A read-only question-answering tool that uses live data from a running skardi-server through the skardi command-line tool. It discovers available data sources and searches them before writing an answer.

Finding information through semantic search, checking available data sources and schemas, and answering questions without changing the data.

It lets you answer questions from current connected data rather than relying only on files or memory.

retrieval — Skill for Claude Code by SkardiLabs

Install

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.

Any agent

npx skills add SkardiLabs/skardi-skills --skill retrieval

Clone the repo

git clone --depth 1 https://github.com/SkardiLabs/skardi-skills

Made for: Claude Code.

Or install skardi, the plugin that ships this one along with the rest of its 4 skills.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/skardilabs/skardi-skills/retrieval/github.svg)](https://agentmods.dev/skills/skardilabs/skardi-skills/retrieval)

Your own site

<a href="https://agentmods.dev/skills/skardilabs/skardi-skills/retrieval"><img src="https://agentmods.dev/badge/skills/skardilabs/skardi-skills/retrieval/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/skardilabs/skardi-skills/retrieval"><img src="https://agentmods.dev/badge/skills/skardilabs/skardi-skills/retrieval.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 220 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 5,307 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00220	$0.05307
Opus 5	$0.00110	$0.02653
Sonnet 5	$0.00044	$0.01061
Haiku 4.5	$0.00022	$0.00531

Measured today against content hash 429e34003e0f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

retrieval 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.

The scan reads SKILL.md. This mod also ships 2 executable files (evals/fixtures/make_data.py, evals/fixtures/setup.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/retrieval/SKILL.md · 219 lines

How it starts

The opening of the file, as written. The whole thing — 219 lines — stays where its author put it; the contents beside it link to each section on GitHub.

retrieval — answer questions from live data through skardi

Your job: take a concrete question, find the data behind a running skardi-server that answers it, and come back with the answer plus the query that produced it. The loop is always the same: discover → search meaning first → SQL for precision → check what came back → report.

The skardi CLI is a thin HTTP client — every command below is one request to the server, which holds the query engine, the source registrations, and the safety policy. You never need database drivers, connection strings, or credentials for the backing stores; if the server is reachable, you can work.

What this skill is not

Not index building. If the user wants documents made searchable, a RAG surface, or embeddings — that is the auto-context skill. This skill consumes whatever search surface already exists.
Not writing. Retrieval means SELECT. Writes (INSERT / UPDATE / DELETE, scheduled materialization) belong to Skardi's job path with its own review; do not do them from here even when a source would allow it.
Not server operations. No server running, no sources registered, missing token — report what is missing and stop. Do not install, start, or reconfigure a server as a side effect of answering a question.

Prerequisites

The skardi CLI on PATH. One small binary, no runtime deps. Check with skardi --version. Install from the GitHub releases page — download the tarball for your platform, untar, put skardi on PATH.
A reachable skardi-server. Connection resolves in this order: --server <URL> flag → $SKARDI_SERVER_URL → ~/.skardi/config.yaml → default http://127.0.0.1:8080. If auth is enabled on the server, pass --token or set $SKARDI_API_TOKEN.
Exit code contract: 2 means the server was unreachable. That is an environment problem, not a query problem — see the stuck protocol.

This skill is written and tested against v0.5.0 of both CLI and server (the current release), except the --purpose/--session-id audit pair, which needs a main build — the exception below. Deployment behavior — which sources exist, what is read-only, row caps — is discovered live and is never assumed from this text.

Read the full file on GitHub · 219 lines

Files

What ships with it

9 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.

Changes

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 Changed · +42 lines 429e34003e0f
2d ago Changed · +35 lines ab97b7bfdd66
11d ago First seen · 142 lines · 220 tokens per session scan A d895035ed65b

Subscribe to this mod's changes

retrieval is a skill published in the GitHub repository SkardiLabs/skardi-skills (5 stars, last pushed yesterday), licensed Apache-2.0. It adds 220 tokens to every session and 5,307 once invoked, about $0.0011 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 2026-08-31.

Data and AI Research

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…

google/skills · 85 tokens

agent-platform-model-registry

Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.

google/skills · 60 tokens

foundry-config-setup

Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.

microsoft/agent-framework · 65 tokens

google-cloud-solution-agentic-analytics-spark-knowledge-catalog

Discovers requirements and generates guidance to design and deploy a governed, secure agentic-analytics solution for data that's distributed across Google Cloud, other cloud providers, or on-premises. Data that's outside Google Cloud (such as data from Databricks, Snowflake, Salesforce, SAP, or Oracle systems) is…

google/skills · 138 tokens

training-check

Interactively monitor training metrics from the current Codex session, periodically checking WandB or fallback logs for NaN, divergence, plateaus, and broken runs.

wanshuiyin/Auto-claude-code-research-in-sleep · 35 tokens

nemo-automodel-launcher-config

Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.

NVIDIA/skills · 30 tokens