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/hby7921/bannerlordsage/agents-mdgit clone --depth 1 https://github.com/hby7921/BannerlordSageWrote 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/hby7921/bannerlordsage/agents-md)<a href="https://agentmods.dev/instructions/hby7921/bannerlordsage/agents-md"><img src="https://agentmods.dev/badge/instructions/hby7921/bannerlordsage/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 | $0.01309 | $0.01309 |
| Opus 5 | $0.00655 | $0.00655 |
| Sonnet 5 | $0.00262 | $0.00262 |
| Haiku 4.5 | $0.00131 | $0.00131 |
Grade A, and why
BannerlordSage 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 4d 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 — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.
BannerlordSage Agent Guide
This repository is a Windows-first MCP server for Mount & Blade II: Bannerlord.
Use this file when an AI coding agent is asked to inspect, install, configure, verify, or run this repo.
Primary Goal
Help the user get BannerlordSage installed and running against a local Bannerlord installation.
What This Repo Does
- imports Bannerlord XML from a local game install
- decompiles official Bannerlord DLLs
- builds SQLite indexes
- exposes MCP tools for Bannerlord querying, modding, and reverse engineering
- can also index and read the user's own local mod source workspace
Important Constraints
- This repo does not include Bannerlord assets
- The user must have a legitimate local Bannerlord installation
- Commands that use
--game-dirrequire the user's real local path - Never invent a game path; ask for it or discover it from local context
- Do not commit
dist/, extracted game assets, SQLite databases, or local secrets
First Files To Read
When you first open this repo, read these files before making assumptions:
README.mdpackage.jsonsrc/server.tssrc/entrypoints/bannerlord-stdio.tssrc/entrypoints/bannerlord-full-stdio.tssrc/entrypoints/bannerlord-setup.ts
Standard Human Install Flow
If the user wants a normal install, use this order:
- Install prerequisites:
- Bun
- ripgrep
- .NET SDK 8+
- ILSpyCmd
- Install repo dependencies:
bun install
- Run Bannerlord setup:
bun run setup:bannerlord -- --game-dir "<BANNERLORD_GAME_DIR>"- setup indexes local decompiled source/XML plus public official/community docs and official API search data by default; use
--skip-docsonly for offline setup
- Start the MCP server:
bun run start:bannerlord
If the user needs the authoring helpers too:
bun run start:bannerlord:full
MCP Client Config
Recommended MCP entry:
[mcp_servers.bannerlordsage]
command = "bun"
args = ["run", "src/entrypoints/bannerlord-stdio.ts"]
cwd = "<REPO_DIR>"
enabled = true
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.
- 4d ago First seen · 170 lines · 1,309 tokens per session scan A bb94830c4a0e
BannerlordSage AGENTS.md is an instructions file published in the GitHub repository hby7921/BannerlordSage (14 stars, last pushed 2mo ago), licensed MIT. It adds 1,309 tokens to every session, about $0.0065 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
blockrun-mcp AGENTS.md
AGENTS.md instructions for BlockRunAI/blockrun-mcp, covering blockrun mcp, commands, project structure, key dependencies and install in codex.
openrouter-mcp-multimodal AGENTS.md
AGENTS.md instructions for stabgan/openrouter-mcp-multimodal, covering agent instructions, before you ship, releasing (read this before publishing), short version and version files (must all match package.json).
intervals-icu-mcp CLAUDE.md
Instructions for hhopke/intervals-icu-mcp, covering claude.md, project overview, development commands, architecture (quick reference) and tool categories.
ai-toolkit AGENTS.md
AGENTS.md instructions for pipefy/ai-toolkit, covering repository guidelines, documentation map, project structure, import namespace migration: pipefysdk → pipefy and src/pipefysdk/init.py (transitional shim).
flyto-core CLAUDE.md
Claude Code instructions for flytohub/flyto-core, covering claude notes, cross-agent handoff and shared code intelligence.
Plonk AGENTS.md
AGENTS.md instructions for ostapondo/Plonk, covering agent rules, layout, adding a module, build & verify and code style.