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 vasilyu1983/AI-Agents-public --skill software-searchgit clone --depth 1 https://github.com/vasilyu1983/AI-Agents-publicWrote 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/vasilyu1983/ai-agents-public/software-search)<a href="https://agentmods.dev/skills/vasilyu1983/ai-agents-public/software-search"><img src="https://agentmods.dev/badge/skills/vasilyu1983/ai-agents-public/software-search/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/vasilyu1983/ai-agents-public/software-search"><img src="https://agentmods.dev/badge/skills/vasilyu1983/ai-agents-public/software-search.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00027 | $0.07504 |
| Opus 5 | $0.00014 | $0.03752 |
| Sonnet 5 | $0.00005 | $0.01501 |
| Haiku 4.5 | $0.00003 | $0.00750 |
Grade A, and why
software-search 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 7d 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 — 543 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Search Engineering
Build search features that return the right results, fast.
Quick Reference
| Need | Recommended Options |
|---|---|
| Full-text search (managed) | Algolia (fastest DX), Elasticsearch/OpenSearch (most flexible) |
| Full-text search (lightweight) | Typesense (simple), Meilisearch (developer-friendly) |
| Full-text search (embedded) | SQLite FTS5, Tantivy (Rust), Lunr.js (client-side) |
| PostgreSQL built-in | pg_trgm + tsvector/tsquery (good enough for many apps) |
| Vector search | pgvector, Pinecone, Weaviate, Qdrant |
| Hybrid search | Keyword + vector, reciprocal rank fusion |
| Autocomplete | Prefix matching, search-as-you-type index, debounced queries |
| Faceted search | Aggregation queries, filter counts, hierarchical facets |
| Search analytics | Click-through rate, zero-result queries, query refinement patterns |
| Search UI | InstantSearch.js (Algolia), SearchKit, custom |
When to Use This Skill
- Choosing a search engine or evaluating whether PostgreSQL search is sufficient
- Building full-text search, autocomplete, or faceted filtering
- Designing an indexing pipeline from source data to search index
- Tuning relevance scoring, synonyms, or ranking signals
- Implementing search analytics to measure and improve quality
- Debugging search quality issues (missing results, poor ranking, slow queries)
When NOT to Use This Skill
- RAG and retrieval for LLM context augmentation → ai-rag
- Database query optimization (SQL performance) → data-sql-optimization
- Marketing SEO and search visibility →
marketing-seo - Product analytics and event tracking →
marketing-product-analytics - Backend API design and architecture → software-backend
Workflow
- Confirm the search problem: engine choice, indexing pipeline, relevance, autocomplete, or analytics.
- Route RAG, database tuning, SEO, or API-architecture questions to the adjacent skill when product search is not the real problem.
- Choose PostgreSQL, a dedicated search engine, vector search, or hybrid search from the decision tree.
- Apply the relevant guidance for indexing, ranking, facets, autocomplete, and measurement.
- Verify current engine capabilities and hosted-service behavior through the navigation references before final recommendations.
What ships with it
5 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.
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.
- 7d ago First seen · 543 lines · 27 tokens per session scan A 4b34ea2d1274
software-search is a skill published in the GitHub repository vasilyu1983/AI-Agents-public (87 stars, last pushed 8d ago), licensed MIT. It adds 27 tokens to every session and 7,504 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 2026-09-03.
Other skills, from other repositories
ai-orchestration-vercel-ai-sdk
Vercel AI SDK patterns - providers, text generation, streaming, structured output, tool calling, chat UI hooks, embeddings, and RAG.
continuum-recipes
Copy-pasteable Continuum patterns — RAG, plan-and-execute, ReAct, multi-tenant agents, FastAPI integration, structured output, prompt-injection scanning, custom containers. Invoke when the user asks "how do I do X with Continuum" and X is a common app pattern rather than a single API question.
vllm-caching
Target audience: operators running vLLM on H100/H200-class datacenter GPUs in production. Assumes CUDA 12/13, Kubernetes or bare container deployment, multi-GPU tensor parallel.
open-webui-api
Administer Open WebUI entirely via its REST API (v0.11.x): user/group lifecycle, permissions, model catalog GitOps (export/import/sync), knowledge/RAG pipelines, config-as-code, SCIM provisioning, event webhooks, and backup surfaces. Grounded in the v0.11.0 source — covers the 476-path surface the official docs leave…
context-management
Strategies for managing AI agent context windows including optimization, summarization, retrieval-augmented generation, progressive disclosure, and pruning. Use when the user is hitting context limits, building long-running agents, implementing RAG, optimizing token usage, or designing systems that need to manage…
atlas
Architect the intelligence layer for agentic systems — RAG pipelines, model selection, embeddings, evaluation, and knowledge systems. Use when the user says "atlas", "ai data", "data arc". Produces data/ML architecture blueprints.