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/kinnectd/a2me-mcp-server/copilot-instructionsgit clone --depth 1 https://github.com/Kinnectd/a2me-mcp-serverWrote 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/kinnectd/a2me-mcp-server/copilot-instructions)<a href="https://agentmods.dev/instructions/kinnectd/a2me-mcp-server/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/kinnectd/a2me-mcp-server/copilot-instructions.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 | $0.00798 | $0.00798 |
| Opus 5 | $0.00399 | $0.00399 |
| Sonnet 5 | $0.00160 | $0.00160 |
| Haiku 4.5 | $0.00080 | $0.00080 |
Grade A, and why
a2me-mcp-server 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 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
a2me-mcp-server — Copilot / Agent Instructions
Overview
a2me-mcp-server is a Model Context Protocol (MCP) server that exposes read-only,
privacy-redacted family-context tools to LLM assistants (Claude, ChatGPT, and the in-product
KAI assistant). It lets an assistant answer questions like "when is mom's birthday?" or "help me
write a message to grandma" using A2Me family data — without exposing sensitive details.
Status: live (v1, read-only). Production is hosted at mcp.a2me.app with Scalekit OAuth and
live A2Me API calls. Mock mode (A2ME_USE_MOCK=true) remains the default for local dev.
Stack
- Node 20+, TypeScript (strict). MCP via
@modelcontextprotocol/sdk, stdio transport. - Zod for input validation, Vitest for tests, ESLint + Prettier.
Commands
npm install
npm run dev # tsx src/index.ts (run locally over stdio)
npm run build # tsc -> dist/
npm run start # node dist/index.js
npm run test # vitest run (test:watch for watch mode)
npm run check # tsc --noEmit (type check)
npm run lint # eslint src/ test/
npm run format # prettier --write .
Layout
src/ → index.ts (entry), server.ts, tools/ (the MCP tools), auth/, client/,
resolver/, mock/ (mock auth + API), config.ts, types/.
Conventions (CRITICAL — privacy)
- Tools are read-only; never mutate A2Me data from here.
- Redact sensitive fields: no raw email / phone / street address; birthdays as month–day only. Scope every result to the authenticated user's family — never leak other families' data. (This matches A2Me's child-safety / privacy-first positioning.)
- Validate all tool inputs with Zod.
- Keep
mock/behind the same interfaces as the real client so swapping in the live API later is a drop-in change.
Repo conventions
- Branching — environment-as-branch (matches the rest of a2me):
dev= dev environment,main= production. Feature branches → PR todev(the default branch); promotedev→mainfor prod releases. Never PR a feature branch straight tomain.- Dev:
dev.mcp.a2me.app· Scalekit Kinnectd Dev env (issuerhttps://kinnectd.scalekit.dev/resources/res_130696843431510786) ·dev.api.kinnectd.com. - Prod:
mcp.a2me.app· a Scalekit Kinnectd Prod env (separate server to register; same namea2me-mcp-serveris fine — envs are isolated) ·api.kinnectd.com. - Deploy: dev auto-deploys on push to
dev; prod is released viacreate-tag.yml(environment=prod) → Cloud Run, through the sharedkinnectd-workflowsdeploy-service.yml. Per-env values (MCP_PUBLIC_URL,MCP_AUTH_ISSUER,MCP_AUTH_AUDIENCE,A2ME_API_URL) are set there.
- Dev:
- Any future credentials must come from env/secret stores — never commit tokens.
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 · 60 lines · 798 tokens per session scan A be5084a5e006
a2me-mcp-server copilot-instructions.md is an instructions file published in the GitHub repository Kinnectd/a2me-mcp-server (0 stars, last pushed yesterday), licensed MIT. It adds 798 tokens to every session, about $0.0040 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
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).
spec-kit AGENTS.md
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.
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.
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 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).
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.