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.
/plugin marketplace add veronchenko/inkwell-memorynpx agentmods add plugins/veronchenko/inkwell-memory/inkwell-hooksgit clone --depth 1 https://github.com/veronchenko/inkwell-memoryGrade A, and why
inkwell-hooks 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.
What it actually says
{
"name": "inkwell-hooks",
"version": "2.0.0",
"description": "Nudges Claude Code / Codex to actually use the Inkwell MCP memory server — search before starting work, and remember non-trivial changes before finishing.",
"author": {
"name": "veronchenko"
},
"homepage": "https://github.com/veronchenko/inkwell-memory",
"repository": "https://github.com/veronchenko/inkwell-memory",
"license": "MIT",
"keywords": [
"memory",
"mcp",
"hooks",
"codex",
"claude"
],
"interface": {
"displayName": "Inkwell Hooks",
"shortDescription": "Nudges agents to actually use the Inkwell MCP memory server",
"longDescription": "Mechanically enforces the Inkwell memory workflow instead of relying on the model to self-police it: blocks `remember` until a `search`/`recall` has run this session, reminds to search at session start, and prompts a self-report before Stop once enough file-editing tool calls have accumulated since the last remember. Installable in both Claude Code and Codex from the same manifest.",
"developerName": "veronchenko",
"category": "Productivity",
"capabilities": [
"Read",
"Write"
],
"websiteURL": "https://github.com/veronchenko/inkwell-memory",
"privacyPolicyURL": "https://github.com/veronchenko/inkwell-memory/blob/main/README.md",
"termsOfServiceURL": "https://github.com/veronchenko/inkwell-memory/blob/main/LICENSE"
}
}
What it installs
The manifest is a name and a version. 1 agent, 5 hooks travel with it, and installing the plugin installs all of them — 99 tokens a session between them. Each is measured on its own page, and each can be installed alone.
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 · 33 lines scan A 2ab38497a26b
inkwell-hooks is a plugin published in the GitHub repository veronchenko/inkwell-memory (2 stars, last pushed 19d 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.
Other plugins, from other repositories
obsidian-mcp-server
Read, write, search, and surgically edit Obsidian vault notes, tags, and frontmatter via MCP. STDIO or Streamable HTTP.
journal
Personal journaling system built on Binder — morning briefings, day planning, reflections, summaries, and period-level goal tracking.
unforgit-claude-code-marketplace
Claude Code plugins for Unforgit persistent repository memory.
unforgit
Persistent repository memory for AI coding agents using MCP tools, repository rules, and durable project knowledge.
exomem
Governed long-term memory over a markdown vault: raw sources stay immutable, conclusions are compiled with provenance, and nothing is deleted - it is superseded. Requires EXOMEMVAULTPATH to point at your vault; run exomem setup if you do not have one yet.
exomem-hosted-records
Governed long-term memory for relevant project work.