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 commands/gennadiyev/sts2mcp/playsts2git clone --depth 1 https://github.com/Gennadiyev/STS2MCPWrote 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/commands/gennadiyev/sts2mcp/playsts2)<a href="https://agentmods.dev/commands/gennadiyev/sts2mcp/playsts2"><img src="https://agentmods.dev/badge/commands/gennadiyev/sts2mcp/playsts2.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 | $0.00000 | $0.00381 |
| Opus 5 | $0.00000 | $0.00191 |
| Sonnet 5 | $0.00000 | $0.00076 |
| Haiku 4.5 | $0.00000 | $0.00038 |
Grade A, and why
playsts2 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 6d 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
Play Slay the Spire 2 using the MCP tools (mcp__sts2__*). Your goal is to play as well as possible and win the run.
Setup
- Read
AGENTS.mdfor general strategy and MCP calling tips. - Read
GUIDE.mdfor hero-specific strategies. If the current hero isn't covered, adapt and add notes after boss fights. - Call
get_game_state(format="markdown")to see the current state and begin playing.
Gameplay Loop
- Map: Evaluate paths. Prefer elites when healthy, rest sites before bosses.
- Combat: Read intents. Sequence cards optimally (setup → skills → attacks). Play from right-to-left indices when possible to avoid index shift bugs.
- Events: Evaluate options based on current HP, gold, and deck needs.
- Rewards: Skip cards that don't synergize. Claim gold and relics. Potions if slots open.
- Rest Sites: Heal if below 80% HP before boss. Otherwise upgrade or train (Girya).
- Shop: Buy if 100+ gold and something useful is available.
Important Rules
- Always re-check
get_game_stateafter playing cards — indices shift. - Use
format: "json"in combat for precise data,format: "markdown"for overview screens. - Use potions BEFORE playing cards when they grant buffs (e.g. Flex Potion).
- Focus fire on bosses — minions flee when the leader dies.
Learning & Updating
- After each boss is defeated, review what worked and what didn't. Update
GUIDE.mdwith new insights — hero-specific tips, boss strategies, card evaluations, or sequencing discoveries. - If playing a hero not yet in
GUIDE.md, create a new section for them.
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.
- 6d ago First seen · 25 lines · 0 tokens per session scan A 0c8494fc3f1d
playsts2 is a command published in the GitHub repository Gennadiyev/STS2MCP (482 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 381 tokens. 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 commands, from other repositories
unity-doctor
Diagnostic health check — verifies MCP connectivity, .claude/ integrity, Unity project structure, and hook registration.
unity-test
Writes missing tests and runs them via MCP. Identifies untested code, creates EditMode/PlayMode tests, executes via runtests, reports results.
unity-audit
Full project health check — meta file integrity, missing references, assembly definition graph, code quality scan, scene hierarchy audit.
unity-migrate
Plan and execute Unity version or render pipeline migration — identifies deprecated APIs, package compatibility, and executes migration steps.
unity-optimize
Profile and optimize performance — uses MCP profiler for frame timing, memory, rendering stats. Identifies bottlenecks and applies fixes.
unity-feature
Plans and implements a Unity feature — identifies subsystems, loads skills, writes code, sets up scene elements via MCP.