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 atlanhq/agent-toolkit --skill atlan-searchgit clone --depth 1 https://github.com/atlanhq/agent-toolkitWrote 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/atlanhq/agent-toolkit/atlan-search)<a href="https://agentmods.dev/skills/atlanhq/agent-toolkit/atlan-search"><img src="https://agentmods.dev/badge/skills/atlanhq/agent-toolkit/atlan-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/atlanhq/agent-toolkit/atlan-search"><img src="https://agentmods.dev/badge/skills/atlanhq/agent-toolkit/atlan-search.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 | $0.00159 | $0.02043 |
| Opus 5.5 | $0.00064 | $0.00817 |
| Sonnet 5.5 | $0.00032 | $0.00409 |
| Haiku 4.5 | $0.00016 | $0.00204 |
Grade A, and why
atlan-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 29d 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 — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Searching the Atlan catalog
The catalog holds metadata — assets, their names, owners, certification, tags, glossary links, domains, quality checks, lineage. It does not hold row values. Pick the entry point from the ask, then apply the rules below.
Pick the tool
| The ask | Tool |
|---|---|
| Topic / natural-language discovery — "what data do we have about churn", "which table has retention rate" | semantic_search |
| Counts and breakdowns — "how many verified tables", "assets by connector" | search_assets with return_count_only / aggregations |
| Exact, deterministic attribute filters — name prefix, certification, connector, type, tag, domain, term | search_assets |
| Full detail on assets you already have GUIDs for — columns, README, custom metadata values | get_assets |
| Upstream / downstream dependencies | traverse_lineage (resolve the GUID first) |
| Data quality checks and rules | search_assets on the DQ types — see references/data-quality.md |
| Which tags or custom-metadata sets exist on this tenant | resolve_metadata |
| A person or a team | get_users / get_groups |
| Which attributes a type supports | describe_asset_type |
| Row-level data values in the source warehouse | query_assets |
| Skills, knowledge files, agents (context repos) | read_artifact |
| How a product feature works | search_atlan_docs |
semantic_search has its own planner: it reads the whole question, decomposes
it, and applies filters itself. search_assets does exactly what you tell it
and nothing more. Reach for semantic_search when the ask is phrased as a
question; search_assets when you already know the precise filter.
The rules that decide whether you get the right answer
1. Be precise about asset type. "tables" means asset_type="Table" — not
Views, not Columns. "dashboards" means the BI dashboard types. asset_type is
singular and takes either a string or a list (["Table", "View"]). Only go
broad when the user says "all assets", and when you do, exclude the internal
plumbing types (see references/filters.md).
What ships with it
6 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.
- 29d ago First seen · 141 lines · 159 tokens per session scan A 3ed11ceeae27
atlan-search is a skill published in the GitHub repository atlanhq/agent-toolkit (41 stars, last pushed yesterday), licensed MIT. It adds 159 tokens to every session and 2,043 once invoked, about $0.0006 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 2026-09-29.
Other skills, from other repositories
natural
Render the provided prompt template with Jinja context and send it to the active NPC's LLM. The rendered text becomes the user prompt; the LLM response is placed in context['output'].
building-agents
Use when building or restructuring an LLM agent — provider adapter, tool calling, structured output, RAG, agent loop, eval gate, cost routing, tracing, MCP server — model-agnostic across OpenAI/Anthropic/Gemini/OSS so a model swap is a config change. NOT vector-store SQL alone (that is postgresdb) or service…
agent-eval
Use when measuring whether an LLM or agent system actually got better and gating merges on it: golden sets, fixing an inflated LLM-as-judge, scoring RAG (faithfulness, contextual recall) or agent trajectories (tool correctness, completion), or picking an eval framework. NOT building the agent loop, tools or RAG…
rag-retrieval
Retrieval-Augmented Generation patterns for grounded LLM responses. Use when building RAG pipelines, embedding documents, implementing hybrid search, contextual retrieval, HyDE, agentic RAG, multimodal RAG, query decomposition, reranking, or pgvector search.
error-analysis
Evals-first error analysis for LLM apps: clusters real Langfuse or JSONL traces into a human-confirmed failure taxonomy with counts, then recommends binary pass/fail evals for recurring named modes. Use to learn what to measure before writing evals. Not for CI failures.
llm-integration
LLM integration patterns for function calling, streaming responses, local inference with Ollama, and fine-tuning customization. Use when implementing tool use, SSE streaming, local model deployment, LoRA/QLoRA fine-tuning, or multi-provider LLM APIs.