udi-opensearch

udi-opensearch is a skill for Claude Code, Codex from ibm-self-serve-assets/building-blocks. It costs 74 tokens per session (3,011 once invoked), scanned A, original, Apache-2.0.

A workflow for moving documents from IBM Cloud Object Storage into OpenSearch, IBM's search and retrieval system, using text extraction and embeddings.

In plain words
What is it for?
Use it to configure and run document ingestion, including OCR text extraction, text chunking, embedding creation, and OpenSearch indexing.
Why use it?
It removes much of the repeated setup needed to register connections, create the ingestion flow, and start document-processing runs.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to configure and run document ingestion, including OCR text extraction, text chunking, embedding creation, and OpenSearch indexing.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ibm-self-serve-assets/building-blocks/udi-opensearch
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 ibm-self-serve-assets/building-blocks --skill udi-opensearch
Clone the repo
git clone --depth 1 https://github.com/ibm-self-serve-assets/building-blocks

Made for: Claude Code, Codex.

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.

agentmods badge for udi-opensearch

README.md
[![agentmods](https://agentmods.dev/badge/skills/ibm-self-serve-assets/building-blocks/udi-opensearch/github.svg)](https://agentmods.dev/skills/ibm-self-serve-assets/building-blocks/udi-opensearch)
Your own site
<a href="https://agentmods.dev/skills/ibm-self-serve-assets/building-blocks/udi-opensearch"><img src="https://agentmods.dev/badge/skills/ibm-self-serve-assets/building-blocks/udi-opensearch/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.

agentmods 80×15 button for udi-opensearch

Your own site · 80×15
<a href="https://agentmods.dev/skills/ibm-self-serve-assets/building-blocks/udi-opensearch"><img src="https://agentmods.dev/badge/skills/ibm-self-serve-assets/building-blocks/udi-opensearch.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 74 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,011 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Privilege Escalation · line 150
    Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
    Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
How audits are shown
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00074 $0.03011
Opus 5 $0.00037 $0.01505
Sonnet 5 $0.00015 $0.00602
Haiku 4.5 $0.00007 $0.00301

Measured 12d ago against content hash e3304ba4a665, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

udi-opensearch 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 12d ago.

The scan reads SKILL.md. This mod also ships 4 executable files (scripts/ingest.py, scripts/ingest.sh, scripts/setup.py, …), 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.

ibm-bob/skills/udi-opensearch/SKILL.md · 247 lines

How it starts

The opening of the file, as written. The whole thing — 247 lines — stays where its author put it; the contents beside it link to each section on GitHub.

UDI Skill — Document Ingestion into OpenSearch

This skill scaffolds a pure-Python two-part UDI pipeline:

  • Part 1 — setup.py — run once: registers COS + OpenSearch connections, creates the UDI flow, saves all IDs to udi_config.json
  • Part 2 — ingest.py — run every time: reads udi_config.json and starts a new flow run

No Terraform required — infrastructure (COS, WML, OpenSearch) is a user prerequisite.

Skill directory layout

.bob/skills/udi-opensearch/
├── SKILL.md
├── .gitignore           → .gitignore
└── scripts/
    ├── .env.example     → scripts/.env.example     (copy to scripts/.env)
    ├── setup.sh         → scripts/setup.sh         (Part 1 — run once)
    ├── ingest.sh        → scripts/ingest.sh        (Part 2 — run repeatedly)
    ├── setup.py         → scripts/setup.py         (called by setup.sh)
    ├── ingest.py        → scripts/ingest.py        (called by ingest.sh)
    └── requirements.txt → scripts/requirements.txt

Pipeline overview

COS bucket → extract text (OCR) → chunk → watsonx embeddings → OpenSearch index
# UDI Operator Role
1 ingest_cpd_connections Reads documents from COS via a registered watsonx connection
2 extract_cpd Extracts text with OCR (high quality mode)
3 chunker Splits text into overlapping chunks
4 embeddings Generates vector embeddings (ibm/slate-30m-english-rtrvr-v2)
5 opensearch Indexes chunks + vectors into an OpenSearch index

Step 0a — Detect the host OS

Before issuing any shell commands, detect the OS:

python -c "import platform; print(platform.system())"
OS result Shell Python binary Set env var
Linux or Darwin bash python3 export KEY="val"
Windows cmd / PowerShell python set KEY=val (cmd) or $env:KEY="val" (PS)

Step 0b — Prerequisites checklist

Before proceeding, confirm the user has all of the following. Present as a checklist using ask_followup_question if anything is unclear.

Read the full file on GitHub · 247 lines

Files

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.

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.

  1. 12d ago First seen · 247 lines · 74 tokens per session scan A e3304ba4a665

Subscribe to this mod's changes

udi-opensearch is a skill published in the GitHub repository ibm-self-serve-assets/building-blocks (24 stars, last pushed today), licensed Apache-2.0. It adds 74 tokens to every session and 3,011 once invoked, about $0.0004 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 2026-08-30.