ci-data-analyst

ci-data-analyst is a skill for Claude Code, Codex from openshift-eng/ai-helpers. It costs 36 tokens per session (5,135 once invoked), scanned A, original, Apache-2.0.

A cost-controlled analyst for OpenShift CI data stored in BigQuery, Google's large-scale data warehouse.

In plain words
What is it for?
Use it to examine prow job runs, JUnit test results, pass and fail rates, flaky tests, regressions, and differences across platforms or other job variants.
Why use it?
It helps investigate test failures and trends while checking query size and estimated cost before running expensive searches.

Skill for Claude CodeCodex

Part of the bigquery plugin — 2 skills, 1 command shipped together

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.

agentmods
npx agentmods add skills/openshift-eng/ai-helpers/ci-data-analyst
Any agent
npx skills add openshift-eng/ai-helpers --skill ci-data-analyst
Clone the repo
git clone --depth 1 https://github.com/openshift-eng/ai-helpers

Made for: Claude Code, Codex.

Or install bigquery, the plugin that ships this one along with the rest of its 2 skills, 1 command.

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 ci-data-analyst

README.md
[![agentmods](https://agentmods.dev/badge/skills/openshift-eng/ai-helpers/ci-data-analyst.svg)](https://agentmods.dev/skills/openshift-eng/ai-helpers/ci-data-analyst)
Your own site
<a href="https://agentmods.dev/skills/openshift-eng/ai-helpers/ci-data-analyst"><img src="https://agentmods.dev/badge/skills/openshift-eng/ai-helpers/ci-data-analyst.svg" alt="Measured on agentmods" height="20"></a>
Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,135 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00036 $0.05135
Opus 5 $0.00018 $0.02567
Sonnet 5 $0.00007 $0.01027
Haiku 4.5 $0.00004 $0.00513

Measured 5d ago against content hash c9ceb5e35ea1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ci-data-analyst 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 5d 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.

plugins/bigquery/skills/ci-data-analyst/SKILL.md · 409 lines

How it starts

The opening of the file, as written. The whole thing — 409 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CI Data Analyst

An agent for querying and analyzing OpenShift CI data stored in BigQuery. Covers prow job runs, junit test results, job variants, and related tables. Prioritizes cost safety: every query is dry-run first, costs are estimated, and the user confirms before execution.

When to Use This Skill

  • Investigating test failures, flakes, or regressions across CI jobs
  • Querying prow job pass/fail rates over time
  • Analyzing test results by variant (platform, architecture, network, upgrade, etc.)
  • Exploring CI data patterns (e.g. which jobs run a test, how often a test fails)
  • Any ad-hoc BigQuery analysis against OpenShift CI datasets

Prerequisites

  • bq CLI installed and authenticated (gcloud auth login)
  • BigQuery read access to the openshift-gce-devel project

Core Principles

1. Cost Safety Is Non-Negotiable

The junit table alone is massive. Every query MUST go through this flow:

  1. Show the query to the user before doing anything
  2. Dry-run to get bytes scanned: bq query --project_id=openshift-gce-devel --dry_run --use_legacy_sql=false '<query>'
  3. Calculate cost: bytes / 10^12 * $6.25 (on-demand pricing)
  4. If cost > $1.00: show the estimated cost and bytes scanned, ask user to confirm before executing
  5. If cost <= $1.00: proceed, but still report the cost in results
  6. Never loop or repeat queries. Run once, cache locally, analyze from the cached data.

2. Always Use Partition and Clustering Filters

Both key tables are partitioned by day:

  • junit: partitioned on modified_time, clustered on release
  • jobs: partitioned on prowjob_start

Every query MUST include a filter on the partition column to avoid full-table scans. Use tight date ranges.

Every junit query targeting a specific release MUST filter on release to activate clustering pruning. This reduces bytes scanned by 60-70%:

WHERE modified_time >= DATETIME("2026-05-01")
  AND modified_time < DATETIME("2026-05-08")
  AND release = '4.22'

Read the full file on GitHub · 409 lines

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. 5d ago First seen · 409 lines · 36 tokens per session scan A c9ceb5e35ea1

Subscribe to this mod's changes

ci-data-analyst is a skill published in the GitHub repository openshift-eng/ai-helpers (116 stars, last pushed today), licensed Apache-2.0. It adds 36 tokens to every session and 5,135 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens