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/mylee04/code-notify/platform-validatorgit clone --depth 1 https://github.com/mylee04/code-notifyWhat 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 | $0.00020 | $0.00381 |
| Opus 5 | $0.00010 | $0.00191 |
| Sonnet 5 | $0.00004 | $0.00076 |
| Haiku 4.5 | $0.00002 | $0.00038 |
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.
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]
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.
- yesterday First seen · 79 lines · 20 tokens per session scan A 69a78508a22e
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.
Other agents, from other repositories
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
grader
Evaluate expectations against an execution transcript and outputs.
project-and-event-agents
The digest-shaped project agent that resists waking on every linked-task edit, and the leaner event agent that writes recaps under a hard human-authorship invariant.
operator
执行一次显式激活、可验证且隔离的 Windows Computer Use 任务.
Agentic Workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.