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/klimpaskov/hoi4-agent-tools/agents-mdgit clone --depth 1 https://github.com/klimPaskov/hoi4-agent-toolsWrote 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/klimpaskov/hoi4-agent-tools/agents-md)<a href="https://agentmods.dev/instructions/klimpaskov/hoi4-agent-tools/agents-md"><img src="https://agentmods.dev/badge/instructions/klimpaskov/hoi4-agent-tools/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 5.1 | $0.00658 | $0.00658 |
| Opus 5 | $0.00329 | $0.00329 |
| Sonnet 5 | $0.00132 | $0.00132 |
| Haiku 4.5 | $0.00066 | $0.00066 |
Grade A, and why
hoi4-agent-tools 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 — 35 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Instructions
HOI4 Agent Tools is a public Model Context Protocol server for coding agents that analyze event chains and technology trees and create or clean focus trees, scripted GUIs, and maps in external Hearts of Iron IV mods. The MCP server is the product surface; do not add a dashboard, interactive editor, or gameplay-tool CLI.
Engineering boundaries
- Keep workspace resolution, Clausewitz parsing, indexing, diagnostics, atomic writes, artifacts, diffs, and failure recovery in
src/hoi4_agent_tools/core. - Focus, GUI, map, event, technology, and MCP adapters must call the same typed core services. Transport handlers contain no domain logic.
- Preserve source bytes when no edit is requested. Preserve comments, ordering, unknown fields, raw blocks, newline style, and detected encoding during targeted edits.
- Refuse a rewrite when a construct cannot be represented safely.
- Every real mod directory directly beneath a configured mod root is discovered as a writable workspace. Explicit workspaces may add nonstandard locations, but they must not weaken canonical-path checks. Each domain rewrite is one MCP call; validation, stale-source checks, atomic replacement, and failure recovery stay internal. Never expose transaction IDs, plan hashes, separate apply calls, or rollback commands to coding agents.
- Remote rewrites retain authentication, Origin and Host validation, principal-to-workspace grants, request limits, and session isolation. Remote access never broadens a configured root or principal grant.
- Reject traversal, symlink escape, cross-workspace access, stale source or provenance, arbitrary commands, and access outside configured roots.
- Never launch, automate, control, or capture output from the game. Offline renders are tool-generated evidence, never game screenshots.
- Keep the Event Chain Viewer read-only. It statically analyzes definitions, calls, state, scope, timing, and routes; it is not an event writer or runtime simulator.
- Keep the Technology Tree Viewer read-only. It statically analyzes technologies, doctrines, placements, unlocks, grants, bonuses, and references; it is not a technology writer, balance scorer, or runtime simulator.
- Do not commit installed-game content or third-party mod content. CI fixtures must be synthetic and project-owned.
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 · 35 lines · 658 tokens per session scan A f2257aca3934
hoi4-agent-tools AGENTS.md is an instructions file published in the GitHub repository klimPaskov/hoi4-agent-tools (5 stars, last pushed yesterday), licensed Apache-2.0. It adds 658 tokens to every session, about $0.0033 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 2026-08-31.
Other instructions, from other repositories
Cities2-MCP AGENTS.md
Instructions for mayor-modder/Cities2-MCP, covering agent rules, workspace safety, commit and pr safety, public-facing writing and merge and release gates.
Unity-AI-Animation CLAUDE.md
Instructions for IvanMurzak/Unity-AI-Animation, covering claude.md, what this is, build / run, critical invariants and find detail in.
better-godot-mcp AGENTS.md
AGENTS.md instructions for n24q02m/better-godot-mcp, covering agents.md - better-godot-mcp, build / lint / test commands, run a single test file, run a single test by name and mise shortcuts.
minecraft-dev-mcp CLAUDE.md
Instructions for MCDxAI/minecraft-dev-mcp, covering claude code context - minecraft dev mcp, project overview, release status, architecture and core services (src/services/).
Unity-AI-Tools-Template CLAUDE.md
Instructions for IvanMurzak/Unity-AI-Tools-Template, covering unity-ai-tools-template, build / run, 1. initialize a new package from the template, 2. open both unity projects so .meta files are generated and 3. bump version across all files in lock-step.
Unity-AI-ParticleSystem CLAUDE.md
Instructions for IvanMurzak/Unity-AI-ParticleSystem, covering claude.md, what this is, build / run, critical invariants and find detail in.