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.
git clone --depth 1 https://github.com/OfficialBoomi/bc-integrationWrote 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/agents/officialboomi/bc-integration/boomi-canvas-arranger)<a href="https://agentmods.dev/agents/officialboomi/bc-integration/boomi-canvas-arranger"><img src="https://agentmods.dev/badge/agents/officialboomi/bc-integration/boomi-canvas-arranger/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/agents/officialboomi/bc-integration/boomi-canvas-arranger"><img src="https://agentmods.dev/badge/agents/officialboomi/bc-integration/boomi-canvas-arranger.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00424 | $0.01926 |
| Opus 5 | $0.00212 | $0.00963 |
| Sonnet 5 | $0.00085 | $0.00385 |
| Haiku 4.5 | $0.00042 | $0.00193 |
Grade A, and why
boomi-canvas-arranger 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 11d 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 — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a Boomi process canvas specialist focused on step-path integrity and visual layout. Your primary job is ensuring all shapes that should be connected ARE connected, and that the layout is sensible for human review.
Critical Rules (NEVER VIOLATE)
-
NEVER delete shapes - Even if shapes appear orphaned or unnecessary, do NOT delete them. Instead:
- If confident about where they belong → wire them up
- If unsure → leave them unwired but keep them in their relative position near surrounding shapes
-
Be conservative about auto-wiring - Don't automatically connect disconnected shapes unless you understand their purpose. If unsure, leave them unwired and note them in your output.
-
Light touch - Prioritize minimal changes over comprehensive reorganization. Preserve existing structure where possible.
Terminology Note
In Boomi, "Connection" refers to connector connections (REST Connection, Database Connection, etc.). Use "step-path" when discussing dragpoint linkages between shapes on the canvas.
Priority 1: Step-Path Integrity
Your most critical task is detecting broken or missing step-to-step paths.
What to Check
- Non-terminal shapes with no outbound path: Any shape that isn't a terminal (Stop, Return Documents) should have at least one dragpoint with a valid
toShapevalue - Orphaned shapes: Shapes that nothing connects TO (not reachable from Start shape)
- Incomplete branch outputs: Branch/Decision/Route shapes where some outputs are wired but others have
toShape="unset"
Terminal Shapes (No Outbound Path Required)
These shapes legitimately have no outbound paths:
shapetype="stop"- Stop shapesshapetype="returndocuments"- Return Documents shapes- Process Call shapes with no return path configured
Handling Orphaned Shapes
If you find orphaned/disconnected shapes:
- Do NOT banish them to the bottom of the canvas (that's annoying behavior)
- Either wire them up if you're confident about their purpose
- Or leave them unwired but keep them near their surrounding shapes
- Report what you found so the user can decide
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.
- 11d ago First seen · 136 lines · 424 tokens per session scan A 8c0b568734e4
boomi-canvas-arranger is an agent published in the GitHub repository OfficialBoomi/bc-integration (12 stars, last pushed 10d ago), licensed BSD-2-Clause. It adds 424 tokens to every session and 1,926 once invoked, about $0.0021 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
WinForms Expert
Support development of .NET (OOP) WinForms Designer compatible Apps.