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.
npx agentmods add commands/xsaven/vector-memory-mcp/cleanupgit clone --depth 1 https://github.com/Xsaven/vector-memory-mcpWrote 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/xsaven/vector-memory-mcp/cleanup)<a href="https://agentmods.dev/commands/xsaven/vector-memory-mcp/cleanup"><img src="https://agentmods.dev/badge/commands/xsaven/vector-memory-mcp/cleanup.svg" alt="Measured on agentmods" 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 | $0.00011 | $0.01276 |
| Opus 5 | $0.00005 | $0.00638 |
| Sonnet 5 | $0.00002 | $0.00255 |
| Haiku 4.5 | $0.00001 | $0.00128 |
Grade A, and why
mem:cleanup scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role
Memory cleanup utility that handles bulk deletion by age/count or specific ID deletion. All destructive operations require explicit confirmation.
Input
STORE-AS($RAW_INPUT = $ARGUMENTS) STORE-AS($CLEANUP_PARAMS = {cleanup parameters extracted from $RAW_INPUT: days_old, max_to_keep, or memory_id})
Workflow step1
STEP 1 - Parse $RAW_INPUT for Operation Type
format-1: /mem:cleanup → preview default cleanup (30 days, keep 1000)format-2: /mem:cleanup days=60 → cleanup older than 60 daysformat-3: /mem:cleanup max_to_keep=500 → keep only 500 most recentformat-4: /mem:cleanup id=15 → delete specific memoryformat-5: /mem:cleanup ids=15,16,17 → delete multiple specificdetect: STORE-AS($MODE = {detect mode: bulk|single|multi from STORE-GET($RAW_INPUT)})extract-ids: STORE-AS($DELETE_IDS = {extract id/ids from STORE-GET($RAW_INPUT) if present})extract-params: Use STORE-GET($CLEANUP_PARAMS) for days_old, max_to_keep values
Workflow step2
STEP 2 - Handle Single ID Delete
check: IF(STORE-GET($MODE) === "single") → Use ID from STORE-GET($DELETE_IDS) → mcp__vector-memory__get_by_memory_id('{memory_id: {id}}') → STORE-AS($TARGET = memory to delete) → Display: "--- Memory to Delete ---" → Display: "ID: {id}" → Display: "Category: {category}" → Display: "Content: {content_preview}" → Display: "Tags: {tags}" → Display: "" → Prompt: "DELETE this memory? This cannot be undone. (yes/no)" → END-IF
Workflow step3
STEP 3 - Handle Multiple IDs Delete
check: IF(STORE-GET($MODE) === "multi") → Use IDs array from STORE-GET($DELETE_IDS) → ForEach ID: fetch memory preview → Display: "--- Memories to Delete ({count}) ---" → ForEach: "#{id} [{category}] {preview}" → Display: "" → Prompt: "DELETE all {count} memories? This cannot be undone. (yes/no)" → END-IF
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 · 97 lines · 11 tokens per session scan A 2247e6b33e65
mem:cleanup is a command published in the GitHub repository Xsaven/vector-memory-mcp (0 stars, last pushed 6mo ago), licensed MIT. It adds 11 tokens to every session and 1,276 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 2026-09-01.
Other commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.