memento copilot-instructions.md

memento copilot-instructions.md is an instructions file for GitHub Copilot from veerps57/memento. It costs 744 tokens per session, scanned A, original, Apache-2.0.

A short GitHub Copilot instruction file for Memento that directs agents to the repository's main guidance and architecture documents.

In plain words
What is it for?
It directs agents to the right guidance for tests, database migrations, architecture decisions, and verification requirements.
Why use it?
It points Copilot to the authoritative rules and area-specific instructions instead of duplicating them in several files.

Instructions file for GitHub Copilot

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/veerps57/memento/copilot-instructions
Clone the repo
git clone --depth 1 https://github.com/veerps57/memento

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.

agentmods badge for memento copilot-instructions.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/veerps57/memento/copilot-instructions.svg)](https://agentmods.dev/instructions/veerps57/memento/copilot-instructions)
Your own site
<a href="https://agentmods.dev/instructions/veerps57/memento/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/veerps57/memento/copilot-instructions.svg" alt="Measured on agentmods" height="20"></a>
Per session 744 This file is loaded in full into every session.
When invoked 744 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 $0.00744 $0.00744
Opus 5 $0.00372 $0.00372
Sonnet 5 $0.00149 $0.00149
Haiku 4.5 $0.00074 $0.00074

Measured 4d ago against content hash 4af6cdc27ce4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

memento 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.

.github/copilot-instructions.md · 43 lines

How it starts

The opening of the file, as written. The whole thing — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GitHub Copilot Instructions

This file is read automatically by GitHub Copilot in VS Code and other Copilot-enabled environments.

The canonical instruction set for all AI agents working on Memento lives in AGENTS.md at the repository root. This file exists only to point Copilot at it; everything below is a brief summary. Do not duplicate content here — read AGENTS.md directly.

Read this first

  1. AGENTS.md — guiding principles, architectural rules, common pitfalls, verification commands.
  2. ARCHITECTURE.md — high-level architecture and links into the deeper docs.
  3. docs/adr/ — every architectural decision and why it was made.

Path-specific guidance

When you edit files in these areas, the canonical reference is:

  • **/*.test.tsAGENTS.md § "Architectural rules" + § "Verification"; tests must use Vitest, mirror the source layout under packages/<pkg>/test/, and keep the 90/90/90/90 coverage gate green.
  • packages/core/src/storage/migrations/**ADR-0001 and existing migrations under that directory; migrations are forward-only and must include matching tests under packages/core/test/storage/migrations/.
  • packages/core/src/commands/**ADR-0003 and packages/core/README.md; every command lands in the single registry and is projected to MCP and CLI by adapters.
  • docs/** — generated reference docs under docs/reference/ are produced by pnpm docs:generate (do not hand-edit); architectural prose under docs/architecture/ and ADRs under docs/adr/ follow the templates already in those directories.

Reusable workflows

These live as concise checklists rather than executable prompt files:

  • Add a command: define schemas in @psraghuveer/memento-schema, register the command in packages/core/src/commands/, add tests, run pnpm docs:generate to refresh docs/reference/cli.md and docs/reference/mcp-tools.md. ADR-0003 is the contract.
  • Add a config key: add a defineKey entry to packages/schema/src/config-keys.ts, follow the JSDoc-style guidance at the top of that file, then pnpm docs:generate to refresh docs/reference/config-keys.md.
  • Add a migration: add the next-numbered migration under packages/core/src/storage/migrations/ with a matching test under packages/core/test/storage/migrations/. Migrations are forward-only.

Read the full file on GitHub · 43 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. 4d ago First seen · 43 lines · 744 tokens per session scan A 4af6cdc27ce4

Subscribe to this mod's changes

memento copilot-instructions.md is an instructions file published in the GitHub repository veerps57/memento (22 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 744 tokens to every session, about $0.0037 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 2026-08-30.