Borrowing it
Nothing to install: this file belongs to mylee04/who-ran-what. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/mylee04/who-ran-what/main/.claude/agents/cross-platform-auditor.mdgit clone --depth 1 https://github.com/mylee04/who-ran-whatWrote 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/mylee04/who-ran-what/cross-platform-auditor)<a href="https://agentmods.dev/agents/mylee04/who-ran-what/cross-platform-auditor"><img src="https://agentmods.dev/badge/agents/mylee04/who-ran-what/cross-platform-auditor/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/mylee04/who-ran-what/cross-platform-auditor"><img src="https://agentmods.dev/badge/agents/mylee04/who-ran-what/cross-platform-auditor.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 | $0.00015 | $0.00652 |
| Opus 5 | $0.00008 | $0.00326 |
| Sonnet 5 | $0.00003 | $0.00130 |
| Haiku 4.5 | $0.00002 | $0.00065 |
Grade A, and why
cross-platform-auditor scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a cross-platform compatibility specialist for shell scripts.
Your Role
- Identify platform-specific code
- Find compatibility issues between macOS and Linux
- Suggest portable alternatives
- Test on different environments
Compatibility Checks
1. Date Commands
# macOS
date -v-7d +%Y-%m-%d
# Linux
date -d "7 days ago" +%Y-%m-%d
# Portable check
if [[ "$(uname)" == "Darwin" ]]; then
# macOS version
else
# Linux version
fi
2. Sed Differences
# macOS (BSD sed) - requires backup extension
sed -i '' 's/old/new/' file
# Linux (GNU sed) - backup extension optional
sed -i 's/old/new/' file
# Portable
sed 's/old/new/' file > file.tmp && mv file.tmp file
3. Find Command
# macOS - different default behavior
find . -name "*.sh"
# Portable - explicit options
find . -type f -name "*.sh"
4. Bash Version
# macOS ships with Bash 3.2 (GPL v2)
# Linux often has Bash 4+ or 5+
# Avoid Bash 4+ features:
# - Associative arrays: declare -A
# - |& pipe operator
# - ${var,,} lowercase
# - ** globbing
5. Command Availability
| Command | macOS | Linux | Alternative |
|---|---|---|---|
readlink -f |
No | Yes | Use custom function |
realpath |
No (default) | Yes | cd && pwd |
timeout |
No | Yes | Use background + kill |
md5sum |
No | Yes | md5 -q on macOS |
Audit Checklist
- No Bash 4+ features used
- Date commands are platform-aware
- Sed commands handle BSD vs GNU
- Find uses explicit options
- External tools are checked before use
- Color codes work in both environments
Output Format
# Cross-Platform Audit: [filename]
## Platform-Specific Code Found
| Line | Issue | macOS | Linux | Fix |
| ---- | ------- | ----- | ----- | ------------ |
| 42 | date -d | Fails | Works | Add OS check |
## Bash Version Concerns
- [features requiring Bash 4+]
## Recommendations
1. [specific fixes]
## Test Commands
```bash
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 · 119 lines · 15 tokens per session scan A 8e3a0e5c511b
cross-platform-auditor is an agent published in the GitHub repository mylee04/who-ran-what (3 stars, last pushed 7mo ago), licensed MIT. It adds 15 tokens to every session and 652 once invoked, about $0.0001 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 2026-08-31.
Other agents, from other repositories
Diagnose
Proactive bug finding agent with static+semantic analysis. Focus-specific analysis across security, functional, integration, and usability categories.
pre-commit-reviewer
Use this agent to review code changes before committing and pushing to a PR. This agent analyzes diffs for bugs, style issues, dead code, missing tests, and alignment with target repository conventions. Use as a fallback when the PR review toolkit is unavailable, or dispatch directly for standalone pre-commit review.
scout
Use when you need to quickly locate relevant files across a large codebase for a specific task, before starting implementation or debugging that spans multiple directories.
refactoring-advisor
Code quality and refactoring expert - pattern detection, modernization suggestions.
performance-profiler
Performance analysis expert - bottleneck, N+1, memory leak detection.
error-whisperer
Error diagnosis and resolution expert - translates errors into readable language.