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 skills add mendixlabs/mxcli --skill verify-with-oqlgit clone --depth 1 https://github.com/mendixlabs/mxcliWrote 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/skills/mendixlabs/mxcli/verify-with-oql)<a href="https://agentmods.dev/skills/mendixlabs/mxcli/verify-with-oql"><img src="https://agentmods.dev/badge/skills/mendixlabs/mxcli/verify-with-oql/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/mendixlabs/mxcli/verify-with-oql"><img src="https://agentmods.dev/badge/skills/mendixlabs/mxcli/verify-with-oql.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
SkillSpector: 2 findings, up to low
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- low Tool Misuse · line 29 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- low Tool Misuse · line 157 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
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 5.1 | $0.00048 | $0.01714 |
| Opus 5 | $0.00024 | $0.00857 |
| Sonnet 5 | $0.00010 | $0.00343 |
| Haiku 4.5 | $0.00005 | $0.00171 |
Grade A, and why
verify-with-oql scanned grade A with 2 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 7d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- [/runtime-admin-api](../runtime-admin-api/SKILL.md) — Admin API details and curl examples Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
import { execSync } from 'child_process'; How it starts
The opening of the file, as written. The whole thing — 195 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verify with OQL Skill
This skill documents how to verify microflow side effects and data changes using OQL queries against a running Mendix app.
When to Use This Skill
Use this when:
- You've deployed changes and want to verify data was created/updated/deleted correctly
- You need to confirm a microflow produced the expected side effects
- You're combining Playwright UI tests with backend data verification
- You want a fast feedback loop: deploy, trigger, verify
The Pattern
The core verification workflow is:
- Deploy — apply MDL changes and rebuild
- Trigger — execute the action (via UI, microflow call, or API)
- Verify — query the database with OQL to confirm the result
# 1. Deploy
mxcli exec changes.mdl -p app.mpr
mxcli docker build -p app.mpr --skip-check
mxcli docker reload -p app.mpr # or: mxcli docker up -p app.mpr --fresh --wait
# 2. Trigger (example: call a microflow that creates test data)
# This could be via Playwright, a rest call, or manual interaction
# 3. Verify
mxcli oql -p app.mpr "select Name, Email from MyModule.Customer where Name = 'Jane Doe'"
OQL Verification Examples
Check data was created
# Verify a customer was created
mxcli oql -p app.mpr "select Name, Email from Sales.Customer where Name = 'Test Customer'"
# count records
mxcli oql -p app.mpr "select count(*) as Total from Sales.Order"
Check data was updated
# Verify status was changed
mxcli oql -p app.mpr "select OrderNumber, status from Sales.Order where OrderNumber = 'ORD-001'"
Check data was deleted
# Verify record no longer exists (should return empty)
mxcli oql -p app.mpr "select count(*) as Total from Sales.Customer where Name = 'Deleted Customer'"
Check associations
# Verify an association was set (join query)
mxcli oql -p app.mpr \
"select o.OrderNumber, c.Name from Sales.Order o join o/Sales.Order_Customer/Sales.Customer c where o.OrderNumber = 'ORD-001'"
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.
- 7d ago First seen · 195 lines · 48 tokens per session scan A 933d52575f98
verify-with-oql is a skill published in the GitHub repository mendixlabs/mxcli (119 stars, last pushed 2d ago), licensed Apache-2.0. It adds 48 tokens to every session and 1,714 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 2 findings (makes network calls, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
e2e-testing
Guide for running end-to-end tests of the Qwen Code CLI, including headless mode, MCP server testing, and API traffic inspection. Use this skill whenever you need to verify CLI behavior with real model calls, reproduce user-reported bugs end-to-end, test MCP tool integrations, or inspect raw API request/response…
terminal-capture
Automates terminal UI screenshot testing for CLI commands. Applies when reviewing PRs that affect CLI output, testing slash commands (/about, /context, /auth, /export), generating visual documentation, or when 'terminal screenshot', 'CLI test', 'visual test', or 'terminal-capture' is mentioned.
tmux-real-user-testing
A real-user test workflow for Qwen Code's terminal interface, using tmux to drive the program and capture readable screen snapshots. tmux is a tool for running and observing terminal sessions.
agent-reproduce-align
Use after a Codex or Claude Code feature has been implemented in Qwen Code to run the selected reference agent and Qwen Code under the same scenario, capture HTTP and terminal traces, compare request bodies, tool/function schemas, outputs, and iterate until the reproduced behavior is close enough.
review-prs
Review a GitHub pull request in the googleapis/mcp-toolbox repo against the team's reviewer checklist: PR title/description conventions, linked issue, logic errors and unhandled edge cases, breaking changes, test coverage, docs updates, security (input handling), and new dependencies. Use whenever a maintainer asks…
fix-failing-tests
Diagnose a failing test in the googleapis/mcp-toolbox repo and land a fix by reasoning from the actual error: read the failure, reproduce it, shrink it until the cause is forced into the open, then fix the cause. Use this whenever a test or CI job is red, a build breaks after a change, many packages fail at once, or a…