engram-mcp: Instructions file for Claude Code

CLAUDE.md

engram-mcp CLAUDE.md is an instructions file for Claude Code from edg-l/engram-mcp. It costs 7,648 tokens per session, scanned A, original, Apache-2.0.

Development instructions for Engram MCP, a local memory server that stores agent memories in SQLite and finds related memories using embeddings.

In plain words
What is it for?
Use them when modifying Engram’s memory database, search vectors, relationships, decay logic, MCP server, command-line tool, or release builds.
Why use it?
They distinguish the server from its human-facing command-line tool and list the build, test, lint, and runtime rules needed for safe changes.

Instructions file for Claude Code

Written for Claude Code: UserPromptSubmit hook event. Also seen: mentions Claude Code.

This is edg-l/engram-mcp's own configuration. It tells Claude Code how to work on engram-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything engram-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to edg-l/engram-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.

Copy the file
curl -O https://raw.githubusercontent.com/edg-l/engram-mcp/master/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/edg-l/engram-mcp

Made for: Claude Code.

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 engram-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/edg-l/engram-mcp/claude-md.svg)](https://agentmods.dev/instructions/edg-l/engram-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/edg-l/engram-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/edg-l/engram-mcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 7,648 This file is loaded in full into every session.
When invoked 7,648 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.07648 $0.07648
Opus 5 $0.03824 $0.03824
Sonnet 5 $0.01530 $0.01530
Haiku 4.5 $0.00765 $0.00765

Measured 8d ago against content hash 702fad51606f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

engram-mcp CLAUDE.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.

CLAUDE.md · 318 lines

How it starts

The opening of the file, as written. The whole thing — 318 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Engram MCP

MCP server for AI agent persistent memory. Crate name: engram_mcp (binaries: engram, engram-cli). SQLite + local embeddings (mdbr-leaf-ir q8, 256-dim MRL).

engram is the MCP server only: JSON-RPC over stdio, no subcommands. It serves when stdin is a pipe (or with --stdio/--serve); any argument or a terminal on stdin prints a usage notice pointing at engram-cli instead (exit 0 for --help, 2 for an unsupported argument). All human/agent CLI use goes through engram-cli.

Development Rules

  • Always run cargo clippy before committing and fix all warnings
  • Run cargo test to verify changes
  • Use cargo build --release for production binaries

Structure

src/
  main.rs      - MCP server entry, stdio transport, resources, prompts
  cli.rs       - CLI binary (engram-cli)
  lib.rs       - module exports
  db.rs        - SQLite ops (memories, embeddings, relationships, batch ops)
  memory.rs    - Memory, MemoryType, MergeSource, MemoryCluster, Relationship, RelationType, ProjectStats, ProjectSummary
  embedding.rs - mdbr-leaf-ir ONNX wrapper (256-dim MRL vectors)
  decay.rs     - relevance decay algorithm (single source of truth; registered as the RELEVANCE() SQL function)
  tools.rs     - MCP tool handlers + dedup + clustering
  format.rs    - human-readable output formatting for MCP results
  summarize.rs - extractive summarization for large content
  export.rs    - import/export JSON format
  error.rs     - MemoryError enum
  hooks/       - Claude Code lifecycle hook handlers: dispatch, filter, redact, install, payload structs
  db/status.rs   - retrieval status: supersession map (from edges) + dead flags
  db/todos.rs    - todo lifecycle sidecar (status/reason/closed_at)
  tools/todo.rs  - todo op batch, duplicate reporting, open-todo lookup for resume
  db/trash.rs    - recoverable snapshots for every destructive operation
  tools/curation.rs - applying supersession/dead status to a ranked result set

Key Types

  • MemoryType: fact, decision, preference, pattern, debug, entity, handoff, adr, todo
  • RelationType: relates_to, supersedes, derived_from
  • Memory: id, project_id, content, tags, importance, relevance_score, timestamps, branch, merged_from
  • MergeSource: id, content_preview, content (full text of the consumed memory), merged_at
  • MemoryCluster: id, project_id, summary, member_count, centroid, timestamps
  • TodoItem: id, project_id, text, status, reason, branch, tags, importance, timestamps, closed_at
  • TodoStatus: open, done, dropped
  • MemoryError: Database, Json, Embedding, NotFound, InvalidType, InvalidRelation, UnknownTool, UnknownProject, InvalidArguments, Io

Read the full file on GitHub · 318 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. 8d ago First seen · 318 lines · 7,648 tokens per session scan A 702fad51606f

Subscribe to this mod's changes

engram-mcp CLAUDE.md is an instructions file published in the GitHub repository edg-l/engram-mcp (15 stars, last pushed 7d ago), licensed Apache-2.0. It adds 7,648 tokens to every session, about $0.0382 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.

Related

Other instructions, from other repositories

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

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).

microsoft/vscode · 5,001 tokens

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.

langchain-ai/langchain · 4,469 tokens

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.

github/spec-kit · 7,104 tokens