agentmods.dev

onchainai copilot-instructions.md

onchainai copilot-instructions.md is an instructions file for GitHub Copilot from Coinyak/onchainai. It costs 969 tokens per session, scanned A, original, MIT.

Project-specific instructions for OnchainAI, a cryptocurrency tool directory built with Rust and web technologies. They describe the required development commands, architecture, and rules for UI, authentication, routing, and server work.

In plain words
What is it for?
Use them when changing OnchainAI's UI, authentication, routing, or server code, and when running its development, build, and test workflows.
Why use it?
They prevent common project mistakes, such as using commands that leave the browser code out of date or testing server code without the required feature.

Instructions file for GitHub Copilot

not rated 1 1mo ago A scan 969 tokens original MIT
View the source file Coinyak/onchainai
Install

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.

agentmods
npx agentmods add instructions/coinyak/onchainai/copilot-instructions
Clone the repo
git clone --depth 1 https://github.com/Coinyak/onchainai

Made for: GitHub Copilot.

Wrote 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.

agentmods badge for onchainai copilot-instructions.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/coinyak/onchainai/copilot-instructions.svg)](https://agentmods.dev/instructions/coinyak/onchainai/copilot-instructions)
Your own site
<a href="https://agentmods.dev/instructions/coinyak/onchainai/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/coinyak/onchainai/copilot-instructions.svg" alt="Measured on agentmods" height="20"></a>
Per session 969 This file is loaded in full into every session.
When invoked 969 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00969 $0.00969
Opus 5 $0.00485 $0.00485
Sonnet 5 $0.00194 $0.00194
Haiku 4.5 $0.00097 $0.00097

Measured 4d ago against content hash e099a112e415, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

onchainai copilot-instructions.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 4d 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.

.github/copilot-instructions.md · 59 lines

How it starts

The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Copilot instructions — OnchainAI

Primary source of truth: AGENTS.md. Read it first. It defines commands, architecture, code style, and rules. This file mirrors the essentials for GitHub Copilot.

Project

Crypto tool directory. Rust single binary: Leptos SSR + Axum + rmcp (MCP) + sqlx + tokio-cron-scheduler.

3-Command UI Workflow

When Command
Once after clone ./scripts/install-agent-hooks.sh
While iterating on UI/auth/routing ./scripts/dev-watch.sh
Before handoff/commit ./scripts/ui-change-gate.sh

Do not finish UI/auth/routing work with cargo build --features ssr, cargo build --release --features ssr, or cargo run --features ssr — they leave WASM stale. Iterate with dev-watch.sh; run ui-change-gate.sh before handoff/commit.

Build / test (server features required)

The crate default feature set is empty. Plain cargo commands that touch server code need --features ssr:

  • cargo check --features ssr — non-UI compile check
  • cargo test --features ssr — tests
  • ONCHAINAI_REQUIRE_DB_TESTS=1 cargo test --features ssr --test review_tool_execution -- --nocapture — fail if review-tool DB integration tests skip
  • cargo clippy --features ssr -- -W clippy::all — lint (must pass before commit)
  • cargo fmt --check — format check
  • cargo leptos build --release — full build (SSR binary + WASM + CSS); used by the UI gate, not for UI iteration

Disk hygiene (IMPORTANT — keep builds from filling the disk)

Rust debug builds bloat target/ fast. Expected, not a bug. Repo is configured to control it — follow this so disk never fills mid-session:

  • Automatic, do not revert: Cargo.toml [profile.dev] uses debug = "line-tables-only" and strips dependency debug info → slower target/debug growth.
  • Before any heavy/release build: run ./scripts/disk-guard.sh. It auto-cleans incremental caches when free disk < 25GB or target/ > 35GB, then re-checks.
  • Between sessions / after many builds: ./scripts/clean-build-artifacts.sh --incremental-only (fast; keeps compiled deps).
  • Only when disk is tight: ./scripts/clean-build-artifacts.sh or cargo clean (next build is a slow full recompile).
  • Never commit target/, .playwright-cli/, or build artifacts.

Read the full file on GitHub · 59 lines

Changes

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.

  1. 4d ago First seen · 59 lines · 969 tokens per session scan A e099a112e415

Subscribe to this mod's changes

onchainai copilot-instructions.md is an instructions file published in the GitHub repository Coinyak/onchainai (1 stars, last pushed 1mo ago), licensed MIT. It adds 969 tokens to every session, about $0.0048 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.

Web3 and blockchainai-agentscryptomcpnextjsx402
Related

Other instructions, from other repositories

pip-web CLAUDE.md

Claude Code instructions for playpip/pip-web, covering claude.md — agent guide for pip, read first (by task), the three layers (respect the boundaries), non-negotiables and commands / definition of done.

playpip/pip-web · 912 tokens

deltasignal-atlas-codex-plugin CLAUDE.md

Claude Code instructions for aitrailblazer/deltasignal-atlas-codex-plugin, covering evidence boundary, project role, core operating rule, claude code mcp install path and first-run policy.

aitrailblazer/deltasignal-atlas-codex-plugin · 4,068 tokens

crypto-market-data AGENTS.md

AGENTS.md instructions for nirholas/crypto-market-data, covering crypto-market-data development guidelines, project overview, terminal management and contributing.

nirholas/crypto-market-data · 249 tokens

ethereum-wallet-toolkit GEMINI.md

Gemini CLI instructions for nirholas/ethereum-wallet-toolkit, covering ethereum-wallet-toolkit and terminal management.

nirholas/ethereum-wallet-toolkit · 181 tokens

aixyz CLAUDE.md

Claude Code instructions for AgentlyHQ/aixyz, a project described as: Next.js-like framework building AI Agents that are payment-native. Bootstrap your agent with A2A, MCP, x402 payments, and ERC-8004 identity.

AgentlyHQ/aixyz · 3 tokens

cryptopilot-mcp CLAUDE.md

Claude Code instructions for cryptopilot-tools/cryptopilot-mcp, covering claude.md, project, stack, architecture and mcp tools (5).

cryptopilot-tools/cryptopilot-mcp · 1,640 tokens