agentmods.dev

sts2-llm: Instructions file for GitHub Copilot

.github/copilot-instructions.md

sts2-llm copilot-instructions.md is an instructions file for GitHub Copilot from ttxttx1111/sts2-llm. It costs 1,234 tokens per session, scanned A, original, MIT.

Repository instructions for a Slay the Spire 2 player agent, a customisation pack for controlling and remembering gameplay through AI tools. They explain where to place agents, skills, game memory, and MCP configuration, plus the limits of live game control.

In plain words
What is it for?
Use them to add or update Copilot agents and skills, maintain persistent game-run memory, configure STS2 MCP access, and check whether the local game-control setup is ready.
Why use it?
They prevent gameplay customisations from being stored in the wrong place and clarify which files and services are required. They also tell the agent to stop and report a problem when live-control tools are not connected.

Instructions file for GitHub Copilot

Written for GitHub Copilot: a Copilot instructions file.

This is ttxttx1111/sts2-llm's own configuration. It tells GitHub Copilot how to work on sts2-llm itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything sts2-llm configures →

not rated 41repo 3mo ago A scan 1,234 tokens original MIT
View source ↗ ttxttx1111/sts2-llm
Reuse

Borrowing it

Nothing to install: this file belongs to ttxttx1111/sts2-llm. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/ttxttx1111/sts2-llm/main/.github/copilot-instructions.md
Clone the repo
git clone --depth 1 https://github.com/ttxttx1111/sts2-llm

Made for: GitHub Copilot.

Wrote 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.

agentmods badge for sts2-llm copilot-instructions.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/ttxttx1111/sts2-llm/copilot-instructions/github.svg)](https://agentmods.dev/instructions/ttxttx1111/sts2-llm/copilot-instructions)
Your own site
<a href="https://agentmods.dev/instructions/ttxttx1111/sts2-llm/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/ttxttx1111/sts2-llm/copilot-instructions/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.

agentmods 80×15 button for sts2-llm copilot-instructions.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/ttxttx1111/sts2-llm/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/ttxttx1111/sts2-llm/copilot-instructions.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,234 This file is loaded in full into every session.
When invoked 1,234 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01234 $0.01234
Opus 5.5 $0.00494 $0.00494
Sonnet 5.5 $0.00247 $0.00247
Haiku 4.5 $0.00123 $0.00123

Measured 1mo ago against content hash 7eaa9c98ef57, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

sts2-llm copilot-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 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.

.github/copilot-instructions.md · 60 lines

How it starts

The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Copilot instructions for this repository

This repository is a GitHub Copilot customization pack for a Slay the Spire 2 player agent, not an application codebase.

Source of truth for customizations

  • Put direct-open agents in .github/agents/
  • Put reusable skills in .github/skills/<skill-name>/
  • Put persistent STS2 run memory in .github/sts2-memory/
  • Put shared VS Code MCP server configuration in .vscode/mcp.json

Runtime assumptions

  • The local game install is expected at D:\program\steam\steamapps\common\Slay the Spire 2\
  • Gameplay control is provided by the STS2MCP mod over localhost:15526
  • In VS Code, the shared MCP setup for this repo lives in .vscode/mcp.json, which uses the VS Code-style servers key
  • In Copilot CLI, equivalent MCP access can come from a temporary current-session attach or from /mcp add / ~/.copilot/mcp-config.json; the CLI home config uses mcpServers
  • A custom agent or skill may load successfully even when the current session does not have STS2 MCP tools attached; in that case live piloting must stop at the MCP-readiness check and report the blocker plainly
  • In Copilot CLI, if the current session already has STS2 MCP tools attached, treat that as good enough to play immediately rather than insisting on persistence first
  • In Copilot CLI, if live STS2 piloting must also work in a fresh session or custom agent, prefer a persistent MCP configuration that is available at session start rather than relying on another session's MCP attachment
  • When the only missing piece is that persistent CLI MCP config and the agent can edit local files, prefer repairing ~/.copilot/mcp-config.json directly before asking the user to do manual setup

Authoring rules for this repo

  • Keep skills and agent instructions reusable; do not hardcode a single run, seed, or class unless the file is explicitly scoped that way
  • Prefer official Copilot customization formats and frontmatter; do not invent custom control files or ad-hoc schemas
  • Encode gameplay guidance as evidence-backed heuristics, and clearly separate general rules from class-specific or relic-specific advice
  • Record meaningful design decisions and behavior changes in repo documentation so the reasoning behind updates stays traceable
  • Keep a concise update log whenever the player workflow changes materially, so the final merged documentation can be assembled from a clear change history
  • Treat .github/design/README.md and .github/design/system-details.md as the maintained entrypoints for current architecture and workflow design
  • Write changelog entries under .github/changelog/ with one markdown file per feature or workflow change plus an updated .github/changelog/README.md index
  • Do not use prepare_task/ as the long-term source of truth for feature history; leave prepare_task/change-log.md as a compatibility pointer only
  • When changing overall workflow, memory structure, review rules, skill boundaries, or agent orchestration, update the design docs in .github/design/
  • When the workspace is a git repository, make coherent commits for completed milestones instead of leaving important design and workflow changes ungrouped
  • Preserve the distinction between:
    • always-on instructions (copilot-instructions.md)
    • reusable capabilities (skills)
    • persistent persona/tooling (custom agents)
  • Assume the user may interact in Chinese; default to concise Chinese unless the user switches languages

Read the full file on GitHub · 60 lines

Changes

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.

  1. 1mo ago First seen · 60 lines · 1,234 tokens per session scan A 7eaa9c98ef57

Subscribe to this mod's changes

sts2-llm copilot-instructions.md is an instructions file published in the GitHub repository ttxttx1111/sts2-llm (41 stars, last pushed 3mo ago), licensed MIT. It adds 1,234 tokens to every session, about $0.0049 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 2026-08-30.

Game developmentai-agentcopilot-cligithub-copilotmcpslay-the-spire-2sts2
Related

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).

microsoft/vscode · 9,715 tokens

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.

vercel/next.js · 7,461 tokens

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).

microsoft/vscode · 5,262 tokens

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.

langchain-ai/langchain · 4,680 tokens

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).

microsoft/vscode · 2,731 tokens

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.

deepseek-ai/deepseek-harness · 4,261 tokens