A local system for keeping an agent’s identity, memories, and learned procedures across conversations and models. It uses an open protocol and connects through MCP, a standard way for AI agents to use external tools.

It is for persistent agent identity, long-term memory, and reusing established workflows.

It reduces the need to re-establish context and working habits after each session or model change. It can also revisit stored beliefs when new information contradicts them.

troth — Plugin for Claude Code by xgre1

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.

Clone the repo

git clone --depth 1 https://github.com/xgre1/troth

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.

README.md

[![agentmods](https://agentmods.dev/badge/plugins/xgre1/troth/plugin/github.svg)](https://agentmods.dev/plugins/xgre1/troth/plugin)

Your own site

<a href="https://agentmods.dev/plugins/xgre1/troth/plugin"><img src="https://agentmods.dev/badge/plugins/xgre1/troth/plugin/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/plugins/xgre1/troth/plugin"><img src="https://agentmods.dev/badge/plugins/xgre1/troth/plugin.svg" alt="Reviewed on agentmods" width="80" 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 19 skills, 2 commands, 1 agent, 6 hooks, 4 MCP servers cost 706 tokens a session between them.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin unknown No closer match found in the catalogue.

Security

Grade A, and why

troth 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 1mo 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.

plugin/.claude-plugin/plugin.json · 21 lines

The source is not reproduced here

Licensed AGPL-3.0

The repository is licensed AGPL-3.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.

Read it on GitHub

Contents

What it installs

The manifest is a name and a version. 19 skills, 2 commands, 1 agent, 6 hooks, 4 MCP servers travel with it, and installing the plugin installs all of them — 706 tokens a session between them. Each is measured on its own page, and each can be installed alone.

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.

1mo ago Changed 532aa0e3fdbc
1mo ago Changed ac0b588e8df6
1mo ago Changed 47c4a12a0809
1mo ago First seen · 21 lines scan A ab2d2fef7525

Subscribe to this mod's changes

troth is a plugin published in the GitHub repository xgre1/troth (10 stars, last pushed 1mo ago), licensed AGPL-3.0. 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.

Memory and context agent agpl ai anthropic claude developer-tools

tau-git-memory

Git-backed local memory store for Tau sessions, with branch-aware recall and manual capture.

AbdoKnbGit/tau · not measured

mind

Claude Mind - Give Claude photographic memory in ONE portable file. Share, version, and transfer your Claude's brain.

2josEx/claude-brain · not measured

tokenless

Tokenless context compression for Claude Code. Cap noisy tool output locally before it enters model context.

MaxForAI/Tokenless · not measured

neurodock

Local-first cognitive substrate for neurodivergent professionals. Bundles the five NeuroDock MCP servers and a set of ND-aware skills for communication decoding, task decomposition, working-memory recall, and clinical guardrails.

tlennon-ie/neurodock · not measured

yantrikdb

Cognitive memory for AI agents — semantic recall, a knowledge graph, contradiction detection and procedural learning. Local-first: one SQLite file, no account, no telemetry.

yantrikos/yantrikdb-mcp · not measured

memory-kit

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…

awrshift/claude-memory-kit · not measured