Borrowing it
Nothing to install: this file belongs to IvanLi-CN/tavily-hikari. 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/IvanLi-CN/tavily-hikari/main/AGENTS.mdgit clone --depth 1 https://github.com/IvanLi-CN/tavily-hikariWrote 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/ivanli-cn/tavily-hikari/agents-md)<a href="https://agentmods.dev/instructions/ivanli-cn/tavily-hikari/agents-md"><img src="https://agentmods.dev/badge/instructions/ivanli-cn/tavily-hikari/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/ivanli-cn/tavily-hikari/agents-md"><img src="https://agentmods.dev/badge/instructions/ivanli-cn/tavily-hikari/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 | $0.01811 | $0.01811 |
| Opus 5 | $0.00905 | $0.00905 |
| Sonnet 5 | $0.00362 | $0.00362 |
| Haiku 4.5 | $0.00181 | $0.00181 |
Grade A, and why
tavily-hikari AGENTS.md scanned grade A with 1 finding 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 9d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- 后端服务参与该验证时,Health: `curl -s http://127.0.0.1:58087/health` → `200`; Summary: `curl -s http://127.0.0.1:58087/api/summary | jq .`. How it starts
The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Project Structure & Module Organization
src/: Rust backend (main.rs,lib.rs,server.rs).web/: Vite + React SPA (TypeScript). Built assets inweb/dist..env: local config (e.g.,TAVILY_API_KEYS). Do not commit secrets.- SQLite files (
*.db) are runtime artifacts and safe to ignore.
Build, Test, and Development Commands
- Repo tooling
bun install --frozen-lockfile— install root tooling deps and run the shared hook installer.bun run hooks:install— reinstall the sharedpost-checkouthook and refreshlefthookcommit hooks when the binary is available onPATH.bun run worktree:setup— force a strict linked-worktree repair for env/deps/cargo fetch.bun run test:worktree-bootstrap— run the linked-worktree bootstrap smoke contract.
- Backend
cargo build— compile the server.cargo run -- --help— show CLI flags;--bind/--port/--db-pathetc.cargo fmt— format Rust code;cargo clippy --locked -j 2 -- -D warnings— lint.cargo test— run tests (add as you go).
- Frontend (
web/)bun install --frozen-lockfile— install deps;bun run --bun dev— local dev (Vite under Bun runtime).bun run build— build SPA toweb/dist;bun run preview— preview build.bun run storybook— run Storybook dev server athttp://127.0.0.1:56006.
- Hooks
bun install --frozen-lockfileorbun run hooks:install— install the sharedpost-checkouthook; iflefthookexists onPATH, also refresh pre-commit (cargo fmt,clippy, Markdown format) and commitlint.
Coding Style & Naming Conventions
- Rust: 2024 edition, rustfmt defaults; modules/files
snake_case, typesPascalCase, functions/varssnake_case. - TypeScript/React: components
PascalCasein*.tsx; hooksuseXxx. - Markdown: formatted by dprint (line width 100). Run
bunx --bun dprint fmtfor changed.md.
Testing Guidelines
- Rust: prefer module unit tests via
#[cfg(test)]and integration tests undertests/when needed. Run withcargo test. - Frontend: no test tooling preconfigured; if introducing tests, prefer Vitest + React Testing Library in
web/. - Backend execution: before selecting focused, shard, full, release, or Compose validation, read
docs/agents/testing.md.
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.
- 9d ago First seen · 120 lines · 1,811 tokens per session scan A f2f7dde2d7fd
tavily-hikari AGENTS.md is an instructions file published in the GitHub repository IvanLi-CN/tavily-hikari (349 stars, last pushed yesterday), licensed MIT. It adds 1,811 tokens to every session, about $0.0091 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
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.
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).
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).
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.