amber

amber is a plugin for Claude Code from yanfeid/claude-amber. Its manifest loads nothing; the 4 skills, 3 hooks it bundles cost 244 tokens per session together, scanned A, original, MIT.

A Claude Code add-on that saves the current session to readable Markdown files before the conversation is shortened, then restores that state afterward. Claude Code is a coding assistant that works in a terminal.

In plain words
What is it for?
Use it to preserve progress across long coding sessions and apply focus-oriented working guidance.
Why use it?
It helps prevent losing task details when a long conversation reaches its context limit and is compacted.

Plugin for Claude Code

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.

Claude Code
/plugin marketplace add yanfeid/claude-amber
agentmods
npx agentmods add plugins/yanfeid/claude-amber/claude-amber
Clone the repo
git clone --depth 1 https://github.com/yanfeid/claude-amber

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 amber

README.md
[![agentmods](https://agentmods.dev/badge/plugins/yanfeid/claude-amber/claude-amber.svg)](https://agentmods.dev/plugins/yanfeid/claude-amber/claude-amber)
Your own site
<a href="https://agentmods.dev/plugins/yanfeid/claude-amber/claude-amber"><img src="https://agentmods.dev/badge/plugins/yanfeid/claude-amber/claude-amber.svg" alt="Measured on agentmods" 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 4 skills, 3 hooks cost 244 tokens a session between them.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

amber 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.

.claude-plugin/plugin.json · 22 lines

What it actually says

{
  "name": "amber",
  "description": "Zero-dependency context survival kit for Claude Code. Auto-checkpoints your session state to plain Markdown before compaction, restores it after — plus focus skills that keep Claude lean and on-task. No database, no background process, no AI compression. Just files you can read.",
  "version": "0.1.0",
  "author": {
    "name": "yanfei",
    "email": "[email protected]"
  },
  "homepage": "https://github.com/yanfeid/claude-amber",
  "repository": "https://github.com/yanfeid/claude-amber",
  "license": "MIT",
  "keywords": [
    "claude-code",
    "context",
    "compaction",
    "memory",
    "hooks",
    "skills",
    "context-engineering"
  ]
}
Contents

What it installs

The manifest is a name and a version. 4 skills, 3 hooks travel with it, and installing the plugin installs all of them — 244 tokens a session between them. Each is measured on its own page, and each can be installed alone.

Files

What ships with it

1 file beside plugin.json in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 22 lines scan A 87b951516b9d

Subscribe to this mod's changes

amber is a plugin published in the GitHub repository yanfeid/claude-amber (2 stars, last pushed 2mo 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.

Related

Other plugins, from other repositories

axme-code

(Alpha) Persistent memory, architectural decisions, and safety guardrails for Claude Code. Your agent starts every session with full project context — stack, decisions, patterns, safety rules, and a handoff from the previous session.

AxmeAI/axme-code · not measured

handoff

Portable project memory + development workflow for coding agents: auto-loads STATUS+RULES each session, enforces folder-level CONTEXT.md on edit, nudges durable state updates at turn end, scaffolds the system into any repo via guided discovery, and ships a tiered 6-phase workflow skill set covering every phase (brief.

AbdurRafay2004/handoff · not measured

wire-memory

Persistent memory for AI agents. Connect to a Wire container to remember decisions, patterns, and context across sessions.

usewire/wire-memory · not measured

engram

Durable, local-first graph memory for AI coding assistants: decisions with reasons, gotchas, conflicts — inspectable and editable in a graph pane.

techtheist/engram · not measured

starlight-intelligence-system

The sovereign intelligence substrate — persistent memory, identity, and attested governance for your whole AI fleet across Claude Code, Cursor, Cline, Codex, Gemini CLI & Antigravity. Local-first. Forkable. Built on the Starlight Intelligence Protocol v1.1.1.

frankxai/Starlight-Intelligence-System · not measured

atomicmemory

Persistent semantic memory for Claude Code — user preferences, project context, prior decisions, and codebase facts that survive across sessions.

atomicstrata/atomicmemory · not measured