Borrowing it
Nothing to install: this file belongs to Coinyak/onchainai. 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/Coinyak/onchainai/main/AGENTS.mdgit clone --depth 1 https://github.com/Coinyak/onchainaiWrote 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/coinyak/onchainai/agents-md)<a href="https://agentmods.dev/instructions/coinyak/onchainai/agents-md"><img src="https://agentmods.dev/badge/instructions/coinyak/onchainai/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/coinyak/onchainai/agents-md"><img src="https://agentmods.dev/badge/instructions/coinyak/onchainai/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 | $0.01367 | $0.01367 |
| Opus 5.5 | $0.00547 | $0.00547 |
| Sonnet 5.5 | $0.00273 | $0.00273 |
| Haiku 4.5 | $0.00137 | $0.00137 |
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 1mo 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 — 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 --shortbefore 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-settools.status - Promote/take-down highlight carousel cards (+ image sourcing):
docs/FEATURED_CARDS.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.
- 1mo ago First seen · 70 lines · 1,367 tokens per session scan A bbb8d56c28c0
onchainai AGENTS.md is an instructions file published in the GitHub repository Coinyak/onchainai (1 stars, last pushed 3mo ago), licensed MIT. It adds 1,367 tokens to every session, about $0.0055 per session on Opus 5.5. 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
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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 copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
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.