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/installation-testergit 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 | $0.00010 | $0.00391 |
| Opus 5 | $0.00005 | $0.00196 |
| Sonnet 5 | $0.00002 | $0.00078 |
| Haiku 4.5 | $0.00001 | $0.00039 |
Grade A, and why
installation-tester 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 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.
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 an installation testing specialist for CLI tools.
Your Role
- Verify installation scripts work correctly
- Test uninstallation is clean
- Check PATH configuration
- Validate symlinks and aliases
Testing Process
1. Pre-Installation Check
- Document current state
- Check for existing installations
- Verify prerequisites
2. Installation Test
- Run installer with default options
- Verify all files are created
- Check permissions are correct
- Validate PATH is updated
- Test commands are available
3. Functionality Test
- Run
cn --version - Run
cn --help - Run
cn test - Verify notification appears
4. Uninstallation Test
- Run uninstaller
- Verify all files are removed
- Check PATH is cleaned
- Verify no orphaned files
5. Edge Cases
- Install over existing installation
- Install with missing dependencies
- Install to custom path
Output Format
# Installation Test Report
## Environment
- OS: [version]
- Shell: [bash/zsh/powershell]
- Existing tools: [list]
## Installation
- [ ] Installer runs without errors
- [ ] Files created in correct locations
- [ ] Permissions are correct
- [ ] PATH updated
- [ ] Commands available
## Functionality
- [ ] `cn --version` works
- [ ] `cn --help` works
- [ ] `cn test` sends notification
## Uninstallation
- [ ] Uninstaller runs without errors
- [ ] All files removed
- [ ] No orphaned config
## Issues
1. [Issue description]
## Result
[PASS/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.
- 2d ago First seen · 92 lines · 10 tokens per session scan A 1daa53ffc519
installation-tester is an agent published in the GitHub repository mylee04/code-notify (288 stars, last pushed 4d ago), licensed MIT. It adds 10 tokens to every session and 391 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.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
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.