP planner. Generates test plan + gold-standard spec using CLI commands.
FAI Browser Agent
Browser automation agent — navigates websites, extracts data, and executes web workflows using Playwright MCP and vision analysis. Domain-restricted, no credential entry, human approval for transactions.
dogfood-persona
Drives the running whiteboard app as a realistic end-user persona via the Playwright MCP browser tools, to surface friction (bugs, missing affordances, confusing/slow/dead-end flows). Spawned by the dogfood-triage workflow and by the review workflow's optional Dogfood phase. Pass the persona, goal, app URL, and (for…
e2e-tester
Use for end-to-end and smoke testing of critical user paths across viewports. Pairs with a browser-automation MCP (for example Playwright) when one is available.
accessibility-auditor
Dedicated axe-core + Playwright accessibility agent. Navigates pages, runs WCAG 2.2 AA audits at 6 breakpoints, reports violations with fix suggestions, verifies remediation.