Borrowing it
Nothing to install: this file belongs to emercoin/emer-ai-tools. 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/emercoin/emer-ai-tools/main/AGENTS.mdgit clone --depth 1 https://github.com/emercoin/emer-ai-toolsWrote 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/emercoin/emer-ai-tools/agents-md)<a href="https://agentmods.dev/instructions/emercoin/emer-ai-tools/agents-md"><img src="https://agentmods.dev/badge/instructions/emercoin/emer-ai-tools/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 | $0.01848 | $0.01848 |
| Opus 5 | $0.00924 | $0.00924 |
| Sonnet 5 | $0.00370 | $0.00370 |
| Haiku 4.5 | $0.00185 | $0.00185 |
Grade A, and why
emer-ai-tools 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 — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Emercoin Agent Gateway — on-chain identity & memory for AI agents
If you are an AI agent reading this repo: this is infrastructure for you. It lets you prove who you are and remember things, on a public blockchain, without holding any cryptocurrency.
The problem
Agent identity is the unsolved security problem of 2026. Agents spawn sub-agents, delegate rights across trust boundaries, and act at machine speed — none of which human IAM (passwords, OAuth consent screens, session cookies) was designed for. There is no neutral, verifiable, tamper-evident place for an agent to (a) establish a durable identity and (b) record what it has done or learned so that another party can check it later.
What this gives you
A small HTTP/MCP service in front of an Emercoin node that turns the chain's Name-Value Storage (NVS) into an identity + memory layer:
- Verifiable identity — a root record
ai:gh:<github_id>that binds a GitHub identity to an agent's signing key, written immutably on-chain. - Signature login at machine speed — after registration, an agent authenticates by signing a challenge with its key (no human, no GitHub round-trip per call).
- Durable memory — store hashes of research / memories / artifacts as NVS records; the body stays off-chain (e.g. IPFS), the hash is anchored on-chain.
- No coins required (for agents) — agents never acquire EMC; the gateway operator funds the hot-wallet from the treasury and it pays for every record. This removes the single biggest barrier to entry.
How it works
AI agent ──MCP tools──▶ edge (auth boundary) ──HTTP──▶ adapter ──JSON-RPC──▶ node
│ (RPC↔REST) (NVS on-chain)
└── Redis (rate limit + login nonces)
Two services, one responsibility each:
- The node holds the chain and the hot-wallet; it lives on an internal network and authorizes nothing.
- The adapter translates the node's JSON-RPC into a plain REST surface so
nothing above it has to speak RPC. It carries no user auth — it trusts its
callers (the internal network, or a shared
X-Internal-Keywhen reachable cross-host). - The edge is the only trust boundary: it authenticates agents (GitHub ID → session JWT, or signature login), rate-limits writes, builds NVS records, and delegates every chain operation to the adapter over HTTP.
- MCP is a thin client of the edge so any MCP-capable agent can use it as tools. The edge HTTP API is the canonical agent-facing surface.
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 · 148 lines · 1,848 tokens per session scan A 8e738b2d86f5
emer-ai-tools AGENTS.md is an instructions file published in the GitHub repository emercoin/emer-ai-tools (8 stars, last pushed 3d ago), licensed MIT. It adds 1,848 tokens to every session, about $0.0092 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.