Borrowing it
Nothing to install: this file belongs to felixssimoes/muxa_xtream. 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/felixssimoes/muxa_xtream/main/AGENTS.mdgit clone --depth 1 https://github.com/felixssimoes/muxa_xtreamWrote 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/felixssimoes/muxa_xtream/agents-md)<a href="https://agentmods.dev/instructions/felixssimoes/muxa_xtream/agents-md"><img src="https://agentmods.dev/badge/instructions/felixssimoes/muxa_xtream/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/felixssimoes/muxa_xtream/agents-md"><img src="https://agentmods.dev/badge/instructions/felixssimoes/muxa_xtream/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 | $0.01285 | $0.01285 |
| Opus 5.5 | $0.00514 | $0.00514 |
| Sonnet 5.5 | $0.00257 | $0.00257 |
| Haiku 4.5 | $0.00128 | $0.00128 |
Grade A, and why
muxa_xtream 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.
How it starts
The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Project Structure & Module Organization
lib/: Public package code (entrypoint:lib/muxa_xtream.dart). Keep APIs small and documented.test/: Unit tests (e.g.,test/muxa_xtream_test.dart). Mirrorlib/structure; one*_test.dartper unit.doc/: Design notes and requirements.- Root files:
pubspec.yaml(deps, SDK),analysis_options.yaml(lints),README.md,CHANGELOG.md.
Build, Test, and Development Commands
- Note: A pre-commit hook runs the full verification pipeline automatically on every commit. Running the verify script manually is optional and useful mainly when iterating on failures.
- Install deps:
dart pub get— resolves package dependencies. - Run tests:
dart test— executes test suites. - Coverage:
dart test --coverage=coverage— writes VM coverage data. - Static analysis:
dart analyze— checks style and common issues. - Format:
dart format .— apply standard Dart formatting. - Publish check:
dart pub publish --dry-run— validates package readiness.
Coding Style & Naming Conventions
- Indentation: 2 spaces, no tabs. Use
dart format. - Lints:
flutter_lints(seeanalysis_options.yaml). Fix all analyzer warnings.- Analyzer must be clean: resolve all issues (including info-level) before committing. If suppression is justified, use the narrowest
// ignore:with a rationale.
- Analyzer must be clean: resolve all issues (including info-level) before committing. If suppression is justified, use the narrowest
- Files:
lowercase_with_underscores.dart(e.g.,my_service.dart). - Types:
UpperCamelCase; members/variables:lowerCamelCase; constants:SCREAMING_SNAKE_CASE. - Public API lives under
lib/; avoid exposing internals inadvertently.
Testing Guidelines
- Framework:
flutter_testwithtest(...)andgroup(...). - Location: place tests in
test/; name files*_test.dart. - Aim for fast, deterministic unit tests. Prefer pure Dart tests for logic.
- You can still run tests and analysis locally while iterating, but the pre-commit hook will enforce verification automatically on commit.
Commit & Pull Request Guidelines
- Commits: use Conventional Commits with structured, multi-line messages.
- Subject:
type(scope): concise summary(imperative, max ~50 chars). - Blank line after subject.
- Body: wrapped at ~72 cols; bullets for key changes; include “why” when helpful.
- Prefer small scopes (e.g.,
core,http,docs,tool). - Tip: when committing via CLI, avoid literal
\\nin-mstrings — Git does not interpret escapes.- Use multiple
-mflags for paragraphs, or pipe a properly formatted message via stdin:git commit -F - <<'MSG'...MSG. - Example:
git commit -m "feat(url): add probe" -m "- Adds HEAD/Range probe\\n- Adds tests"(note: each-mis a new paragraph; for line breaks within a paragraph, prefer-F -).git commit -F - <<'MSG'\\nfeat(url): add probe\\n\\n- Adds HEAD/Range probe\\n- Adds tests\\nMSG
- Use multiple
- Examples:
chore(core): complete Phase 0 bootstrap
- Subject:
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 · 79 lines · 1,285 tokens per session scan A bb6c16035807
muxa_xtream AGENTS.md is an instructions file published in the GitHub repository felixssimoes/muxa_xtream (5 stars, last pushed 3mo ago), licensed MIT. It adds 1,285 tokens to every session, about $0.0051 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.
muxa_xtream AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| muxa_xtream AGENTS.mdfelixssimoes/muxa_xtream | Instructions file | 5 | 3mo ago | MIT | A | 1,285 | 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 |