Borrowing it
Nothing to install: this file belongs to H4sh3/agent-notify. 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/H4sh3/agent-notify/main/AGENTS.mdgit clone --depth 1 https://github.com/H4sh3/agent-notifyWrote 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/instructions/h4sh3/agent-notify/agents-md)<a href="https://agentmods.dev/instructions/h4sh3/agent-notify/agents-md"><img src="https://agentmods.dev/badge/instructions/h4sh3/agent-notify/agents-md/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/instructions/h4sh3/agent-notify/agents-md"><img src="https://agentmods.dev/badge/instructions/h4sh3/agent-notify/agents-md.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 | $0.00263 | $0.00263 |
| Opus 5.5 | $0.00105 | $0.00105 |
| Sonnet 5.5 | $0.00053 | $0.00053 |
| Haiku 4.5 | $0.00026 | $0.00026 |
Grade A, and why
agent-notify AGENTS.md 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 2mo 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
Repository guidance
Product intent
This project is a local spoken-message experience, not only an MCP wrapper around a text-to-speech engine. A played message should also be visible in a small, always-on-top overlay at the right side of the screen.
The overlay uses an unambiguous status square:
- green means the message has started and is currently playing;
- red means playback has ended.
Keep the overlay compact, readable, and useful without interaction. Audio must still work when no graphical display is available.
Implementation conventions
- Keep stdout reserved for JSON-RPC in the stdio MCP server.
- Prefer Python standard-library UI and process facilities unless a new dependency is clearly justified.
- Keep synthesis, audio playback, and presentation separable so each can be tested without loading a TTS model or opening a real window.
- Preserve cached WAV generation and audio-only fallback behavior.
- Any background notifier process must remain detached from Codex.
Validation
Run the full test suite after behavioral changes:
uv run pytest
For overlay changes, also perform a manual desktop check with:
uv run tts-notify \
'{"type":"agent-turn-complete","last-assistant-message":"Overlay check complete."}'
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.
- 2mo ago First seen · 41 lines · 263 tokens per session scan A ec87f3a52844
agent-notify AGENTS.md is an instructions file published in the GitHub repository H4sh3/agent-notify (0 stars, last pushed 20d ago), licensed MIT. It adds 263 tokens to every session, about $0.0011 per session on Opus 5.5. 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.
agent-notify AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| agent-notify AGENTS.mdH4sh3/agent-notify | Instructions file | 0 | 20d ago | MIT | A | 263 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 275k | 3d ago | MIT | A | 4,313 | Codex, OpenCode |