What is onchainai AGENTS.md?

Project instructions for OnchainAI, a crypto tool directory and application that discovers and exposes MCP, command-line, library, API, x402, real-world-asset, and AI-agent tools. They describe the project's structure, development commands, and rules for making changes.

Starting work safely, routing changes to the right documentation, following the required interface checks, and preparing UI or code changes for handoff.

They help contributors work on the project consistently while preserving existing links, buttons, authentication states, filters, and other behavior.

onchainai AGENTS.md — Instructions file for Codex and OpenCode by Coinyak: Project instructions for OnchainAI, a crypto tool directory and…

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/agents-md

Clone the repo

git clone --depth 1 https://github.com/Coinyak/onchainai

Made for: Codex, OpenCode.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/coinyak/onchainai/agents-md.svg)](https://agentmods.dev/instructions/coinyak/onchainai/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/coinyak/onchainai/agents-md"><img src="https://agentmods.dev/badge/instructions/coinyak/onchainai/agents-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 1,367 This file is loaded in full into every session.

When invoked 1,367 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.

Model	Per session	Once invoked
Fable 5	$0.01367	$0.01367
Opus 5	$0.00683	$0.00683
Sonnet 5	$0.00273	$0.00273
Haiku 4.5	$0.00137	$0.00137

Measured 4d ago against content hash bbb8d56c28c0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

onchainai 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 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.

AGENTS.md · 70 lines

How it starts

The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.

OnchainAI

Crypto tool directory: discover, normalize, and expose MCP, CLI, SDK, API, x402, RWA, and AI-agent tools.

Rust API/MCP binary (Axum + sqlx + tokio-cron, Railway) + Next.js frontend (frontend/, Vercel) + Supabase Postgres.

Agent Rule

Keep AGENTS.md under 70 lines. Do not expand it with procedure details; route to wiki docs and executable scripts.

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`

restart-dev.sh, verify-bundle.sh, and deploy-railway.sh are gate/deploy internals — agents do not run them as separate UI steps.

Also once after clone (macOS): ./scripts/install-disk-autoclean.sh schedules an auto-sweep of multi-GB linker snapshots so disk does not silently fill. See docs/DISK_MAINTENANCE.md.

Start

Run git status --short before edits. Do not revert or overwrite unrelated user/agent changes.
Read the relevant topic docs before changing that surface.
Prefer small scoped changes; preserve existing links, buttons, auth states, filters, sidebar behavior, and data-testids unless the task explicitly changes them.
Report verification commands actually run. Do not claim browser/visual QA passed unless it ran.

Topic Routing

Agent workflow and gates: docs/AGENT_HARNESS.md
MCP observability (Vercel/Railway): docs/MCP_AGENT_WORKFLOW.md
Multi-agent coordination (5 roles): docs/MULTI_AGENT_COORDINATION.md
UI/design/layout: DESIGN.md, docs/UI_UX_DESIGN.md, .agents/skills/onchainai-ui-workflow/SKILL.md
Build/deploy (API + Next.js): docs/BUILD_DEPLOY_RULES.md; auto-deploy rules: docs/superpowers/specs/2026-07-05-split-deploy-automation-spec.md
Security/auth/RLS/secrets: docs/SECURITY.md
Architecture/schema/crawler/MCP: docs/MVP_DESIGN.md
Disk/build cleanup: docs/DISK_MAINTENANCE.md
x402 정본: docs/X402_OPEN_LISTING_SPEC.md (open listing + K2 premium); referrals: docs/X402_REFERRAL_SPEC.md; free tier: docs/superpowers/specs/2026-07-04-free-tier-guardian-spec.md
OKX.AI listing (LIVE, ASP #4609): contract + re-submit runbook: docs/listings/directory-forms.md §OKX, scripts/register-okx-asp.sh; prod guard: scripts/k2-prod-smoke.sh
Public launch, plugin bundle (plugin/onchainai/), user connect surface: docs/LAUNCH_READINESS_SPEC.md, docs/CONNECT.md
Operator/admin behavior: docs/OPERATOR_GUIDE.md
Verified/official status requests: run node scripts/verify-tool-official.mjs <slug> --apply (rules: docs/OPERATOR_GUIDE.md §4) — never hand-set tools.status
Promote/take-down highlight carousel cards (+ image sourcing): docs/FEATURED_CARDS.md

Read the full file on GitHub · 70 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.

4d ago First seen · 70 lines · 1,367 tokens per session scan A bbb8d56c28c0

Subscribe to this mod's changes

onchainai AGENTS.md is an instructions file published in the GitHub repository Coinyak/onchainai (1 stars, last pushed 1mo ago), licensed MIT. It adds 1,367 tokens to every session, about $0.0068 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.

ai-agents crypto mcp nextjs x402

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

proofgate AGENTS.md

AGENTS.md instructions for karan68/proofgate: This version has breaking changes — APIs, conventions, and file structure may all differ from your training data. Read the relevant guide in nodemodules/next/dist/docs/ (resolved from this file's directory; in monorepos the next package may not be visible from the repo…

karan68/proofgate · 154 tokens

onchainai AGENTS.md