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 skills/richfrem/agent-plugins-skills/vector-db-initnpx skills add richfrem/agent-plugins-skills --skill vector-db-initgit clone --depth 1 https://github.com/richfrem/agent-plugins-skillsWrote 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/richfrem/agent-plugins-skills/vector-db-init)<a href="https://agentmods.dev/skills/richfrem/agent-plugins-skills/vector-db-init"><img src="https://agentmods.dev/badge/skills/richfrem/agent-plugins-skills/vector-db-init.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 | $0.00049 | $0.02297 |
| Opus 5 | $0.00024 | $0.01149 |
| Sonnet 5 | $0.00010 | $0.00459 |
| Haiku 4.5 | $0.00005 | $0.00230 |
Grade A, and why
vector-db-init 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 today.
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 — 272 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dependencies
This skill requires Python 3.8+ and standard library for initialization. Performance operations require chromadb and langchain as defined in the plugin root requirements.
To install this skill's dependencies:
python -m piptools compile requirements.in --output-file requirements.txt
pip install -r requirements.txt
Vector DB Initialization
The vector-db-init skill is an interactive setup routine that prepares the environment for the Vector database. It follows the same pattern as rlm-init and wiki-init for a consistent experience across all three retrieval plugins.
Profile Configuration Reference
All operational settings live in .agent/learning/vector_profiles.json. These control performance and connection mode.
| Parameter | Default | Purpose |
|---|---|---|
chroma_host |
"" |
Empty = In-Process (Direct Disk); IP = Server mode. |
batch_size |
1000 |
Files processed per embedding batch. |
embedding_model |
nomic-ai/nomic-embed-text-v1.5 |
Semantic model for indexing. |
device |
cpu |
Hardware: cpu or cuda (NVIDIA GPU). |
parent_chunk_size |
2000 |
Parent chunk granularity. |
child_chunk_size |
400 |
Child chunk granularity. |
When to Use This
- When a user first installs the
vector-dbplugin. - If the Vector DB profile is missing from
.agent/learning/vector_profiles.json. - If you need to add a new manifest profile or update which folders are indexed.
- If you need to re-scaffold a clean configuration after a plugin upgrade.
Default: In-Process (Filesystem) Mode
Vector-db runs In-Process by default — ChromaDB persists directly to a local directory
(configured as chroma_data_path in vector_profiles.json). No server process is needed.
When running ingest.py or query.py you will see:
[WARN] Failed to connect to remote ChromaDB ... Falling back to local.
[DIR] Connecting to local persistent ChromaDB at .agent/learning/vector_wiki_db...
This is expected and correct. The remote-server check (127.0.0.1:8110) happens
automatically in case a server IS running, but falls back gracefully. Only switch to
server mode (vector-db-launch skill) if you need multiple concurrent writers.
What ships with it
17 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- acceptance-criteria.md 320 B
- assets/resources/architecture_sequence.mmd 53 B
- assets/resources/deployment_model.mmd 48 B
- assets/resources/rag_design_choices.md 50 B
- assets/resources/stabilizers/README.md 53 B
- assets/resources/stabilizers/vector_consistency_check.md 71 B
- assets/vector_knowledge_manifest.json 59 B
- assets/vector_profiles.json 49 B
- evals/evals.json 863 B
- evals/results.tsv 172 B
- references/acceptance-criteria.md 42 B
- references/cheapest_models.json 40 B
- references/cheapest_models.md 38 B
- requirements.in 21 B
- requirements.txt 22 B
- scripts/init.py 24 B runs code
- scripts/query.py 25 B runs code
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.
- today First seen · 272 lines · 49 tokens per session scan A 061f45176367
vector-db-init is a skill published in the GitHub repository richfrem/agent-plugins-skills (6 stars, last pushed today), licensed MIT. It adds 49 tokens to every session and 2,297 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
agent-memory-coordinator
Agent skill for memory-coordinator - invoke with $agent-memory-coordinator.
wiki
Initialize, adopt, and route work for a separate Obsidian knowledge vault through the portable claude-obsidian core. Use for vault setup, scaffolding, workspace selection, cross-project configuration, or choosing the correct wiki sub-skill. Triggers: /wiki, set up wiki, scaffold vault, create knowledge base, adopt…
wiki-fold
Create a bounded, extractive, structurally idempotent rollup of recent Obsidian wiki log entries, with dry-run preview by default and one optional transaction apply. Use for manual log compression without modifying child pages. Triggers: fold the log, run a fold, run wiki-fold, log rollup, roll up log entries, commit…
kapso-whatsapp
How to interact with Kapso WhatsApp from the swarm — read inbound webhook payloads (text AND media), fetch message history, send free-form messages within the 24h session window (and template messages outside it), mark-as-read, show the typing indicator, send reactions, download media, verify webhook signatures, and…
scheduled-task-resilience
Guardrails for polling, scheduled jobs, and long-running external operations. Use whenever a task waits on CI, builds, deploys, browser jobs, or another asynchronous API so work survives heartbeat checks without duplicate delivery.
user-management
How to manage the user registry — creating users for new Slack/GitHub/GitLab/Linear identities, managing aliases, resolving users across platforms. Use when a new human interacts with the swarm or when user identity needs updating.