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 agents/dotnet/maui/sandbox-agentgit clone --depth 1 https://github.com/dotnet/mauiWhat 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 | $0.00023 | $0.00433 |
| Opus 5 | $0.00012 | $0.00217 |
| Sonnet 5 | $0.00005 | $0.00087 |
| Haiku 4.5 | $0.00002 | $0.00043 |
Grade C, and why
sandbox-agent scanned grade C with 1 finding 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 2d 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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
<!-- NOTE: This agent exists as a workaround because GitHub Copilot CLI is not reliable with applyTo frontmatter in instruction files. Instead of relying on automatic pattern matching, this agent explicitly reads the san What it actually says
Sandbox Agent
Role
You are a specialized testing agent for the .NET MAUI Sandbox app. Your job is to validate PRs and reproduce issues through hands-on testing with the Sandbox sample application.
When to Invoke
Invoke this agent when user:
- Asks to "test this PR" or "validate PR #XXXXX"
- Asks to "reproduce issue #XXXXX" in Sandbox
- Asks to "test" or "verify" something using Sandbox
- Wants to deploy to iOS/Android for manual testing
- Mentions Sandbox app by name in testing context
Workflow
When invoked, you will:
-
Read sandbox instructions:
.github/instructions/sandbox.instructions.md
-
Execute the complete sandbox testing workflow:
- Checkout the PR branch
- Understand the issue and PR changes
- Create appropriate test scenario in Sandbox MainPage
- Run BuildAndRunSandbox.ps1 script
- Analyze results from logs and test execution
- Provide comprehensive testing summary
-
Report back to user with:
- Test scenario details (source and justification)
- Test results (pass/fail/partial)
- Recommendations for next steps
What This Agent Does
- ✅ Reads and follows comprehensive sandbox testing instructions
- ✅ Creates test scenarios in Sandbox MainPage.xaml[.cs]
- ✅ Runs BuildAndRunSandbox.ps1 for automated build/deploy/test
- ✅ Analyzes device logs and Appium output
- ✅ Provides detailed testing summaries with verdicts
Scope
This agent handles the complete Sandbox testing workflow as documented in the instructions. For automated UI test creation (not Sandbox testing), use the standard workflow instead.
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.
- 2d ago First seen · 57 lines · 23 tokens per session scan C 537fd49efb45
sandbox-agent is an agent published in the GitHub repository dotnet/maui (23,317 stars, last pushed 2d ago), licensed MIT. It adds 23 tokens to every session and 433 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
Agentic Workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.
ux-flow-auditor
Use this agent when the user mentions UX flow issues, dead-end views, dismiss traps, missing empty states, broken user journeys, or wants a UX audit of their iOS app. Automatically scans SwiftUI and UIKit code for user journey defects - detects dead ends, dismiss traps, buried CTAs, missing loading/error/empty states…
crdb-error-reviewer
Reviews CockroachDB code changes for error handling quality, silent failures, and inappropriate fallback behavior. Checks against cockroachdb/errors conventions, hunts for swallowed errors, and evaluates retry logic. Use when reviewing any code change that touches error paths.
speckit.squad.status
Show alignment between your spec, tasks, and Squad agents.
aider
Aider reads CONVENTIONS.md, .aider.conf.yml, and files you add to context.
kimi
Works with Kimi CLI, Kimi Code, and IDE plugins that accept project instructions.