Borrowing it
Nothing to install: this file belongs to jtv4k/mongodb-memory-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/jtv4k/mongodb-memory-mcp/main/.claude/skills/vector-index-management/SKILL.mdgit clone --depth 1 https://github.com/jtv4k/mongodb-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/skills/jtv4k/mongodb-memory-mcp/vector-index-management)<a href="https://agentmods.dev/skills/jtv4k/mongodb-memory-mcp/vector-index-management"><img src="https://agentmods.dev/badge/skills/jtv4k/mongodb-memory-mcp/vector-index-management/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/skills/jtv4k/mongodb-memory-mcp/vector-index-management"><img src="https://agentmods.dev/badge/skills/jtv4k/mongodb-memory-mcp/vector-index-management.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 | $0.00088 | $0.02846 |
| Opus 5.5 | $0.00035 | $0.01138 |
| Sonnet 5.5 | $0.00018 | $0.00569 |
| Haiku 4.5 | $0.00009 | $0.00285 |
Grade A, and why
vector-index-management 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 2mo 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 — 250 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vector and search index management
Three search indexes and seven standard indexes, all declared as code, all applied by one idempotent command. The Atlas UI is never the source of truth: an index clicked together by hand cannot be reproduced on Atlas Local, in CI, or on the next cluster.
| Index | Collection | Type | Definition |
|---|---|---|---|
MONGODB_VECTOR_INDEX_NAME (default chunks_vector_index) |
chunks |
vectorSearch |
src/db/index-definitions/chunks.vector.json |
MONGODB_TEXT_INDEX_NAME (default chunks_text_index) |
chunks |
search |
src/db/index-definitions/chunks.text.json |
MONGODB_DOCUMENTS_TEXT_INDEX_NAME (default documents_text_index) |
documents |
search |
src/db/index-definitions/documents.text.json |
Standard b-tree indexes live in STANDARD_INDEXES in src/db/indexes.ts, each
carrying a why string naming the query it serves. If nothing runs that query,
delete the index rather than keeping it "just in case".
The command
# read-only: what would change, and what is queryable right now
./scripts/ndocker.sh npm run db:indexes -- --dry-run
# apply, then wait for the search indexes to become queryable
./scripts/ndocker.sh npm run db:indexes
# apply and return immediately
./scripts/ndocker.sh npm run db:indexes -- --no-wait
# override MONGODB_INDEX_READY_TIMEOUT_MS for this run
./scripts/ndocker.sh npm run db:indexes -- --timeout 600000
It needs MONGODB_URI and MONGODB_DB_NAME in its environment. Inside the dev
stack that is already true:
docker compose -f docker/docker-compose.yml -f docker/docker-compose.dev.yml -f docker/docker-compose.db.yml \
run --rm app npm run db:indexes
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.
- 2mo ago First seen · 250 lines · 88 tokens per session scan A e030e6613e9d
vector-index-management is a skill published in the GitHub repository jtv4k/mongodb-memory-mcp (0 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 88 tokens to every session and 2,846 once invoked, about $0.0004 per session on Opus 5.5. 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.
vector-index-management compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| vector-index-managementjtv4k/mongodb-memory-mcp | Skill | 0 | 2mo ago | Apache-2.0 | A | 88 | Claude Code |
| dbxt8y2/dbx | Skill | 29k | yesterday | Apache-2.0 | A | 74 | Claude Code, Codex |
| azure-mgmt-mongodbatlas-dotnetmicrosoft/skills | Skill | 3.2k | yesterday | MIT | A | 64 | Claude Code |
| nosqliPurpleAILAB/Decepticon | Skill | 6.5k | 8d ago | Apache-2.0 | A | 38 | Claude Code, Codex |
| byted-volcengine-mongodbbytedance/agentkit-samples | Skill | 484 | yesterday | Apache-2.0 | A | 82 | Claude Code, Codex |
| commerce-app-storageadobe/skills | Skill | 319 | yesterday | Apache-2.0 | A | 78 | Claude Code |
| mongodb-connectionfcakyon/claude-codex-settings | Skill | 1.2k | yesterday | Apache-2.0 | A | 122 | Claude Code |