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/ttxttx1111/sts2-llm/runtimegit clone --depth 1 https://github.com/ttxttx1111/sts2-llmWhat 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 | $0.00194 | $0.00194 |
| Opus 5 | $0.00097 | $0.00097 |
| Sonnet 5 | $0.00039 | $0.00039 |
| Haiku 4.5 | $0.00019 | $0.00019 |
Grade A, and why
sts2-llm runtime.instructions.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 3d 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.
What it actually says
runtime 相关指令
- 保持架构分工：player 决策，runtime 持久化与监督，reviewer 基于证据学习。
- 不要为
map_route、shop、rest_site、event、rewards、card_reward、boss_relic重新添加浅层局部 heuristics，除非只是非常窄的机械性 fallback。 - 修改 live runtime 代码时，优先让 standalone player 作为执行引擎，而不是在 coordinator 里重复实现战术逻辑。
- 保持证据链可审计：先 event，再 summary，再 lesson。
- 如果碰到归档的 legacy runtime JSON，明确把它们当历史材料，不要误接回活动主路径。
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.
- 3d ago First seen · 12 lines · 194 tokens per session scan A a2e747083ada
sts2-llm runtime.instructions.md is an instructions file published in the GitHub repository ttxttx1111/sts2-llm (41 stars, last pushed 1mo ago), licensed MIT. It adds 194 tokens to every session, about $0.0010 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 2026-08-30.
Other instructions, from other repositories
Build-CLI AGENTS.md
Instructions for microsoft/Build-CLI, covering agents.md, plugin ecosystems, sync rules, cli and cli behavior contracts.
STS2MCP AGENTS.md
Instructions for Gennadiyev/STS2MCP, covering sts2 mcp — ai gameplay guide, mcp tool calling tips, state polling, card index shifting and event & reward flow.
spec-kit-copilot AGENTS.md
Instructions for github/spec-kit-copilot, covering what this repository is, core skills plugin, core decisions (do not silently undo) and when revving the core skills plugin.
groundhog-day AGENTS.md
Instructions for DUBSOpenHub/groundhog-day, covering agents.md: working guide for ai agents, architecture, file ownership map, key design decisions and 1. no external dependencies beyond standard tools.
copilot-brag-sheet AGENTS.md
Instructions for microsoft/copilot-brag-sheet, covering agents.md, 1. project overview, 2. architecture map, 3. build / test / lint commands and run a single test file.
apex-accelerator iac-bicep-best-practices.instructions.md
Bicep-specific IaC best practices for Azure templates. Security baseline, naming, AVM mandate, anti-patterns.