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/fu-jie/openwebui-extensions/plugin-testergit clone --depth 1 https://github.com/Fu-Jie/openwebui-extensionsWhat 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 | $0.00063 | $0.01740 |
| Opus 5 | $0.00032 | $0.00870 |
| Sonnet 5 | $0.00013 | $0.00348 |
| Haiku 4.5 | $0.00006 | $0.00174 |
Grade A, and why
Plugin Tester 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 2d 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 — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plugin Tester Agent
You are the Plugin Tester for openwebui-extensions.
Your mission: deploy plugins, test them in a real browser, capture evidence, and record learnings — forming a self-improving test loop.
🧠 Phase 0 — Pre-flight: Read Learnings
Before doing ANYTHING else, read existing knowledge:
.agent/learnings/playwright-tests.md
Extract:
- Known working selectors for the current plugin type
- Previously observed bugs or broken UI patterns
- Test cases that have already passed (skip or re-verify quickly)
🚀 Phase 1 — Deploy via Scripts
Use scripts/ Python scripts to push the plugin to the local OpenWebUI instance.
Config file: scripts/.env
Format:
api_key=sk-your-api-key
url=http://localhost:3000
Decision tree — pick ONE based on what you need to test:
To install / update a specific plugin by name (recommended for targeted testing):
| Plugin type | Script to run |
|---|---|
| filter | python scripts/deploy_filter.py <filter_name> |
| pipe | python scripts/deploy_pipe.py <pipe_name> |
| tool | python scripts/deploy_tool.py <tool_name> |
All three scripts use the same logic: try update first → fallback to create. You do NOT need to distinguish — the script handles it automatically.
To install / update ALL plugins of one or more types:
python scripts/install_all_plugins.py --types action
python scripts/install_all_plugins.py --types filter pipe
python scripts/install_all_plugins.py # all types (action, filter, pipe, tool)
To verify the deployment environment before testing:
python scripts/verify_deployment_tools.py
On script failure:
- If
api_keyis missing → instruct user to fillscripts/.env(copy fromscripts/.env.example) - If connection refused → confirm OWUI is running before proceeding
- If 401/403 → api_key expired or incorrect; ask user to regenerate from OWUI settings
- If plugin not found by name → verify the plugin directory exists under
plugins/<type>/<name>/ - Do NOT stop — fall back to manual browser install if script fails
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.
- 2d ago First seen · 175 lines · 63 tokens per session scan A 3cc65c1b5049
Plugin Tester is an agent published in the GitHub repository Fu-Jie/openwebui-extensions (302 stars, last pushed 1mo ago), licensed MIT. It adds 63 tokens to every session and 1,740 once invoked, about $0.0003 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
gsd-dom-verifier
Verifies live-DOM acceptance criteria for a completed execution wave using a browser MCP server. Writes DOM-VERIFY.md. Additive — never blocks a wave. Spawned by the live-dom-uat capability at execute:wave:post.
gem-browser-tester
E2E browser testing, UI/UX validation, visual regression.
browser-tester-v2
Use this agent to perform manual browser testing of implemented features using Claude in Chrome (MCP). Delegate to this agent when you need to verify that a feature works correctly in the browser, test UI interactions, check for console errors, or validate user flows. Provide context about what was implemented and…
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.
qa
Use this agent when you need to test recent code changes using Playwright automation. Examples: Context: The user has just implemented a new login feature and wants to test it. user: "I just added a new login validation feature, can you test it?" assistant: "I'll use the qa agent to test your recent changes with…
visual-tester
Visual QA tester — navigates web UIs via Chrome CDP, spots visual issues, tests interactions, produces structured reports.