Borrowing it
Nothing to install: this file belongs to alexanderolvera/dfhack-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/alexanderolvera/dfhack-mcp/main/.github/copilot-instructions.mdgit clone --depth 1 https://github.com/alexanderolvera/dfhack-mcpWrote 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/alexanderolvera/dfhack-mcp/copilot-instructions)<a href="https://agentmods.dev/instructions/alexanderolvera/dfhack-mcp/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/alexanderolvera/dfhack-mcp/copilot-instructions/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/alexanderolvera/dfhack-mcp/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/alexanderolvera/dfhack-mcp/copilot-instructions.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00726 | $0.00726 |
| Opus 5.5 | $0.00290 | $0.00290 |
| Sonnet 5.5 | $0.00145 | $0.00145 |
| Haiku 4.5 | $0.00073 | $0.00073 |
Grade A, and why
dfhack-mcp copilot-instructions.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 2mo 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Copilot code review instructions — dfhack-mcp
You are an advisory reviewer. Leave informational notes and inline comments that help the author; you are not a merge gate. Never approve, never request changes as a blocking verdict, never tell the author to merge or not merge, and never imply a check must pass before merge. Frame everything as observations and suggestions the author is free to take or leave.
What this project is
An MCP server that exposes a live Dwarf Fortress fort to an AI agent as a small
set of curated, read-only tools. TypeScript, Node 24, run directly via
type-stripping (no build step in dev). It talks to DFHack Remote RPC on
localhost:5000 through the published dfhack-remote-node client.
Lead with intent
Before commenting on details, state — in one or two sentences — what you understand the PR is trying to do, inferred from its title, description, linked issue, and diff. If the code and the stated intent diverge, that mismatch is the single most useful thing you can surface. Call it out plainly.
What to look for (in priority order)
- Intent vs. implementation — does the change actually accomplish what it claims? Missed cases, silent behavior changes, half-applied refactors.
- Correctness — logic errors, unhandled
null/undefined, off-by-one, incorrect async/await, unhandled promise rejections, type assertions that paper over real type holes. - Project doctrine (flag violations, these are load-bearing here):
- Read-only. v1 tools observe the game; they must never mutate it. Flag any RPC call or Lua that writes/changes fort state.
- Facts, not advice. Tools report what is sensed; they do not tell the player what to do. Flag output fields that editorialize or recommend.
- Localhost only. Never enable
allow_remote; the server only talks tolocalhost:5000. Flag anything that broadens the network surface. - Small, glanceable responses. Sensor tools return already-summarized JSON from one purpose-written Lua query. Flag unbounded lists or dumps.
- Explicit
.tsextensions on local imports; keepnpm run typecheckandnpm run lintclean.
- Code quality — naming, dead code, duplication, unclear control flow, comments that no longer match the code, error messages that won't help a user.
- Tests / verify — this repo verifies tools against a real running fort, not mocks (T0 contract in CI; T1/T2 need a live fort or fixture save). If a change adds a mock in place of the verify harness, or ships a tool with no corresponding verify coverage, note it.
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.
- 2mo ago First seen · 55 lines · 726 tokens per session scan A 67ff368babc7
dfhack-mcp copilot-instructions.md is an instructions file published in the GitHub repository alexanderolvera/dfhack-mcp (2 stars, last pushed 2mo ago), licensed ISC. It adds 726 tokens to every session, about $0.0029 per session on Opus 5.5. 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
vscode buildNext.instructions.md
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).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
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.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.