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.
git clone --depth 1 https://github.com/xobotyi/cc-foundryWrote 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.
[](https://agentmods.dev/plugins/xobotyi/cc-foundry/better-memory)<a href="https://agentmods.dev/plugins/xobotyi/cc-foundry/better-memory"><img src="https://agentmods.dev/badge/plugins/xobotyi/cc-foundry/better-memory/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.
<a href="https://agentmods.dev/plugins/xobotyi/cc-foundry/better-memory"><img src="https://agentmods.dev/badge/plugins/xobotyi/cc-foundry/better-memory.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
better-memory 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.
What it actually says
{
"name": "better-memory",
"version": "0.0.3",
"description": "Keeps Claude Code's auto memory to facts that still hold: gates memory writes and sifts new entries when the session goes idle",
"author": {
"name": "xobotyi",
"email": "[email protected]",
"url": "https://github.com/xobotyi"
},
"homepage": "https://github.com/xobotyi/cc-foundry/tree/master/plugins/better-memory",
"repository": "https://github.com/xobotyi/cc-foundry",
"license": "MIT",
"keywords": ["memory", "auto-memory", "mod", "sift"],
"userConfig": {
"enabled": {
"title": "Guard auto memory",
"description": "Run the better-memory mod: memory is written only through its tools, entries need anchors, and it maintains MEMORY.md. Off, Claude Code's own memory runs unchanged and only the sift skill remains.",
"type": "boolean",
"default": true
},
"sift": {
"title": "Sift when idle",
"description": "Judge new and unchecked entries in a separate Claude process when an interactive session goes idle. Off, entries stay as written until you run the sift skill.",
"type": "boolean",
"default": true
}
}
}
What it installs
The manifest is a name and a version. 1 skill travel with it, and installing the plugin installs all of them — 52 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.
- yesterday Changed c0e68bb88203
- 2d ago First seen · 29 lines scan A fa42576a02b9
better-memory is a plugin published in the GitHub repository xobotyi/cc-foundry (23 stars, last pushed yesterday), 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 2026-11-07.
better-memory compared with plugins from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| better-memoryxobotyi/cc-foundry | Plugin | 23 | yesterday | MIT | A | — | Claude Code |
| esp32-cppjohnkozaris/jko-claude-plugins | Plugin | 11 | 4d ago | MIT | A | — | Claude Code |
| evolving-liteprimeline-ai/evolving-lite | Plugin | 50 | 1mo ago | MIT | A | — | Claude Code |
| code-cleanupjohnkozaris/jko-claude-plugins | Plugin | 11 | 4d ago | MIT | A | — | Claude Code |
| backend-architecturejohnkozaris/jko-claude-plugins | Plugin | 11 | 4d ago | MIT | A | — | Claude Code |
| backend-validatorjohnkozaris/jko-claude-plugins | Plugin | 11 | 4d ago | MIT | A | — | Claude Code |
| maestro-mobile-validatorjohnkozaris/jko-claude-plugins | Plugin | 11 | 4d ago | MIT | A | — | Claude Code |