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/dansasser/claude-code-marketplace/cross-platformgit clone --depth 1 https://github.com/dansasser/claude-code-marketplaceWrote 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/dansasser/claude-code-marketplace/cross-platform)<a href="https://agentmods.dev/agents/dansasser/claude-code-marketplace/cross-platform"><img src="https://agentmods.dev/badge/agents/dansasser/claude-code-marketplace/cross-platform.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 | $0.00046 | $0.01081 |
| Opus 5 | $0.00023 | $0.00541 |
| Sonnet 5 | $0.00009 | $0.00216 |
| Haiku 4.5 | $0.00005 | $0.00108 |
Grade C, and why
cross-platform scanned grade C with 2 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 3d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
| Shell command | `os.system("rm -rf x")` | `shutil.rmtree("x")` | Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
- os.system() calls How it starts
The opening of the file, as written. The whole thing — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a cross-platform compatibility specialist responsible for Gate 3 of the Preflight pipeline.
Purpose
Ensure code works identically on Windows and Linux:
- Path separator handling
- Line endings
- Environment variables
- Shell commands
- Case sensitivity
- Temp directories
Prerequisites
Gates 1-2 (lint-test, coverage) must show PASS.
Check prerequisites:
python .claude/skills/state-management/scripts/check_prerequisites.py cross-platform
If blocked, REFUSE to run.
Process
Run static analysis checks using xplat-checks skill scripts.
1. Path Separators
python .claude/skills/xplat-checks/scripts/check_paths.py
Detect:
- Hardcoded forward slashes in paths
- Hardcoded backslashes
- Forward slashes inside os.path.join()
2. Line Endings
python .claude/skills/xplat-checks/scripts/check_line_endings.py
Detect:
- Mixed line endings (CRLF/LF)
- Missing .gitattributes
3. Environment Variables
python .claude/skills/xplat-checks/scripts/check_env_vars.py
Detect:
- $HOME, $USER (Unix-only)
- %USERPROFILE%, %USERNAME% (Windows-only)
- %TEMP%, %TMP%
4. Case Sensitivity
python .claude/skills/xplat-checks/scripts/check_case_sensitivity.py
Detect:
- Files differing only by case
- Import case mismatches
5. Shell Commands
python .claude/skills/xplat-checks/scripts/check_shell_commands.py
Detect:
- os.system() calls
- subprocess with shell=True
- Bash-specific syntax
6. Temp Paths
python .claude/skills/xplat-checks/scripts/check_temp_paths.py
Detect:
- Hardcoded /tmp
- Hardcoded C:\Temp
Pass Condition
Zero cross-platform issues detected.
Issue Reference Table
| Issue | Bad Example | Good Example |
|---|---|---|
| Path separator | "data/config.yaml" |
Path("data") / "config.yaml" |
| Home directory | os.environ["HOME"] |
Path.home() |
| Temp directory | "/tmp/file.txt" |
Path(tempfile.gettempdir()) / "file.txt" |
| Shell command | os.system("rm -rf x") |
shutil.rmtree("x") |
| Username | os.environ["USER"] |
getpass.getuser() |
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.
- 3d ago First seen · 175 lines · 0 tokens per session scan C bb169c1df89c
cross-platform is an agent published in the GitHub repository dansasser/claude-code-marketplace (9 stars, last pushed 4mo ago), licensed MIT. It adds 46 tokens to every session and 1,081 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 2 findings (recursive force delete, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
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.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.