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/storegit clone --depth 1 https://github.com/Xsaven/vector-memory-mcpWhat 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 | $0.00013 | $0.01169 |
| Opus 5 | $0.00006 | $0.00584 |
| Sonnet 5 | $0.00003 | $0.00234 |
| Haiku 4.5 | $0.00001 | $0.00117 |
Grade A, and why
mem:store scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Iron Rules
Analyze-content (CRITICAL)
MUST analyze STORE-GET($RAW_INPUT) content before storing
- why: Content analysis ensures proper categorization and prevents garbage storage
- on_violation: Parse STORE-GET($RAW_INPUT), extract content, determine domain and type
Check-duplicates (HIGH)
MUST search for similar memories before storing
- why: Prevents duplicate entries and wasted storage
- on_violation: Execute mcp__vector-memory__search_memories('{query: "{content_summary}", limit: 3}')
Mandatory-approval (CRITICAL)
MUST get user approval before storing memory
- why: User must validate content, category, and tags before committing
- on_violation: Present memory specification and wait for YES/APPROVE
Input
STORE-AS($RAW_INPUT = $ARGUMENTS) STORE-AS($MEMORY_CONTENT = {content to store extracted from $RAW_INPUT})
Role
Memory storage specialist that analyzes content, checks for duplicates, suggests appropriate category and tags, and stores memory after user approval.
Workflow step1
STEP 1 - Parse STORE-GET($RAW_INPUT)
format-1: Direct content: /mem:store "This is the memory content"format-2: With params: /mem:store content="..." category=code-solution tags=php,laravelextract: Extract from STORE-GET($RAW_INPUT): content (required), category (optional), tags (optional)derive-content: STORE-AS($CONTENT = {extract content from STORE-GET($RAW_INPUT)})derive-category: STORE-AS($CATEGORY = {extract category from STORE-GET($RAW_INPUT) if provided})derive-tags: STORE-AS($TAGS = {extract tags from STORE-GET($RAW_INPUT) if provided})output: STORE-AS($INPUT = {STORE-GET($CONTENT), STORE-GET($CATEGORY)?, STORE-GET($TAGS)?})
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 · 109 lines · 13 tokens per session scan A d654e6172d27
mem:store is a command published in the GitHub repository Xsaven/vector-memory-mcp (0 stars, last pushed 6mo ago), licensed MIT. It adds 13 tokens to every session and 1,169 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.