Borrowing it
Nothing to install: this file belongs to sirquy/bestie. 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/sirquy/bestie/main/AGENTS.mdgit clone --depth 1 https://github.com/sirquy/bestieWrote 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/sirquy/bestie/agents-md)<a href="https://agentmods.dev/instructions/sirquy/bestie/agents-md"><img src="https://agentmods.dev/badge/instructions/sirquy/bestie/agents-md.svg" alt="Measured on agentmods" 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 | $0.01098 | $0.01098 |
| Opus 5 | $0.00549 | $0.00549 |
| Sonnet 5 | $0.00220 | $0.00220 |
| Haiku 4.5 | $0.00110 | $0.00110 |
Grade A, and why
bestie 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 8d 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Coding Agent Instructions
Project State
Bestie now has a functional TypeScript CLI/runtime implementation. Treat the docs as the product contract for scope and behavior, but use the existing src/ code and tests as the implementation pattern.
Start with:
- PROJECT.md for product vision, owner requirements, and source-of-truth decisions.
- docs/IMPLEMENTATION_PRIORITY.md for Now / Next / Later / Future scope.
- docs/NOW_BUILD_SPEC.md for the current build slice.
- docs/NOW_ARCHITECTURE_SPEC.md for Phase Now module boundaries.
Current Scope
Current shipped scope is no longer only the original Phase Now slice. The local npm CLI/runtime now includes:
- terminal chat
- editable character prompt and installed skills from
~/.bestie/skills - minimal onboarding/config wizard
- provider-profile LLM calls with fallback diagnostics, including OpenAI/ChatGPT, Anthropic Claude, OpenAI-compatible endpoints, Groq, OpenRouter, Ollama, and native Gemini API-key mode
- basic redacted logs
- Telegram and Zalo channel runtimes behind
bestie channels telegram|zalo - daemon management through
bestie daemon --channel telegram|zalo|cron|all - one Linux user service through
bestie service install|uninstall|restart|status, backed bybestie.serviceand hidden foregroundbestie service run - local SQLite memory, pending approvals, pause/resume, and memory inspection commands
- permission-gated local read/write/action tools, including allowed external workspace paths
- bounded internal subagent spawning through
internal.spawn_subagent - SDK-backed MCP add/list/show/test/tools/classify/login/call, remote HTTP OAuth setup, and classified read calls
- local Doctor diagnostics and safe fixes
- npm version checks through
bestie updateand throttled update notices on chat/daemon/service startup
Do not pull broad MCP/ACP platform work, a plugin marketplace, UI, avatar/body, or hosted/SaaS work into the current scope unless the user explicitly asks.
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.
- 8d ago First seen · 73 lines · 1,098 tokens per session scan A 518cd06c3640
bestie AGENTS.md is an instructions file published in the GitHub repository sirquy/bestie (108 stars, last pushed 2d ago), licensed MIT. It adds 1,098 tokens to every session, about $0.0055 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 instructions, from other repositories
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.