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/GaZmagik/claude-memory-pluginWrote 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/commands/gazmagik/claude-memory-plugin/check-health)<a href="https://agentmods.dev/commands/gazmagik/claude-memory-plugin/check-health"><img src="https://agentmods.dev/badge/commands/gazmagik/claude-memory-plugin/check-health/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/commands/gazmagik/claude-memory-plugin/check-health"><img src="https://agentmods.dev/badge/commands/gazmagik/claude-memory-plugin/check-health.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00019 | $0.02515 |
| Opus 5 | $0.00010 | $0.01257 |
| Sonnet 5 | $0.00004 | $0.00503 |
| Haiku 4.5 | $0.00002 | $0.00251 |
Grade A, and why
check-health 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 9d 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.
How it starts
The opening of the file, as written. The whole thing — 294 lines — stays where its author put it; the contents beside it link to each section on GitHub.
User Input
$ARGUMENTS
Goal
Perform a health check of the memory system using the built-in memory validate command. Supports all 4 scope levels: User, Project, Local, and Enterprise.
Prerequisites
CRITICAL: Before running any memory commands, you MUST activate the memory skill first using the Skill tool:
Skill: memory
This ensures the skill is loaded and the memory CLI command is available (installed via bun link). Without this step, the commands below may not work correctly.
Execution Steps
1. Determine Scope
Check arguments first:
--useror--globaloruserorglobal→ Useuserscope--projectorproject→ Useprojectscope--localorlocal→ Uselocalscope--enterpriseorenterprise→ Useenterprisescope (for managed environments)--allorall→ Check all accessible scopes sequentiallyquickor--quick→ Quick check mode (can combine with any scope)
Note: --global is accepted as a legacy alias for --user.
If no scope provided, first check which scopes are accessible:
# Check enterprise scope availability (for managed environments)
memory config get scopes.enterprise.enabled 2>/dev/null | jq -r '.data // false'
# Check if in a git repo (for project/local scopes)
git rev-parse --git-dir >/dev/null 2>&1 && echo "in_git_repo"
Then use AskUserQuestion with available options:
{
"question": "Which memory scope would you like to check?",
"header": "Memory scope",
"options": [
{"label": "User", "description": "Personal cross-project memories in ~/.claude/memory/"},
{"label": "Project", "description": "Shared project memories in .claude/memory/ (tracked in git)"},
{"label": "Local", "description": "Personal project memories in .claude/memory/local/ (gitignored)"},
{"label": "All accessible", "description": "Check all accessible scopes sequentially"}
],
"multiSelect": false
}
Dynamic options:
- Only show "Project" and "Local" if in a git repository
- Always show "User" and "All accessible"
- Enterprise scope is supported but not shown by default (pass
--enterpriseexplicitly)
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.
- 9d ago First seen · 294 lines · 19 tokens per session scan A 37333c9615c4
check-health is a command published in the GitHub repository GaZmagik/claude-memory-plugin (6 stars, last pushed 6mo ago), licensed MIT. It adds 19 tokens to every session and 2,515 once invoked, about $0.0001 per session on Opus 5. 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 commands, from other repositories
minutes-ideas
Surface recent voice memos and ideas captured from any device. Use when the user asks "what ideas did I have?", "what were my recent memos?", "what did I record while walking?", or wants to recall a captured thought.
learn
Force claude-smart to extract learnings from this session now.
memory-store
Store an insight, decision, or pattern to memory.
cc-memory
Configure persistent memory that survives across sessions using a layered approach: split rule files for always-loaded context, auto-memory for organic learning, and optional MCP-backed long-term memory for large codebases.
analyze-context
USE WHEN you want to analyze project context before starting work on a task. Calls context + recall, then synthesizes goals, decisions, gotchas, and relevant memories into a pre-task brief.
lians-recall
Recall current (non-stale) facts from Lians memory, optionally as-of a past date.