A packaged Claude Code plug-in that adds long-term memory through the memharness server, a session-start recall hook, and a post-commit reminder.

Use it to install the memharness memory workflow in one command and support proactive recall and capture during coding sessions.

It helps the agent carry useful user and project knowledge across sessions and record facts with their sources and timing.

memharness — Plugin by las7

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 las7/memharness

agentmods

npx agentmods add plugins/las7/memharness/marketplace

Clone the repo

git clone --depth 1 https://github.com/las7/memharness

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

memharness 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 2d 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/marketplace.json · 21 lines

What it actually says

{
  "$schema": "https://anthropic.com/claude-code/marketplace.schema.json",
  "name": "memharness",
  "description": "Bi-temporal, provenance-carrying long-term memory for AI agents, packaged so the proactive experience installs in one command.",
  "owner": {
    "name": "las7"
  },
  "plugins": [
    {
      "name": "memharness",
      "description": "Long-term memory for Claude Code: the memharness MCP server plus a session-start recall hook, a post-commit capture nudge, and a proactive-use policy skill. Turns the raw tools into the proactive memory experience without hand-editing your harness.",
      "author": {
        "name": "las7"
      },
      "category": "productivity",
      "source": "./plugins/memharness",
      "homepage": "https://github.com/las7/memharness"
    }
  ]
}

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.

2d ago First seen · 21 lines scan A 9773967f350d

Subscribe to this mod's changes

memharness is a plugin published in the GitHub repository las7/memharness (6 stars, last pushed 2mo ago), licensed Apache-2.0. 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.

Data and AI Git and workflow LLM Memory and context agent-memory agents artificial-intelligence bi-temporal

memharness

Getting it into your agent

Grade A, and why

Nothing flagged

What it actually says

What this file has done since we first saw it

Other plugins, from other repositories

potpie

mechanist

knowl

knowl

inspeximus

cortadel