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/sairam0424/mindforge/embeddingsgit clone --depth 1 https://github.com/sairam0424/MindForgeWrote 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/sairam0424/mindforge/embeddings)<a href="https://agentmods.dev/commands/sairam0424/mindforge/embeddings"><img src="https://agentmods.dev/badge/commands/sairam0424/mindforge/embeddings.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 5.1 | $0.00049 | $0.00605 |
| Opus 5 | $0.00024 | $0.00302 |
| Sonnet 5 | $0.00010 | $0.00121 |
| Haiku 4.5 | $0.00005 | $0.00060 |
Grade A, and why
mindforge:embeddings 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.
What it actually says
<execution_context> @.mindforge/skills/embedding-systems/SKILL.md </execution_context>
-
Embedding Model Selection: Recommend models by domain (text: OpenAI ada-002/text-embedding-3, Cohere, E5; images: CLIP, DINOv2), evaluate trade-offs (dimensionality vs accuracy, speed vs quality), and specify fine-tuning requirements for domain adaptation.
-
Vector Database Architecture: Compare database options (Pinecone for managed simplicity, Qdrant for control, Weaviate for multimodal, pgvector for SQL integration), design sharding and replication strategies for scale, and specify index types (HNSW, IVF, flat) based on query patterns.
-
Hybrid Search Implementation: Design keyword search integration (BM25, Elasticsearch) alongside vector search, implement score fusion strategies (RRF, weighted combination), and optimize for both semantic understanding and exact term matching.
-
Indexing and Optimization: Configure HNSW parameters (M, ef_construction) for speed/accuracy balance, implement quantization (product quantization, scalar quantization) for memory efficiency, and design incremental indexing for real-time updates.
-
Query Optimization: Implement query preprocessing (normalization, expansion, reranking), design filtered search with metadata constraints, and create multi-stage retrieval pipelines (coarse-to-fine, two-tower reranking).
-
Monitoring and Evaluation: Define retrieval quality metrics (precision@k, recall@k, MRR, NDCG), implement latency tracking and cost monitoring per query, and design A/B testing framework for embedding model comparisons.
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 · 38 lines · 49 tokens per session scan A 532abe4c1050
mindforge:embeddings is a command published in the GitHub repository sairam0424/MindForge (0 stars, last pushed 2d ago), licensed MIT. It adds 49 tokens to every session and 605 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 commands, from other repositories
pgvector-search
Production hybrid search with PGVector and BM25 using Reciprocal Rank Fusion, metadata filtering, and performance tuning for semantic retrieval. Use when building hybrid semantic and keyword search, tuning PGVector performance, or filtering by metadata. Triggers on pgvector, hybrid search, BM25, reciprocal rank…
tune-vector-index
Recommend and generate optimized HNSW or IVFFlat index configuration given row count and query latency target. Outputs DROP + CREATE INDEX SQL with tuned parameters, EXPLAIN ANALYZE template, and pgvector-specific query-time settings (efsearch, probes).
laravel-vector-search
Add semantic/vector search with pgvector (Laravel 13+); use the laravel:vector-search skill exactly as written.
design-vector-schema
Design a pgvector migration SQL file. Captures model + dimension + distance metric + row count → generates reversible Flyway/Alembic migration with correct index type, metadata columns, and null guards.
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.