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.
npx agentmods add instructions/suigar-gaming/ts-sdks/agents-mdgit clone --depth 1 https://github.com/Suigar-Gaming/ts-sdksWrote 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/suigar-gaming/ts-sdks/agents-md)<a href="https://agentmods.dev/instructions/suigar-gaming/ts-sdks/agents-md"><img src="https://agentmods.dev/badge/instructions/suigar-gaming/ts-sdks/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 | $0.03970 | $0.03970 |
| Opus 5 | $0.01985 | $0.01985 |
| Sonnet 5 | $0.00794 | $0.00794 |
| Haiku 4.5 | $0.00397 | $0.00397 |
Grade A, and why
ts-sdks 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 5d 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 — 293 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This file provides guidance to AI agents working with code in this repository.
Overview
This repository contains the TypeScript SDK workspace for Suigar v2 on Sui. The current publishable packages are @suigar/sdk under packages/sdk and @suigar/mcp under packages/mcp. Both packages are ESM-only. The main public SDK integration surface is the suigar() client extension, which is used to build and serialize game transactions on top of @mysten/sui.
Common Commands
Setup and Build
# Initial setup
pnpm install
# Generate bindings and build the package
pnpm --dir packages/sdk run build
# Build without regenerating contract bindings
pnpm --dir packages/sdk run build:ci
# Build the MCP package and bundled MCP App
pnpm turbo run build --filter=@suigar/mcp
# Build and run the local stdio MCP server for manual client testing
pnpm turbo run build --filter=@suigar/mcp
node packages/mcp/dist/bin.mjs
# Regenerate Move contract bindings only
pnpm --dir packages/sdk run codegen
Testing
# Run the full test suite
pnpm --dir packages/sdk run test
# Run type checking
pnpm --dir packages/sdk run typecheck
pnpm --dir packages/mcp run typecheck
# Run a specific vitest file
pnpm --dir packages/sdk exec vitest run test/unit/transactions.test.ts
# Run a specific test name
pnpm --dir packages/sdk exec vitest run -t "builds a coinflip transaction with the configured package id"
Linting and Formatting
# Check lint and formatting
pnpm run lint
# Auto-fix lint and formatting issues
pnpm run lint:fix
Package Management
# Create a changeset
pnpm run changeset
# Apply version updates from changesets
pnpm run changeset:version
# Publish release changes
pnpm run release
Architecture
Repository Structure
packages/sdk/-@suigar/sdkpackage rootsrc/- SDK source codeclient.ts-suigar()extension registration and extension client implementationtransactions/- transaction builders for standard and PvP gamescontracts/- generated Move bindings and BCS helperstypes/- public option and config typesutils/- public parser, constants, and numeric helpers exposed through@suigar/sdk/utilshelpers/- internal config resolution, metadata encoding, and transaction support helpersconfigs/- network-scoped package ids, supported coin types, and price info object ids
packages/sdk/test/unit/- Vitest coverage for config resolution, cache helpers, and transaction builderspackages/mcp/-@suigar/mcpstdio MCP server and MCP Appsrc/server.ts- MCP server, tool registration, and app resource registrationsrc/tools.ts- SDK-backed tool handlers for config, metadata, and unsigned transaction buildingsrc/app/- Vite-built single-file MCP App UItest/- Vitest coverage for tools and app resource behavior
packages/sdk/dist/- generated build outputtsconfig.shared.json- shared TypeScript compiler options for workspace packagesplayground/- workspace-local Next.js integration playground
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.
- 5d ago First seen · 293 lines · 3,970 tokens per session scan A b158238919d2
ts-sdks AGENTS.md is an instructions file published in the GitHub repository Suigar-Gaming/ts-sdks (0 stars, last pushed yesterday), licensed Apache-2.0. It adds 3,970 tokens to every session, about $0.0198 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
agent-wallet-sdk AGENTS.md
AGENTS.md instructions for up2itnow0822/agent-wallet-sdk, covering agents.md -- agent wallet sdk, purpose, ownership, local contracts and work guidance.
headless-coder-sdk CLAUDE.md
Instructions for OhadAssulin/headless-coder-sdk, covering claude.md, build & development commands, internally runs: node ./scripts/run-workspaces.mjs build, internally runs: node ./scripts/run-workspaces.mjs test and build a single package.
typescript AGENTS.md
AGENTS.md instructions for typeship-ax/typescript, covering typeship — agent context, ground rules, authentication, using the sdk and documentation.
aptos-ts-sdk CLAUDE.md
Claude Code instructions for aptos-labs/aptos-ts-sdk, covering claude.md, project overview, runtime compatibility, common commands and commit guidelines.
mailrith-agent-platform GEMINI.md
Gemini CLI instructions for anrawool/mailrith-agent-platform: Use the Mailrith MCP server and the mailrith-email-marketing skill for Mailrith email marketing work.
aptos-ts-sdk AGENTS.md
AGENTS.md instructions for aptos-labs/aptos-ts-sdk, covering agents.md, project overview, runtime compatibility, requirements and repo layout.