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/sisyphe42/reignsagent/agents-mdgit clone --depth 1 https://github.com/Sisyphe42/ReignsAgentWrote 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/sisyphe42/reignsagent/agents-md)<a href="https://agentmods.dev/instructions/sisyphe42/reignsagent/agents-md"><img src="https://agentmods.dev/badge/instructions/sisyphe42/reignsagent/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 | $0.02277 | $0.02277 |
| Opus 5 | $0.01138 | $0.01138 |
| Sonnet 5 | $0.00455 | $0.00455 |
| Haiku 4.5 | $0.00228 | $0.00228 |
Grade A, and why
ReignsAgent 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ReignsAgent System Specification & Agent Guidelines
0. Project Goal
ReignsAgent is a production-oriented, Reigns-like agentic game product for generating, testing, editing, previewing, and shipping card-based narrative experiences.
This is not only a developer middleware project. The final system must be usable by real content creators through a functional frontend where they can import content, configure or connect AI generation, edit generated cards, structure narrative progression, preview gameplay, inspect narrative and balance diagnostics, and prepare deployable game builds. Architecture must remain separated, but the product goal includes a complete user-facing creation and publishing workflow.
The long-term goal is a self-improving loop:
- Core runs the game rules headlessly and stays small, deterministic, and UI-free.
- Reviewer stress-tests card sets through Monte Carlo simulation and emits objective JSON diagnostics for coverage, pacing, endings, dead paths, and balance.
- Pipeline imports local content, calls generation connectors, and uses Reviewer diagnostics to propose or generate corrections.
- Interface provides the production frontend for content development, AI configuration, editing, preview, diagnostics, and deployment preparation while preserving module boundaries.
The project should optimize for pure left/right card interaction, inspectable data, automated narrative/balance feedback, and modular evolution. The player-facing game must remain the cleanest possible Reigns-style swipe experience, but the authored content may still contain data-driven chapters, themes, story arcs, endings, and stateful narrative evolution.
Narrative progression and Anti-RPG boundary: the system may support data-driven story progression through author-defined tags, variables, metadata, chapters, themes, arcs, endings, and configurable state/gauge presentation. These are narrative organization and authoring concepts, not built-in RPG management systems. The system must not ship predefined equipment, pets, inventory, shop, rarity, crafting, character-build, skill-tree, loot, or resource-management gameplay. Any such concepts may exist only as user-authored data labels interpreted by custom content, not as built-in gameplay loops, UI systems, or product features. The visible gameplay remains pure card text plus binary left/right choices.
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 · 68 lines · 2,277 tokens per session scan A 2dcc1051fef8
ReignsAgent AGENTS.md is an instructions file published in the GitHub repository Sisyphe42/ReignsAgent (298 stars, last pushed yesterday), licensed MIT. It adds 2,277 tokens to every session, about $0.0114 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
novel-to-game AGENTS.md
AGENTS.md instructions for zenstory-ai/novel-to-game, covering noveltogame engineering guide, rules and verification.
fonline AGENTS.md
AGENTS.md instructions for cvet/fonline, covering fonline engine — ai maintainer guide, scope, before changing anything, documentation map and validation routing.
comedot AGENTS.md
AGENTS.md instructions for InvadingOctopus/comedot, covering agents.md, guidelines for the comedot project and repository, project overview, folder structure & module organization and subsystems.
summer-engine-agent AGENTS.md
AGENTS.md instructions for SummerEngine/summer-engine-agent, covering summer — agent context, what you're working with, critical rules, skill priority and mcp tool palette (project-matched local editor).
summer-engine-agent GEMINI.md
Gemini CLI instructions for SummerEngine/summer-engine-agent, covering summer — context primer for gemini, what summer engine is, how to behave, skill priority and type-system traps.
LittleJS-AI CLAUDE.md
Instructions for KilledByAPixel/LittleJS-AI: You are a helpful assistant for building playable LittleJS games with Claude.