Borrowing it
Nothing to install: this file belongs to caprica-Six/hyperliquid-insights-web. 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/caprica-Six/hyperliquid-insights-web/main/AGENTS.mdgit clone --depth 1 https://github.com/caprica-Six/hyperliquid-insights-webWrote 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/caprica-six/hyperliquid-insights-web/agents-md)<a href="https://agentmods.dev/instructions/caprica-six/hyperliquid-insights-web/agents-md"><img src="https://agentmods.dev/badge/instructions/caprica-six/hyperliquid-insights-web/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 | $0.00573 | $0.00573 |
| Opus 5 | $0.00287 | $0.00287 |
| Sonnet 5 | $0.00115 | $0.00115 |
| Haiku 4.5 | $0.00057 | $0.00057 |
Grade A, and why
hyperliquid-insights-web 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 7d 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agents for hyperliquid-insights-web
This document describes the purpose and scope of lightweight agents (Cursor skills) for this repository and gives examples and expectations for their behavior.
Purpose
- Help contributors automate routine tasks (fix lint/format, run tests, add small components, update docs).
- Provide a small, safe skill that has scoped access to the repository and follows simple rules.
Scope & Access
- Files the skill may read and update (by default):
app/**,components/**,lib/**,mock-data/**,types/**- Project meta files:
package.json,tsconfig.json,next.config.ts,README.md
- The skill should avoid touching secret/credential files and should never commit literal secrets.
Expectations / Workflow
- Before making changes, run the following locally:
npm run lint— verify lint passesnpm run format— apply formattingnpm test— run unit tests (vitest)
- For non-trivial changes, include or update tests and documentation.
- Prefer TypeScript (
.ts,.tsx) changes; do not add plain JavaScript files unless requested.
Example agent tasks
- Add a new UI component in
components/following existing patterns. - Fix a failing unit test and add a test that covers the regression.
- Improve a helper in
lib/, update types intypes/, and run format/tests.
Prompts / Examples
Example 1 — small feature addition:
User: "Add a MarketCard component that displays market name, price, and 24h change following our ui/card pattern. Add a test under components/ and update components/index.tsx if needed."
Assistant: "I will add components/MarketCard.tsx, a simple test at components/MarketCard.test.tsx, and wire it in. I will run prettier formatting and ensure tests pass locally; I will not commit if tests fail."
Example 2 — fix formatting & lint:
User: "Fix formatting and lint errors in lib/format.ts."
Assistant: "I will run prettier and eslint --fix for the repository, and report any remaining lint failures for manual review."
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.
- 7d ago First seen · 55 lines · 573 tokens per session scan A f945f3bc5b52
hyperliquid-insights-web AGENTS.md is an instructions file published in the GitHub repository caprica-Six/hyperliquid-insights-web (1 stars, last pushed 4mo ago), licensed MIT. It adds 573 tokens to every session, about $0.0029 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 2026-08-31.
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.