agentmods.dev

longhand

longhand is a plugin for Claude Code from Wynelson94/longhand. Its token cost is not measured, scanned A, original, MIT.

A local memory plugin for Claude Code that stores tool calls, file edits, and reasoning blocks from sessions. It lets you search that saved history without sending recall requests to an external API.

In plain words
What is it for?
Use it to recall previous sessions, inspect tool and file-edit history, and search the agent's local working record.
Why use it?
It reduces the need to repeat information from earlier sessions and provides a searchable record of what the coding agent did. Keeping the records locally can also help when reviewing past work.

Plugin for Claude Code

not rated 13 22d ago A scan tokens not measured original MIT
View the source file Wynelson94/longhand
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 Wynelson94/longhand
agentmods
npx agentmods add plugins/wynelson94/longhand/longhand
Clone the repo
git clone --depth 1 https://github.com/Wynelson94/longhand

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 longhand

README.md
[![agentmods](https://agentmods.dev/badge/plugins/wynelson94/longhand/longhand.svg)](https://agentmods.dev/plugins/wynelson94/longhand/longhand)
Your own site
<a href="https://agentmods.dev/plugins/wynelson94/longhand/longhand"><img src="https://agentmods.dev/badge/plugins/wynelson94/longhand/longhand.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 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

longhand 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": "longhand",
  "version": "1.0.1",
  "description": "Persistent local memory for Claude Code. Every tool call, every file edit, every thinking block from every session \u2014 stored verbatim on your machine. Semantic recall in ~126ms with zero API calls.",
  "author": {
    "name": "Nate Nelson",
    "url": "https://github.com/Wynelson94"
  },
  "homepage": "https://github.com/Wynelson94/longhand",
  "repository": "https://github.com/Wynelson94/longhand",
  "license": "MIT",
  "keywords": [
    "memory",
    "recall",
    "mcp",
    "local",
    "session-history",
    "forensic",
    "search"
  ]
}
Contents

What it installs

The manifest is a name and a version. 1 hook, 1 MCP server travel with it, and installing the plugin installs all of 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 a94a8e3fe6cf

Subscribe to this mod's changes

longhand is a plugin published in the GitHub repository Wynelson94/longhand (13 stars, last pushed 22d 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.

Memory and contextai-memoryanthropicchromadbclaude-codeforensiclocal-first
Related

Other plugins, from other repositories

iai-memory

Persistent local memory for your assistant: every turn captured verbatim, relevant memory injected at session start and before each turn, and fifteen memory tools over MCP. Requires the iai-pme package (pip install iai-pme).

CodeAbra/iai-personal-memory-engine · not measured

plur

Persistent, local-first shared memory for AI agents. Corrections, preferences, and conventions persist across sessions, tools, and machines — stored as plain YAML on your disk, with zero-cost local search.

plur-ai/plur · not measured

remnic

Universal memory for AI agents — automatic recall, observation, and cross-agent knowledge sharing.

joshuaswarren/remnic · not measured

total-agent-memory

Persistent local memory for Claude Code — temporal knowledge graph, procedural memory, AST codebase ingest, cross-project analogy. Installs the MCP server, the memory-protocol skill and the capture hooks in one step.

vbcherepanov/total-agent-memory · not measured

cairntir

Memory-first reasoning layer for Claude Code. Kills cross-chat AI amnesia.

pnmcguire480/cairntir · not measured

claude-dejavu

Claude remembers its mistakes. Detects antipatterns from session logs and auto-patches CLAUDE.md.

cmg8431/claude-dejavu · not measured