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 instructions/heyhuynhgiabuu/proxypal/agents-mdgit clone --depth 1 https://github.com/heyhuynhgiabuu/proxypalWhat 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 | $0.00716 | $0.00716 |
| Opus 5 | $0.00358 | $0.00358 |
| Sonnet 5 | $0.00143 | $0.00143 |
| Haiku 4.5 | $0.00072 | $0.00072 |
Grade A, and why
proxypal 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 yesterday.
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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ProxyPal
Tauri v2 desktop app — proxy API management with SolidJS frontend and Rust backend.
Stack
- Frontend: SolidJS 1.9 + TypeScript 5.6 + Tailwind CSS 3 + Kobalte UI
- Backend: Rust (Tauri v2, 10 plugins: dialog, fs, updater, deep-link, etc.)
- Build: Vite 6 + Tauri CLI | Test: Vitest 4 | PM: pnpm
- Charts: ECharts 6 + Chart.js 4 | i18n: @solid-primitives/i18n
Structure
src/ # SolidJS frontend
components/ # UI components (22+), charts/, ui/
pages/ # Dashboard, Analytics, ApiKeys, Settings, etc.
stores/ # Reactive stores (app, requests, theme, toast)
i18n/ # Internationalization (locale, catalog)
lib/ # Utilities (tauri bindings, quotaCache)
src-tauri/src/ # Rust backend
commands/ # Tauri commands (proxy, cloudflare, ssh, config)
types/ # Shared type definitions (16 modules)
lib.rs # Main library entry
config.rs, state.rs # App config and state management
Commands
pnpm tauri dev # Dev (frontend + backend)
pnpm tsc --noEmit # Type check (frontend)
pnpm check:ts # Fast type check (uses tsgo when available, falls back to tsc)
pnpm check:parallel # Parallel: type check + lint + format
cd src-tauri && cargo check # Type check (backend)
pnpm test # Vitest (10 tests, 3 files)
pnpm build # Vite build (frontend only)
Code Style
// SolidJS: interface above component, splitProps, `class` not `className`
interface ProviderCardProps {
name: string;
provider: Provider;
connected: number;
onConnect: (provider: Provider) => Promise<void>;
}
export function ProviderCard(props: ProviderCardProps) {
const [loading, setLoading] = createSignal(false);
// ...
}
// Rust: Result<T, String>, State<AppState>, #[serde(rename_all = "camelCase")]
#[tauri::command]
pub fn save_config(state: State<AppState>, config: AppConfig) -> Result<(), String> {
let mut current_config = state.config.lock().unwrap();
*current_config = config;
Ok(())
}
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.
- yesterday First seen · 77 lines · 716 tokens per session scan A 53890878f2a0
proxypal AGENTS.md is an instructions file published in the GitHub repository heyhuynhgiabuu/proxypal (1,195 stars, last pushed 10d ago), licensed MIT. It adds 716 tokens to every session, about $0.0036 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
langchain 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.
CLIProxyAPI AGENTS.md
Instructions for router-for-me/CLIProxyAPI, covering agents.md, repository, commands, config and architecture.
neo-chat AGENTS.md
Instructions for u14app/neo-chat, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and testing guidelines.
ima2-gen AGENTS.md
Instructions for lidge-jun/ima2-gen, covering ima2-gen — ai context, what this project does, tech stack, project structure and agent skills (packaged).
opencodex AGENTS.md
Instructions for lidge-jun/opencodex, covering agents.md, what this project is, repository layout, optional subsystems stay off the core path and the devlog directory.
langchain CLAUDE.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.