memory-kit

A persistent-memory plugin for Claude Code agents. It keeps a limited set of active context between sessions, records handoffs, and promotes settled information into a longer-term knowledge base or rules.

In plain words
What is it for?
Use it to preserve session decisions, create handoffs, maintain project knowledge, and run reviews or audits of an agent's stored context.
Why use it?
It reduces the need to reconstruct project context after every session while keeping temporary notes separate from durable knowledge.

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 awrshift/claude-memory-kit
agentmods
npx agentmods add plugins/awrshift/claude-memory-kit/memory-kit
Clone the repo
git clone --depth 1 https://github.com/awrshift/claude-memory-kit

Made for: Claude Code.

Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

memory-kit 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 yesterday.

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.

plugins/memory-kit/.claude-plugin/plugin.json · 23 lines

What it actually says

{
  "name": "memory-kit",
  "displayName": "Claude Memory Kit",
  "version": "6.2.0",
  "description": "Persistent memory for Claude Code agents: a hot cache injected every session and held under three size caps, per-session handoffs, and agent-audited promotion into knowledge articles and rules. Carries the builder's layers too — executor/recon/idea-validator agents, session review, second opinion, agent QA and a system audit — all lazy-loaded skills you only pay for on use.",
  "author": {
    "name": "awrshift",
    "url": "https://github.com/awrshift"
  },
  "homepage": "https://github.com/awrshift/claude-memory-kit",
  "repository": "https://github.com/awrshift/claude-memory-kit",
  "license": "MIT",
  "keywords": [
    "memory",
    "context-management",
    "session-handoff",
    "knowledge-base",
    "orchestration",
    "agent-qa",
    "system-audit"
  ]
}
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. yesterday First seen · 23 lines scan A 39f8fa422544

Subscribe to this mod's changes

memory-kit is a plugin published in the GitHub repository awrshift/claude-memory-kit (31 stars, last pushed 5d 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 2026-08-30.

Related

Other plugins, from other repositories

config-guard

Who guards the guards: a PreToolUse hook that blocks the agent from tampering with its own guardrail configuration. Deny-by-default protection for settings.json, hook scripts and hooks.json manifests, .mcp.json, plugin manifests, and (at strict level) CLAUDE.md and rules/agents/commands, across Bash, Edit, MultiEdit…

karanb192/claude-code-hooks · not measured

dead-end-registry

Approach-level negative-knowledge memory for Claude Code. Mines your transcripts (Stop/PreCompact, both async and zero added latency) for approaches you TRIED and then REVERTED (with the reason, date, and estimated token cost of the detour) into a per-repo registry. On UserPromptSubmit it injects a 'you already tried…

karanb192/claude-code-hooks · not measured

guard-pack

All six guard hooks in one Node process: config-guard, block-dangerous-commands, protect-secrets, protect-tests, git-safety, and case-insensitive-guard, evaluated in that order with the first blocking verdict winning in that guard's own output format. Installing the guards individually costs six Node startups per…

karanb192/claude-code-hooks · not measured

instructions-audit

A prompt-injection tripwire for instruction files. An InstructionsLoaded hook audits CLAUDE.md / .claude/rules/.md content as it enters context and flags hidden or hostile directives: invisible Unicode smuggling (zero width characters, tag characters, variation-selector runs; the TrapDoor supply-chain signature), bidi.

karanb192/claude-code-hooks · not measured

nerf-receipts

A personal flight recorder for Claude Code quality. Background hooks (async, zero added latency) record your own per-session signals keyed by model id and Claude Code version: tool-failure rate, same-file edit churn, turn-end counts, and tokens-per-completed-task. At your next SessionStart (or on demand via…

karanb192/claude-code-hooks · not measured

protect-secrets

A secrets firewall for Claude Code. A PreToolUse hook screens every Read, Edit, Write, and Bash call against tiered patterns (critical/high/strict): sensitive files like .env, SSH keys, AWS/kube/gcloud/docker credentials, and keystores, plus shell commands that expose or exfiltrate them (cat .env, printenv, echo…

karanb192/claude-code-hooks · not measured