Borrowing it
Nothing to install: this file belongs to TheNovaNodes/google-jules-mcp. 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/TheNovaNodes/google-jules-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/TheNovaNodes/google-jules-mcpWrote 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/thenovanodes/google-jules-mcp/agents-md)<a href="https://agentmods.dev/instructions/thenovanodes/google-jules-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/thenovanodes/google-jules-mcp/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/thenovanodes/google-jules-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/thenovanodes/google-jules-mcp/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 | $0.01289 | $0.01289 |
| Opus 5.5 | $0.00516 | $0.00516 |
| Sonnet 5.5 | $0.00258 | $0.00258 |
| Haiku 4.5 | $0.00129 | $0.00129 |
Grade A, and why
google-jules-mcp 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 1mo 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
🛸 AGENTS.md — Directives for Autonomous & Pair-Programming AI Agents
Context: This document is the primary machine-readable operational manifest for all AI coding agents (Google Jules, Antigravity, Cursor, Claude Code, Devin, and NovaNodes collective bots) operating within this repository.
🏛️ PART 1: NOVANODES CORE INVARIANTS (Universal Standard)
1. Strict Git Flow (ПРАВИЛА КРОВИ)
- 🛑 NEVER push directly to
mainormasterbranches. - All changes (features, bugfixes, refactorings, documentation) MUST go through dedicated branch naming (
feat/...,fix/...,refactor/...,docs/...) and a formal Pull Request (PR). - NEVER merge PRs without explicit approval from ЗавЛаб.
- No Force-Push: Never rewrite public commit history (
git push -f) on upstream branches.
2. Security & Credential Hygiene
- 🛑 Zero-Leakage Policy: NEVER hardcode API keys, tokens, passwords, or credentials into source code, unit tests, commit messages, or PR bodies.
- All secrets must be loaded dynamically from environment variables (e.g.,
os.Getenv("JULES_API_KEY")). - Never echo or log secret values in command stdout/stderr.
3. Deadlock, Timeout & Process Safety
- Network Timeouts: Every outbound network call or HTTP client must configure explicit timeouts (default: 60s total, connection pooling with 90s idle timeout).
- Command Timeouts: When running auxiliary shell commands, always enforce hard timeouts (
timeout -k 2s 15s ...) to prevent zombie processes. - Stdio Redirection: When spawning background processes or smoke-testing MCP stdio servers, always redirect stdin (
< /dev/null) to avoid terminalSIGTTINhangs. - No Infinite Polling: Never loop endlessly (
while true: sleep(1)) waiting for external events. Use scheduled checks or event-driven wakeups.
4. Continuous Verification (No Blind Reports)
- Pre-PR Native Minimum: Never claim a task is complete without running the project's native test suite and linters locally.
- Verification without Absurdity: Use native project tools directly (
go test,go vet,make); do not pull heavy emulator containers. - Post-PR Cloud CI: After creating a PR, monitor the actual GitHub Actions CI (
gh pr checks <id>). Do not report success until all cloud checks are green.
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.
- 1mo ago Changed · +52 lines · +1,028 tokens per session 90ad19a841b6
- 2mo ago First seen · 19 lines · 261 tokens per session scan A 3ea695301489
google-jules-mcp AGENTS.md is an instructions file published in the GitHub repository TheNovaNodes/google-jules-mcp (1 stars, last pushed 1mo ago), licensed MIT. It adds 1,289 tokens to every session, about $0.0052 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.
google-jules-mcp AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| google-jules-mcp AGENTS.mdTheNovaNodes/google-jules-mcp | Instructions file | 1 | 1mo ago | MIT | A | 1,289 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |