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 skills add DNYoussef/context-cascade --skill agentdb-performance-optimizationgit clone --depth 1 https://github.com/DNYoussef/context-cascadeWrote 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/dnyoussef/context-cascade/agentdb-performance-optimization)<a href="https://agentmods.dev/skills/dnyoussef/context-cascade/agentdb-performance-optimization"><img src="https://agentmods.dev/badge/skills/dnyoussef/context-cascade/agentdb-performance-optimization/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/dnyoussef/context-cascade/agentdb-performance-optimization"><img src="https://agentmods.dev/badge/skills/dnyoussef/context-cascade/agentdb-performance-optimization.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 | $0.00070 | $0.04693 |
| Opus 5.5 | $0.00028 | $0.01877 |
| Sonnet 5.5 | $0.00014 | $0.00939 |
| Haiku 4.5 | $0.00007 | $0.00469 |
Grade A, and why
agentdb-performance-optimization 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 1mo 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 — 631 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LIBRARY-FIRST PROTOCOL (MANDATORY)
Before writing ANY code, you MUST check:
Step 1: Library Catalog
- Location:
.claude/library/catalog.json - If match >70%: REUSE or ADAPT
Step 2: Patterns Guide
- Location:
.claude/docs/inventories/LIBRARY-PATTERNS-GUIDE.md - If pattern exists: FOLLOW documented approach
Step 3: Existing Projects
- Location:
D:\Projects\* - If found: EXTRACT and adapt
Decision Matrix
| Match | Action |
|---|---|
| Library >90% | REUSE directly |
| Library 70-90% | ADAPT minimally |
| Pattern exists | FOLLOW pattern |
| In project | EXTRACT |
| No match | BUILD (add to library after) |
When NOT to Use This Skill
- Local-only operations with no vector search needs
- Simple key-value storage without semantic similarity
- Real-time streaming data without persistence requirements
- Operations that do not require embedding-based retrieval
Success Criteria
- Vector search query latency: <10ms for 99th percentile
- Embedding generation: <100ms per document
- Index build time: <1s per 1000 vectors
- Recall@10: >0.95 for similar documents
- Database connection success rate: >99.9%
- Memory footprint: <2GB for 1M vectors with quantization
Edge Cases & Error Handling
- Rate Limits: AgentDB local instances have no rate limits; cloud deployments may vary
- Connection Failures: Implement retry logic with exponential backoff (max 3 retries)
- Index Corruption: Maintain backup indices; rebuild from source if corrupted
- Memory Overflow: Use quantization (4-bit, 8-bit) to reduce memory by 4-32x
- Stale Embeddings: Implement TTL-based refresh for dynamic content
- Dimension Mismatch: Validate embedding dimensions (384 for sentence-transformers) before insertion
Guardrails & Safety
- NEVER expose database connection strings in logs or error messages
- ALWAYS validate vector dimensions before insertion
- ALWAYS sanitize metadata to prevent injection attacks
- NEVER store PII in vector metadata without encryption
- ALWAYS implement access control for multi-tenant deployments
- ALWAYS validate search results before returning to users
What ships with it
19 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.
- examples/example-1-quantization.md 7.8 KB
- examples/example-2-hnsw-tuning.md 11 KB
- examples/example-3-batching.md 12 KB
- graphviz/workflow.dot 6.0 KB
- readme.md 6.2 KB
- references/hnsw-parameters.md 13 KB
- references/quantization-techniques.md 12 KB
- references/readme-gold.md 9.7 KB
- resources/scripts/batch_ops.py 15 KB runs code
- resources/scripts/cache_optimize.py 14 KB runs code
- resources/scripts/hnsw_tuning.sh 8.1 KB runs code
- resources/scripts/quantize_vectors.py 13 KB runs code
- resources/templates/cache-config.json 9.0 KB
- resources/templates/hnsw-params.json 8.3 KB
- resources/templates/quantization-config.yaml 3.6 KB
- SKILL-meta.yaml 421 B
- tests/test-1-quantization-4x.md 7.4 KB
- tests/test-2-hnsw-tuning.md 9.5 KB
- tests/test-3-batch-ops.md 10 KB
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.
- 1mo ago First seen · 631 lines · 70 tokens per session scan A 654095d33e4c
agentdb-performance-optimization is a skill published in the GitHub repository DNYoussef/context-cascade (32 stars, last pushed 3mo ago), licensed MIT. It adds 70 tokens to every session and 4,693 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
agent-platform-rag-engine-management
Manage and query Agent Platform RAG Engine Corpora and retrieve grounded contexts using the Google GenAI SDK. Use when listing RAG corpora or files, inspecting a corpus, retrieving contexts, or generating content grounded in a RAG corpus. Do not use for standard database queries (use SQL/Spanner skills), Google…
llm-app-patterns
Production-ready patterns for building LLM applications. Covers RAG pipelines, agent architectures, prompt IDEs, and LLMOps monitoring. Use when designing AI applications, implementing RAG, building agents, or setting up LLM observability.
9router-embeddings
Generate vector embeddings via 9Router /v1/embeddings using OpenAI / Gemini / Mistral / Voyage / Nvidia / GitHub embedding models for RAG, semantic search, similarity. Use when the user wants embeddings, vectors, RAG, semantic search, or to embed text.
similarity-search-patterns
Implement efficient similarity search with vector databases. Use when building semantic search, implementing nearest neighbor queries, or optimizing retrieval performance.
embedding-strategies
Select and optimize embedding models for semantic search and RAG applications. Use when choosing embedding models, implementing chunking strategies, or optimizing embedding quality for specific domains.
edd
Eval-driven development loop for this repo (rag-loop, an aircraft-systems RAG app on LangGraph, OpenAI, Qdrant Cloud, and TruLens). Use when the user wants to run an experiment, inspect feedback metrics, or decide keep-or-reject on a config/prompt change.