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 skills/mendixlabs/mxcli/debug-bsonnpx skills add mendixlabs/mxcli --skill debug-bsongit clone --depth 1 https://github.com/mendixlabs/mxcliWhat 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 | $0.00056 | $0.05175 |
| Opus 5 | $0.00028 | $0.02587 |
| Sonnet 5 | $0.00011 | $0.01035 |
| Haiku 4.5 | $0.00006 | $0.00517 |
Grade A, and why
debug-bson 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 yesterday.
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 — 610 lines — stays where its author put it; the contents beside it link to each section on GitHub.
BSON Serialization Debugging Skill
This skill provides guidance for debugging BSON serialization issues when implementing or fixing Mendix SDK writers.
When to Use This Skill
Use this skill when:
- Objects created via MDL don't appear correctly in Studio Pro
- Properties are missing, empty, or showing default values
- Widget captions, parameters, or nested structures aren't stored correctly
- You need to compare SDK-generated BSON with Studio Pro-generated BSON
- You encounter "empty" or "(Empty caption)" issues in Studio Pro
- Debugging BSON array version markers or object structures
Overview
When the ModelSDK Go serializes objects to BSON, the output must exactly match what Mendix Studio Pro expects. Even small differences in:
- Field names (e.g.,
captionvsCaptionTemplate) - Object structures (e.g., string vs nested object)
- Array version markers (e.g.,
[2, items...]vs[3, items...])
...can cause Studio Pro to ignore the data entirely.
Part 1: The Debugging Workflow
Step 1: Identify the Problem
Symptoms that indicate BSON serialization issues:
- MDL
describecommand shows correct data, but Studio Pro shows empty/default - Object is created but properties don't persist
- Nested structures (templates, parameters) are missing
- "(Empty caption)" or similar placeholder text in Studio Pro
Step 2: Create a Reference Object in Studio Pro
- Open the MPR project in Mendix Studio Pro
- Manually create or fix the problematic object
- Save the project (this writes the correct BSON)
- Note the exact name/path of the fixed object
Step 3: Dump Both BSON Structures
Use the mxcli dump-bson command to extract and compare:
# Dump the SDK-generated object (the broken one)
mxcli dump-bson -p app.mpr -o "PgTest.BrokenPage" > broken.json
# Dump the Studio Pro-generated object (the fixed one)
mxcli dump-bson -p app.mpr -o "PgTest.FixedPage" > fixed.json
# Compare the two
diff broken.json fixed.json
Or use the --compare flag:
mxcli dump-bson -p app.mpr --compare "PgTest.BrokenPage" "PgTest.FixedPage"
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.
- yesterday First seen · 610 lines · 56 tokens per session scan A 3cac80ae8941
debug-bson is a skill published in the GitHub repository mendixlabs/mxcli (115 stars, last pushed 2d ago), licensed Apache-2.0. It adds 56 tokens to every session and 5,175 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 skills, from other repositories
zh-output-example
Reviews Chinese skill documentation for publication readiness. Invoke when the user asks in Chinese to review a skill.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.
powerpoint
Create designed, editable PowerPoint .pptx presentations with PptxGenJS. Use when the user asks to create, generate, update, or inspect a deck, slide deck, presentation, or .pptx file.
review-offered-task
Review a task that has been offered to you and decide whether to accept or reject it.
Swift Performance Optimization Skill
Use when investigating measured Swift or Apple-platform regressions in CPU, memory, launch, scrolling, animation hitches, image processing, energy, networking, or concurrency, or when designing performance tests and Instruments experiments. Do not use for speculative micro-optimization, ordinary refactoring, or a…
systematic-debugging
Root-cause a bug already in front of you, instead of guessing at fixes. Use on triggers like "root cause this", "why is this failing", "debug systematically", "this test is flaky", "it works locally but not in CI", or when a fix attempt has already failed once. Enforces a phased evidence-first process before any code…