Borrowing it
Nothing to install: this file belongs to gblinproject/gblin-treasury-risk-regime. 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/gblinproject/gblin-treasury-risk-regime/main/AGENTS.mdgit clone --depth 1 https://github.com/gblinproject/gblin-treasury-risk-regimeWrote 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/gblinproject/gblin-treasury-risk-regime/agents-md)<a href="https://agentmods.dev/instructions/gblinproject/gblin-treasury-risk-regime/agents-md"><img src="https://agentmods.dev/badge/instructions/gblinproject/gblin-treasury-risk-regime/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/gblinproject/gblin-treasury-risk-regime/agents-md"><img src="https://agentmods.dev/badge/instructions/gblinproject/gblin-treasury-risk-regime/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 | $0.02144 | $0.02144 |
| Opus 5.5 | $0.00858 | $0.00858 |
| Sonnet 5.5 | $0.00429 | $0.00429 |
| Haiku 4.5 | $0.00214 | $0.00214 |
Grade A, and why
gblin-treasury-risk-regime 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 — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — GBLIN MCP Server
Instructions for AI coding agents (Claude Code, Cursor, Windsurf, GitHub Copilot, Codex, etc.) working on this repository, and general guidance for any AI assistant building autonomous agents on Base mainnet that need to manage USDC.
Humans should read
README.mdfirst.
What this repo is
@gblin-protocol/mcp-server is the official Model Context Protocol server
for the GBLIN protocol on Base mainnet. It exposes twenty tools that let any AI
agent read live treasury state, verify governance and attestations, and
produce ready-to-broadcast calldata to enter, leave and bid.
GBLIN is the treasury standard for AI agents on Base: an on-chain
45 % cbBTC + 45 % WETH + 10 % USDC basket with an automated Crash Shield, plus
a deterministic JIT redemption (the Zap's sellGBLINForEth + one WETH→USDC
swap) that lets agents convert GBLIN to USDC the moment an x402 invoice arrives.
Tech stack (working on this codebase)
- Language: TypeScript strict, ES modules
- Runtime: Node.js 20+ (no DOM, no React)
- MCP SDK:
@modelcontextprotocol/sdkover stdio - On-chain reads:
viemagainst Base mainnet - No external services: no telemetry, no analytics, no key custody
- License: MIT
Hard rules for code edits
- Never broadcast transactions. Tools return calldata; the user's wallet signs and broadcasts. The server must remain key-less.
- Never accept
minOut = 0. Every swap quote must produce a strictly positiveminOutderived from the Lens (quoteSell/quoteBuy) plus a dynamic slippage buffer (2.5 % normal / 4 % during Crash Shield). - Stale-feed guard. Reject any Chainlink answer that is non-positive or
older than the vault accepts: 26 hours for a stable asset's feed, the
vault's own
oracleAge(read live through the Lens) for every other. The server never quotes on a price the contract would refuse; tools abort with a clear error rather than return bad data. - No new RPC endpoints. Stick to Base mainnet via the user-supplied
GBLIN_RPC_URLenv var (defaults tohttps://base-rpc.publicnode.com). - No emoji in code or commits unless the user explicitly asks.
- TypeScript strict. No
any, no// @ts-ignore. Runnpm run buildbefore claiming a change is done. - Tools must be deterministic. Same inputs at the same block → same output. No randomness, no timestamps embedded in calldata.
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 Changed · +27 lines · +617 tokens per session b1d36d126f6f
- 1mo ago Changed · +2 lines · +50 tokens per session 2c0670df527c
- 1mo ago Changed · +2 lines · +52 tokens per session 3be6dc29fb0d
- 2mo ago First seen · 131 lines · 1,425 tokens per session scan A 55eab643e4d0
gblin-treasury-risk-regime AGENTS.md is an instructions file published in the GitHub repository gblinproject/gblin-treasury-risk-regime (1 stars, last pushed 15d ago), licensed MIT. It adds 2,144 tokens to every session, about $0.0086 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.
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.
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).