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.
git clone --depth 1 https://github.com/openshift-eng/ai-helpersWrote 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/commands/openshift-eng/ai-helpers/query)<a href="https://agentmods.dev/commands/openshift-eng/ai-helpers/query"><img src="https://agentmods.dev/badge/commands/openshift-eng/ai-helpers/query/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/commands/openshift-eng/ai-helpers/query"><img src="https://agentmods.dev/badge/commands/openshift-eng/ai-helpers/query.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 | $0.00021 | $0.00625 |
| Opus 5.5 | $0.00008 | $0.00250 |
| Sonnet 5.5 | $0.00004 | $0.00125 |
| Haiku 4.5 | $0.00002 | $0.00063 |
Grade A, and why
query 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 16d 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Name
bigquery-ci-data:query
Synopsis
/bigquery-ci-data:query what is the pass rate for periodic aws jobs on 4.22 this week?
/bigquery-ci-data:query which tests have the most retries in the last 7 days?
/bigquery-ci-data:query show me operator degraded time trends for etcd this month
/bigquery-ci-data:query what override decisions has the chain presubmit agent made recently?
Description
General-purpose entry point for querying OpenShift CI data stored in BigQuery. Understands multiple datasets and routes to the appropriate tables based on the question.
The command covers:
- Jobs and tests (
ci_analysis_us): Prow job pass rates, junit test failures/flakes, variant analysis - Autodl data (
ci_data_autodl): Risk analysis, retry statistics, operator state, CPU metrics, audit logs, disruption - Agent decisions (
ci_analysis_us): Chain presubmit override decisions
Implementation
Steps
-
Parse the question: Determine which domain(s) and table(s) are needed:
- Job pass rates, test failures, variant breakdowns → use
jobs-and-testsskill - Risk analysis, retries, operator state, CPU, audit logs, disruption, instance types → use
autodlskill - Presubmit override decisions → use
chai-presubmit-override-decisionsskill - Always load the
foundationsskill for cost safety protocol
- Job pass rates, test failures, variant breakdowns → use
-
Identify parameters: Extract or ask for:
- Date range (suggest 7 days if not specified)
- Release version (if relevant)
- Specific job names, test names, operators, etc.
-
Build and execute query following the foundations workflow:
- Show query to user
- Dry-run for cost estimate
- Confirm if over $1.00
- Execute and cache results
- Analyze and report findings
-
Present results with summary statistics, notable patterns, and suggestions for follow-up.
Arguments
- question (required): Natural language description of what CI data to investigate
Examples
- Test failure investigation:
/bigquery-ci-data:query how often is kube-apiserver readyz failing on 4.22 this week?
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.
- 16d ago First seen · 75 lines · 21 tokens per session scan A 6c0aa95ae622
query is a command published in the GitHub repository openshift-eng/ai-helpers (121 stars, last pushed today), licensed Apache-2.0. It adds 21 tokens to every session and 625 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-06.
Other commands, from other repositories
dart-fix-ci
Command "dart-fix-ci" from dartsim/dart, covering required reading, workflow and output.
domains
Apply the CLI runtime and safety contract before executing a command. Runtime --help is authoritative.
access
Apply the CLI runtime and safety contract before executing a command. Runtime --help is authoritative.
merge-conflict-analysis
You are analyzing merge conflicts for PR #${{ pr-number }}.
analyst
Use when performing local analyst review before pushing PR changes. Assesses code quality, impact analysis, and maintainability.
security-check
Fast security baseline audit of a product — tracked secrets, unpinned/vulnerable GitHub Actions, workflow permission scope, untrusted-input triggers, MCP-config surface, and an RLS reminder. Add --live to also check the RUNNING system for drift (live RLS status, storage-bucket visibility, Security Advisors, preview…