dfhack-mcp AGENTS.md

A set of instructions for AI coding agents working on the dfhack-mcp code repository. It explains how to keep code and comments useful, avoid duplicated information, and review changes consistently.

In plain words
What is it for?
Reviewing changes in dfhack-mcp, deciding whether new helper code is needed, and maintaining comment and documentation quality.
Why use it?
It gives the agent project-specific guidance that general coding instructions do not cover. This helps keep reviews focused and reduces unnecessary code or comments.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/alexanderolvera/dfhack-mcp/agents-md
Clone the repo
git clone --depth 1 https://github.com/alexanderolvera/dfhack-mcp

Made for: Codex, OpenCode.

Per session 1,215 This file is loaded in full into every session.
When invoked 1,215 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.01215 $0.01215
Opus 5 $0.00607 $0.00607
Sonnet 5 $0.00243 $0.00243
Haiku 4.5 $0.00121 $0.00121

Measured yesterday against content hash 92cb86e7c0a6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

dfhack-mcp 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 yesterday.

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.

AGENTS.md · 102 lines

How it starts

The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Guidance for AI coding agents working in this repo, beyond what's in CONTRIBUTING.md. CONTRIBUTING.md covers the tiered verify harness and the tool-adding checklist; this file covers code/comment hygiene — things to actively look for on every pass through this codebase, not just when asked.

Does this snippet earn its keep?

Before adding — or when passing over — a derived/curated field, function, or script, ask whether it's actually adding information, or just re-packaging something already available elsewhere in the same payload/module with a bit of prose wrapped around it. A second, hand-maintained summary of a fact is a second place for that fact to drift out of sync with the source (see the "Facts, not advice" doctrine in CONTRIBUTING.md — the same reasoning applies to internal duplication, not just advice-vs-fact).

Precedent: identify's tactics[] field (src/tools/identify/tactics.ts, removed) derived a curated {trait, note} list — trapavoid, flier, fire, building_destroyer, webber, ranged — from the creature dossier's own flags[]/interactions[], which the same response already returns. It duplicated data the caller could already see, cost a second source of truth (its ranged derivation had its own bug — issue #66 — before the field was cut entirely), and its removal deleted real code with no loss of information. That's the shape to look for: a field/helper that mostly restates data sitting one hop away in the same response.

Also watch for orphaned scripts: scripts/verify-identify.mjs (removed) had a stale import path from before identify became a directory, and wasn't referenced by any npm script or doc — it had already silently stopped working. If a script/module isn't reachable from package.json, a doc, or another module, don't assume it's still doing anything.

Comment hygiene

The target is zero comment blocks. Code should be legible enough — through naming, structure, and small functions — that it doesn't need prose alongside it to be understood. A comment is a sign the code didn't quite say what it means; prefer fixing that over documenting around it.

Read the full file on GitHub · 102 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. yesterday First seen · 102 lines · 1,215 tokens per session scan A 92cb86e7c0a6

Subscribe to this mod's changes

dfhack-mcp AGENTS.md is an instructions file published in the GitHub repository alexanderolvera/dfhack-mcp (0 stars, last pushed 23d ago), licensed ISC. It adds 1,215 tokens to every session, about $0.0061 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.

Related

Other instructions, from other repositories

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

buildNext

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 · 6,785 tokens

next.js 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 · 7,296 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, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

spec-kit AGENTS.md

Instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,040 tokens

langchain 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 · 4,345 tokens