What is MCP-memento copilot-instructions.md?

A project guide for MCP-memento, a tool that lets coding agents search and use information from a code repository. It explains the server, file indexing, related-file lookup, and context assembly.

Use it when answering code questions or making changes in MCP-memento, especially when locating related files or refreshing its index.

It tells the coding agent which repository tools to use and discourages guessing when code context is missing or outdated.

How caiowilson/MCP-memento configures GitHub Copilot

Reuse

Borrowing it

Nothing to install: this file belongs to caiowilson/MCP-memento. 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/caiowilson/MCP-memento/main/.github/copilot-instructions.md

Clone the repo

git clone --depth 1 https://github.com/caiowilson/MCP-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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/caiowilson/mcp-memento/copilot-instructions/github.svg)](https://agentmods.dev/instructions/caiowilson/mcp-memento/copilot-instructions)

Your own site

<a href="https://agentmods.dev/instructions/caiowilson/mcp-memento/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/caiowilson/mcp-memento/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/caiowilson/mcp-memento/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/caiowilson/mcp-memento/copilot-instructions.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 637 This file is loaded in full into every session.

When invoked 637 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	$0.00637	$0.00637
Opus 5	$0.00318	$0.00318
Sonnet 5	$0.00127	$0.00127
Haiku 4.5	$0.00064	$0.00064

Measured 9d ago against content hash 285cb769c994, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

MCP-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 9d 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 · 37 lines

How it starts

The opening of the file, as written. The whole thing — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MCP Tooling Policy (VS Code)

Use MCP tools to ground answers in the repo:

For any code question, call repo_context for the active file first.
If more context is needed, call repo_related_files, then repo_read_file or repo_search.
If unsure, say so and call a tool rather than guessing.
If results look stale or empty, call repo_index_status or repo_index_debug, then repo_reindex.

Tool names use underscore style (e.g., repo_context, repo_read_file, memory_search).

Project architecture (big picture)

Entrypoint is cmd/server/server.go: app.Run() wires up the MCP server.
The MCP server lives in internal/mcp/server.go: JSON-RPC over stdio, tool registry, and dot-to-underscore name mapping for clients.
Indexing is a background worker in internal/indexing/indexer.go with on-disk chunk storage under ~/.memento-mcp/.
File chunks are line-based and bounded by bytes/lines in internal/indexing/chunk.go.
Related-files resolution is in internal/mcp/related_tools.go: Go uses go/packages semantic refs; JS/TS and PHP use import/include graphs.
Context windows are assembled in internal/mcp/context_tool.go (chunk scoring + limits).

Critical workflows

Build server: make build (this applies the pinned tree-sitter grammar subset; see README.md).
Run server: ./bin/memento-mcp (stdio JSON-RPC).
Tests: make test; for vet, pass the TREE_SITTER_TAGS value from the Makefile through -tags (see README.md).
VS Code extension (WIP): in vscode-extension/README.md use npm install + npm run build.

Project-specific conventions

The server’s workspace root is its process working directory; VS Code must set MCP cwd to ${workspaceFolder} (see README.md).
Indexing differs for git vs non-git repos: git uses git status polling + debounce; non-git uses fs watcher (see internal/mcp/server.go).
Tool names are underscore-only; dot names are mapped to underscores at runtime (see internal/mcp/server.go).

Read the full file on GitHub · 37 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.

9d ago First seen · 37 lines · 637 tokens per session scan A 285cb769c994

Subscribe to this mod's changes

MCP-memento copilot-instructions.md is an instructions file published in the GitHub repository caiowilson/MCP-memento (11 stars, last pushed today), licensed MIT. It adds 637 tokens to every session, about $0.0032 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.

Memory and context local-first mcp mcp-server semantic-search

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-memento: Instructions file for GitHub Copilot