A local project-memory add-on for AI coding agents. It records file changes and shell-command results, provides session briefings, and lets the agent search project decisions, warnings, and discoveries across sessions.

Keeping a local record of coding work, reviewing project history, finding past decisions, and optionally consulting multiple models about designs.

It reduces the need to repeat project context after a break or in a new session.

engram — Plugin for Claude Code by coinstax

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.

Clone the repo

git clone --depth 1 https://github.com/coinstax/engram

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.

README.md

[![agentmods](https://agentmods.dev/badge/plugins/coinstax/engram/plugin/github.svg)](https://agentmods.dev/plugins/coinstax/engram/plugin)

Your own site

<a href="https://agentmods.dev/plugins/coinstax/engram/plugin"><img src="https://agentmods.dev/badge/plugins/coinstax/engram/plugin/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/plugins/coinstax/engram/plugin"><img src="https://agentmods.dev/badge/plugins/coinstax/engram/plugin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session not measured What this adds to a session before it is invoked.

When invoked not measured The manifest loads nothing itself; its 1 skill, 2 hooks, 1 MCP server cost 61 tokens a session between them.

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.

Security

Grade A, and why

engram 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 2mo 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.

plugin/.claude-plugin/plugin.json · 20 lines

What it actually says

{
  "name": "engram",
  "version": "1.9.1",
  "description": "Local-first project memory for AI coding agents. Passive capture of file mutations and bash outcomes, structured briefings at session start, decisions/warnings/discoveries searchable across sessions, optional multi-model design consultations.",
  "author": {
    "name": "Colin Mackie"
  },
  "homepage": "https://github.com/coinstax/engram",
  "repository": "https://github.com/coinstax/engram",
  "license": "MIT",
  "keywords": [
    "memory",
    "context",
    "project-memory",
    "briefing",
    "session",
    "mcp"
  ]
}

Contents

What it installs

The manifest is a name and a version. 1 skill, 2 hooks, 1 MCP server travel with it, and installing the plugin installs all of them — 61 tokens a session between them. Each is measured on its own page, and each can be installed alone.

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.

2mo ago First seen · 20 lines scan A 33d0f5d50a73

Subscribe to this mod's changes

engram is a plugin published in the GitHub repository coinstax/engram (0 stars, last pushed 3mo ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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.

Memory and context

engram next to 6 plugins from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
engramcoinstax/engram	Plugin	0	3mo ago	MIT	A	—	Claude Code
open-knowledge-vaultglebis/claude-skills	Plugin	410	yesterday	MIT	A	—	Claude Code
knowledge-and-memoryoaustegard/claude-skills	Plugin	158	yesterday	MIT	A	—	Claude Code
paimnott/PAI	Plugin	67	today	MIT	A	—	Claude Code
claude-mega-brainguhcostan/claude-mega-brain	Plugin	127	3mo ago	MIT	A	—	Claude Code
tree-ring-memoryTerminallyLazy/Tree-Ring-Memory	Plugin	22	1mo ago	MIT	A	—	Claude Code
bestpracticeavanturer/claude-bestpractice	Plugin	2	yesterday	MIT	A	—	Claude Code