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/mendix-odata-pushdownnpx skills add mendixlabs/mxcli --skill mendix-odata-pushdowngit 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/mendix-odata-pushdown)<a href="https://agentmods.dev/skills/mendixlabs/mxcli/mendix-odata-pushdown"><img src="https://agentmods.dev/badge/skills/mendixlabs/mxcli/mendix-odata-pushdown.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 | $0.00117 | $0.02526 |
| Opus 5 | $0.00059 | $0.01263 |
| Sonnet 5 | $0.00023 | $0.00505 |
| Haiku 4.5 | $0.00012 | $0.00253 |
Grade A, and why
mendix-odata-pushdown 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 — 208 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pushing OData query options into your own SQL
The problem this exists for
Mendix will publish any entity over OData, including one with no table behind
it: declare the resource non-persistable, give it a read microflow, done. What
the documentation does not say is that Mendix then applies none of the query
options to your answer. $filter, $orderby, $top, $skip, $count and the
key lookup all arrive on the request URI and all stay there. Whatever the
microflow returns is exactly what the client gets.
That is not a 500 and not an empty grid. It is a 200 with the wrong rows:
?$top=5returns all 917 rows and the widget shows five of them, so paging looks correct while every page ships the whole table.- A client re-reading one held row by key gets the collection back, adopts the first row as that object's identity, and keeps it. A detail page for one record shows another record's data, and nothing logs a word.
The second one is the reason to care. It is not a performance problem; it is wrong data on screen, and every check is green.
What the pack gives you
Four Java actions and the entity they return. Nothing in them is specific to any database or any app.
{{MODULE}}.Parse(Uri, Columns, Dialect, MaxTop, DefaultTop,
DefaultOrderBy, KeyField, RejectUnsupported) -> {{MODULE}}.Query
{{MODULE}}.Key(Uri, KeyField) -> String
{{MODULE}}.FilterNumber(Uri, Field, Fallback) -> Long
{{MODULE}}.CallStatement(Routine, Kind, Parameters, Dialect) -> String
Parse is the whole thing. Key and FilterNumber are short forms for the
common case — a resource reachable one way only ("the sessions of this
weekend"), whose entire contract is one value out of $filter. CallStatement
builds the invocation for a resource backed by a stored routine.
{{MODULE}}.Query
| Field | Style | What it is |
|---|---|---|
FilterSql |
splice | " WHERE …", or empty |
OrderBySql |
splice | " ORDER BY … LIMIT n OFFSET m" |
SelectSql |
splice | " a, b, c" for $select, or empty for all columns |
SelectedColumns |
bind | the same columns as exposed names |
Key |
bind | the key the client is re-reading one row by; empty for a collection |
Top, Skip |
bind | the page, already clamped to MaxTop |
SortColumn1/2, SortDirection1/2 |
bind | the sort, as exposed names and A/D |
WantsCount |
both | $count=true — the client wants the size of the set |
Rejected, RejectReason |
bind | the request asked for something untranslatable. Only a bind caller sees these: with RejectUnsupported = true (what a splice caller passes) Parse throws instead of returning, so a splice caller always has Rejected = false |
What ships with it
13 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- java/actions/CallStatement.java 1.5 KB
- java/actions/FilterNumber.java 1.4 KB
- java/actions/Key.java 1.3 KB
- java/actions/Parse.java 2.0 KB
- java/ODataQueryParser.java 29 KB
- java/QueryObject.java 2.9 KB
- java/RoutineCall.java 7.6 KB
- mdl/module.mdl 13 KB
- pack.yaml 3.4 KB
- references/failure-modes.md 4.5 KB
- references/packaging-gap.md 5.3 KB
- references/patterns.md 5.3 KB
- scripts/ParserCheck.java 4.3 KB
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 · 208 lines · 117 tokens per session scan A 89fd12e09ea0
mendix-odata-pushdown is a skill published in the GitHub repository mendixlabs/mxcli (115 stars, last pushed 2d ago), licensed Apache-2.0. It adds 117 tokens to every session and 2,526 once invoked, about $0.0006 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 2026-09-03.
Other skills, from other repositories
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…
stale-sweep
Sweep the googleapis/mcp-toolbox repo for issues and PRs with no real activity in N days (default 60), sort each by whose silence it is (the author's, ours, or nobody's), and draft the nudge or close comment. Use whenever a maintainer asks for a stale sweep, backlog cleanup, or an SLO check, e.g. "stale sweep", "find…
triage-issues
Triage GitHub issues in the googleapis/mcp-toolbox repo: propose the correct labels (type / priority / product / status), check for duplicates, verify a bug has enough info to act on, and draft a triage comment. Use whenever a maintainer asks you to triage, label, categorize, prioritize, or "look at" an issue (or a…
backend-engineer
Supabase integration specialist. Handles database schema, authentication, Row Level Security (RLS), real-time subscriptions, and storage. Connects existing UI to real backend. Only called AFTER UI exists with mock data. Triggers: connect database, connect Supabase, add auth, make login, backend integration, real data…
new-migration
Create a new database migration file with the correct next ID, preventing duplicates.