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 commands/mendix/web-widgets/edit-test-projectgit clone --depth 1 https://github.com/mendix/web-widgetsWhat 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 | $0.00000 | $0.02218 |
| Opus 5 | $0.00000 | $0.01109 |
| Sonnet 5 | $0.00000 | $0.00444 |
| Haiku 4.5 | $0.00000 | $0.00222 |
Grade A, and why
edit-test-project 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 today.
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 — 190 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are helping the developer edit a Mendix test project (.mpr file) to support a new or updated Playwright e2e test in the web-widgets monorepo.
Context
- Test projects live at:
packages/pluggableWidgets/<widget>/tests/testProject/<Name>.mpr mxclireads/writes.mprfiles via MDL (Mendix Definition Language)- Binary:
automation/tools/mxcli— gitignored, install withbash automation/mxcli/setup.sh - The
.mprmust be closed in Studio Pro before mxcli can edit it - mxcli is alpha software — ensure
.mendix-cache/backup/AppBackup.mprexists before bulk edits - For Playwright rules that new pages must satisfy, see
mendix:e2e-specanddocs/requirements/e2e-test-guidelines.md
Step 1 — Identify widget and goal
Ask the user (or infer from context): which widget, and what scenario requires a test project change?
Step 2 — Check prerequisites
[[ -x automation/tools/mxcli ]] && echo "OK" || bash automation/mxcli/setup.sh
ls packages/pluggableWidgets/<widget>/tests/testProject/*.mpr | grep -v backup
Verify Studio Pro is not holding the project open before any mxcli writes:
ls packages/pluggableWidgets/<widget>/tests/testProject/.mendix-cache/lock 2>/dev/null \
&& echo "⚠️ Studio Pro lock file present — close the project first" \
|| echo "OK — no lock file"
Step 3 — Inspect current state
# Full overview: modules, pages, entities, navigation
bash automation/mxcli/mx-testproject.sh inspect <widget>
# Targeted queries:
automation/tools/mxcli -p <MPR_PATH> -c "SHOW PAGES IN <Module>"
automation/tools/mxcli -p <MPR_PATH> -c "SHOW ENTITIES IN <Module>"
automation/tools/mxcli -p <MPR_PATH> -c "SHOW MICROFLOWS IN <Module>"
automation/tools/mxcli -p <MPR_PATH> -c "DESCRIBE PAGE <Module>.<PageName>"
bash automation/mxcli/mx-testproject.sh search <widget> 'keyword'
DESCRIBE PAGEcaveat: pages containing only pluggable widgets (no built-in widgets likeDATAVIEW,LAYOUTGRID, etc.) may render as an empty body even when widget content exists in the MPR. Useautomation/tools/mxcli bson dump -p <MPR> --type page --object <Module>.<Page>and grep for widget names to verify content was written.
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.
- today First seen · 190 lines · 0 tokens per session scan A 471a19bce873
edit-test-project is a command published in the GitHub repository mendix/web-widgets (40 stars, last pushed yesterday), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 2,218 tokens. 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 2026-09-01.
Other commands, from other repositories
test
Run the app's microflow tests and verify it in the browser.
mx-handoff
Generate copy-paste-ready Studio Pro instruction sheets when a human-in-loop step is required. Exact paths, classes, widgets, bindings -- no vague guidance. Auto-runs verification (mx-doctor + impact + playwright) after the human replies "done".
mx-test-page
Drive Playwright against the testbed (port 8082). MANDATORY testbed-fingerprint guard (URL :8082 + "Test Project" ribbon) before any other assertion -- safety gate against driving the live project.
e2e
使用 Playwright 对 Web UI 进行端到端测试（支持视频录制、Trace 录制、控制台/网络日志捕获）.
auto-browse
Auto-browse — learn, optimize, and graduate browser operations or web data-mining workflows.
research-perplexity
Run a deep research query using Perplexity's /research mode via Playwright browser automation. This is an alternative to /export-to-council that uses Perplexity's dedicated research mode instead of multi-model council.