What is mcp-ai-agent-guidelines copilot-instructions.md?

Repository-specific instructions for a TypeScript server that exposes tools through MCP, a standard way for AI applications to call external tools. They describe its architecture, build and test commands, and generated tool definitions.

Use them when developing, testing, checking types, or updating tools, workflows, registries, or runtime code in this MCP server.

They show how to change the server safely and remind you to regenerate derived files when the main tool registries or workflow definitions change.

How Anselmoo/mcp-ai-agent-guidelines configures GitHub Copilot

Reuse

Borrowing it

Nothing to install: this file belongs to Anselmoo/mcp-ai-agent-guidelines. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/Anselmoo/mcp-ai-agent-guidelines/main/.github/copilot-instructions.md

Clone the repo

git clone --depth 1 https://github.com/Anselmoo/mcp-ai-agent-guidelines

Made for: GitHub Copilot.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/anselmoo/mcp-ai-agent-guidelines/copilot-instructions.svg)](https://agentmods.dev/instructions/anselmoo/mcp-ai-agent-guidelines/copilot-instructions)

Your own site

<a href="https://agentmods.dev/instructions/anselmoo/mcp-ai-agent-guidelines/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/anselmoo/mcp-ai-agent-guidelines/copilot-instructions.svg" alt="Measured on agentmods" height="20"></a>

Per session 913 This file is loaded in full into every session.

When invoked 913 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00913	$0.00913
Opus 5	$0.00456	$0.00456
Sonnet 5	$0.00183	$0.00183
Haiku 4.5	$0.00091	$0.00091

Measured 8d ago against content hash 6bb4ad618ea5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

mcp-ai-agent-guidelines 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 8d 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.

.github/copilot-instructions.md · 53 lines

How it starts

The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.

mcp-ai-agent-guidelines

TypeScript ESM MCP server exposing public instruction tools backed by generated registries, workflow specs, and handwritten skill/runtime implementations.

Build, test, and lint

npm ci
npm run build
npm run test
npm run test -- src/tests/runtime/mcp-server.test.ts
npx vitest run src/tests/runtime/mcp-server.test.ts -t "lists public, workspace, memory, session, snapshot, and orchestration tools"
npm run test:coverage
npm run check
npm run check:fix
npm run type-check
npm run quality
python3 -m unittest scripts.test_mcp_smoke

When changing the canonical registries or workflow graph, regenerate derived files before validating:

python3 scripts/generate-tool-definitions.py
npm run check:generated

Useful runtime entrypoints:

node dist/index.js
mcp-cli info

High-level architecture

src/index.ts is the MCP server entrypoint. It wires the SDK request handlers for tools, resources, and prompts, composes the runtime (InstructionRegistry, SkillRegistry, ModelRouter, WorkflowEngine, session store), and dispatches utility tools such as memory, session, snapshot, orchestration, visualization, and workspace operations.
The public MCP surface is registry-driven, not handwritten in one place. src/instructions/instruction-specs.ts is the canonical public instruction registry, src/skills/skill-specs.ts is the canonical skill catalog plus legacy alias bridge, and src/workflows/workflow-spec.ts is the authoritative instruction-to-skill/state-machine coverage graph. Generated manifests and public tool definitions under src/generated/ are emitted from those sources.
Skill execution is tiered. src/tools/skill-handler.ts derives the execution tier from the skill prefix, applies the context membrane, and enforces extra gates such as physics justification before invoking a registered handler.
Tool visibility is policy-driven. src/tools/shared/tool-surface-manifest.ts filters ListTools using HIDDEN_TOOLS and automatically hides routing-adapt when DISABLE_ADAPTIVE_ROUTING=true (default: visible), while CallTool still supports the hidden aliases internally.
There are two user-facing entrypoints in the published package: mcp-ai-agent-guidelines for the MCP stdio server and mcp-cli for interactive onboarding/orchestration/status flows.

Read the full file on GitHub · 53 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.

8d ago First seen · 53 lines · 913 tokens per session scan A 6bb4ad618ea5

Subscribe to this mod's changes

mcp-ai-agent-guidelines copilot-instructions.md is an instructions file published in the GitHub repository Anselmoo/mcp-ai-agent-guidelines (6 stars, last pushed 2d ago), licensed MIT. It adds 913 tokens to every session, about $0.0046 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.

ai-agent hierachical mcp mcp-server mermaid prompting

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.

vercel/next.js · 7,296 tokens

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 · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

mcp-ai-agent-guidelines: Instructions file for GitHub Copilot