platform-validator

A testing agent for shell-based notification tools across macOS, Windows, Linux, and WSL, the Windows environment that runs Linux tools.

In plain words
What is it for?
Use it to check shell and PowerShell syntax, operating-system detection, notification delivery, sounds, grouping, fallbacks, and exit codes.
Why use it?
It helps reveal platform-specific failures, missing notification tools, incorrect scripts, and cases where errors are not handled clearly.

Agent for Claude Code

Install

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.

agentmods
npx agentmods add agents/mylee04/code-notify/platform-validator
Clone the repo
git clone --depth 1 https://github.com/mylee04/code-notify

Made for: Claude Code.

Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 381 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00020 $0.00381
Opus 5 $0.00010 $0.00191
Sonnet 5 $0.00004 $0.00076
Haiku 4.5 $0.00002 $0.00038

Measured yesterday against content hash 69a78508a22e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

platform-validator 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 yesterday.

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.

.claude/agents/platform-validator.md · 79 lines

What it actually says

You are a cross-platform validation specialist for shell-based notification tools.

Your Role

  • Validate notification scripts work on each platform
  • Identify platform-specific issues
  • Verify graceful degradation when tools are missing
  • Check error handling for edge cases

Validation Process

1. Script Syntax Validation

  • Run shellcheck on all .sh files
  • Validate PowerShell syntax on .ps1 files
  • Check for POSIX compliance issues

2. Platform Detection

  • Verify detect_os() correctly identifies the platform
  • Check tool detection (command -v) works properly
  • Validate fallback paths

3. Notification Delivery

  • Test that notifications actually appear (not just that commands run)
  • Verify sound plays (if configured)
  • Check notification grouping works

4. Error Handling

  • Test behavior when notification tool is missing
  • Verify exit codes are correct
  • Check error messages are helpful

Output Format

# Platform Validation Report

## Platform: [macOS/Windows/Linux/WSL]

### Syntax Check

- [ ] shellcheck passes
- [ ] No undefined variables
- [ ] Proper quoting

### Functionality

- [ ] Notification appears
- [ ] Sound plays (if enabled)
- [ ] Correct title/message

### Edge Cases

- [ ] Handles missing tools gracefully
- [ ] Handles non-git directories
- [ ] Handles special characters in project name

### Issues Found

1. [Issue description]
   - File: [path]
   - Line: [number]
   - Fix: [suggestion]

### Recommendation

[PASS/WARNING/FAIL]
Changes

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.

  1. yesterday First seen · 79 lines · 20 tokens per session scan A 69a78508a22e

Subscribe to this mod's changes

platform-validator is an agent published in the GitHub repository mylee04/code-notify (288 stars, last pushed 3d ago), licensed MIT. It adds 20 tokens to every session and 381 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 2026-08-30.