Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/mendixlabs/mxclinpx agentmods add skills/mendixlabs/mxcli/write-workflowsWrote 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/write-workflows)<a href="https://agentmods.dev/skills/mendixlabs/mxcli/write-workflows"><img src="https://agentmods.dev/badge/skills/mendixlabs/mxcli/write-workflows/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/write-workflows"><img src="https://agentmods.dev/badge/skills/mendixlabs/mxcli/write-workflows.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
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 →
- high Tool Misuse · line 290 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.
- medium Excessive Agency · line 92 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00049 | $0.08939 |
| Opus 5.5 | $0.00020 | $0.03576 |
| Sonnet 5.5 | $0.00010 | $0.01788 |
| Haiku 4.5 | $0.00005 | $0.00894 |
Grade A, and why
write-workflows 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 5d 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 — 686 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Find it fast
sed -n '<from>,<to>p' SKILL.md one section rather than reading the file;
./mxcli syntax <topic> answers how do I write this for a fraction of either.
| lines | section |
|---|---|
| 35-46 | When to Use This Skill |
| 47-110 | Syntax — CREATE WORKFLOW |
| 111-282 | Activities |
| 283-289 | DROP WORKFLOW |
| 290-355 | ALTER WORKFLOW |
| 356-376 | DESCRIBE round-trip |
| 377-397 | Activity names, and why jump to depends on them |
| 398-418 | Rewriting an existing workflow |
| 419-506 | Microflow statements for workflow tasks |
| 507-527 | System-module enumerations are synthesized, not stored |
| 528-644 | Platform rules |
| 645-675 | Observing a running workflow |
| 676-685 | Validate before presenting |
Mendix Workflows Skill
Guidance for authoring workflows in Mendix projects with MDL — not just
reading them. CREATE WORKFLOW / DROP WORKFLOW / ALTER WORKFLOW are fully
supported and build in Studio Pro. Workflows are not read-only in mxcli; do
not punt workflow creation to Studio Pro.
When to Use This Skill
- Creating a business process: approvals, reviews, multi-step tasks with user interaction, timers, and parallel branches.
- Adding/removing/reordering activities in an existing workflow (
ALTER WORKFLOW). - Regenerating a workflow from
DESCRIBE WORKFLOWoutput (round-trippable).
A workflow is a Workflows$Workflow unit driven by a context entity: the
persistent entity each workflow instance is about (the Expense being approved,
the LeaveRequest being reviewed). User tasks render a page bound to
System.WorkflowUserTask.
Syntax — CREATE WORKFLOW
The header options may be written in any order — each at most once — and the
body must close with END WORKFLOW. (They used to be order-sensitive, in
exactly the sequence below; a clause written out of place failed with
mismatched input 'DISPLAY' expecting {ON, BEGIN, EXPORT, DUE, OVERVIEW}, which
named neither the clause nor the rule. See ako/mxcli#586.)
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.
- 5d ago Changed · +22 lines 9cad69521edd
- 13d ago Changed · +29 lines 7dfc8e9f7a6b
- 14d ago Changed · +3 lines 2677636fa002
- 15d ago Changed · +8 lines 06e7e0545eb7
- 16d ago Changed · +52 lines bc5794f8c234
- 24d ago Changed · +22 lines b5f6bfbd81ca
- 29d ago Changed · +13 lines fb23666432de
- 1mo ago Changed · +96 lines 696fdf91c292
- 1mo ago Changed · +52 lines d5d4e3acf245
- 1mo ago First seen · 389 lines · 49 tokens per session scan A adbe483ac094
write-workflows is a skill published in the GitHub repository mendixlabs/mxcli (131 stars, last pushed yesterday), licensed Apache-2.0. It adds 49 tokens to every session and 8,939 once invoked, about $0.0002 per session on Opus 5.5. 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
create-issue
Draft and submit a GitHub issue from a user idea or bug description, with bilingual body and correct labels.
issue-creator
A guide for turning unclear user feedback from text, chat excerpts, or screenshots into a focused GitHub issue, a tracked software-work item. It preserves the original request and separates evidence from information that is still unknown.
status
Surfaces the current state of work in gflow-cli. Three variants at different levels of detail: full state (status), next task only (next), active plan identity (active). All variants run scripts/dev/activeplan.py and filter its output to the requested detail level.
hatch3r-board-groom
Ongoing backlog refinement for existing board items. Re-prioritize, reclassify, re-scope, archive stale items, decompose oversized issues, merge duplicates, refresh dependencies, and remediate board health findings.
hatch3r-board-init
Initializes a project board (GitHub Projects V2, Azure Boards, or GitLab Issue Boards) with hatch3r's label taxonomy, status fields, and board structure. Platform detected from hatch.json.
hatch3r-board-shared
Shared context and procedures for all board commands. Provides platform-agnostic board config, label taxonomy, branch conventions, sync enforcement, and tooling directives. Platform-specific details are in commands/board/shared-{platform}.md.