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 openshift-eng/ai-helpers --skill autodlgit 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/skills/openshift-eng/ai-helpers/autodl)<a href="https://agentmods.dev/skills/openshift-eng/ai-helpers/autodl"><img src="https://agentmods.dev/badge/skills/openshift-eng/ai-helpers/autodl/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/openshift-eng/ai-helpers/autodl"><img src="https://agentmods.dev/badge/skills/openshift-eng/ai-helpers/autodl.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 | $0.00044 | $0.02957 |
| Opus 5.5 | $0.00018 | $0.01183 |
| Sonnet 5.5 | $0.00009 | $0.00591 |
| Haiku 4.5 | $0.00004 | $0.00296 |
Grade A, and why
autodl 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 yesterday.
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 — 332 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Autodl Tables
Query data automatically collected during OpenShift CI test runs, stored in openshift-ci-data-analysis.ci_data_autodl. This data is generated by monitor tests and analysis code in openshift/origin and uploaded by the ci-data-loader after each job run.
Follow the foundations skill for cost safety, caching, and execution workflow.
When to Use This Skill
- Investigating risk analysis verdicts for job runs
- Analyzing test retry behavior and flake patterns
- Examining kube-apiserver audit log patterns (latency, request counts, watch storms)
- Tracking operator state transitions during test runs
- Correlating CPU usage with test failures
- Understanding DNS disruption during tests
- Checking cluster instance types and configuration
Common Columns
All autodl tables include three columns added by the ci-data-loader:
| Column | Type | Notes |
|---|---|---|
| JobRunName | STRING | Prow job run identifier — join key to other datasets |
| PartitionTime | TIMESTAMP | Partition column — always filter on this |
| Source | STRING | Data source identifier |
The JobRunName can be used to correlate autodl data with job runs in openshift-gce-devel.ci_analysis_us.jobs (match against prowjob_build_id or extract from prowjob_url).
Following up in a run's artifacts
Autodl rows are summaries. For the raw data behind them (Prometheus snapshots, audit logs, intervals), go to the run's artifacts:
- Look up
prowjob_urlandgcs_bucketin thejobstable. Do not guess the bucket name. - CI artifacts are in the public
test-platform-results-publicbucket and can be read anonymously over HTTPS. Take the run's path fromprowjob_url(everything after the bucket name) rather than building it: periodics and postsubmits uselogs/<job>/<build_id>, presubmits usepr-logs/pull/<org>_<repo>/<pr>/<job>/<build_id>. Read files withhttps://storage.googleapis.com/test-platform-results-public/<path>/...and browse directories withhttps://gcs.ci.openshift.org/gcs/test-platform-results-public/<path>/. - The
test-platform-resultsbucket (no-publicsuffix) is private. Don't use it, and don't change the user's gcloud account or rungcloud auth loginto reach artifacts. - See the
ci:prow-job-analysisskill'sreferences/artifacts.mdfor the artifact layout.
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.
- yesterday Changed · +9 lines f6ce13af91d9
- 16d ago First seen · 323 lines · 44 tokens per session scan A 23e90f5c4a13
autodl is a skill published in the GitHub repository openshift-eng/ai-helpers (121 stars, last pushed today), licensed Apache-2.0. It adds 44 tokens to every session and 2,957 once invoked, about $0.0002 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 skills, from other repositories
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
deck-retro
Run a fully local agent-deck retrospective over the user's own transcripts, Recall index and logs. Use when a user wants to find recurring failures or take their own finding from investigation through synthetic reproduction, a user-filed issue, a test-first fix and contributor PR handoff. Also use for weekly usage…
incident-response-incident-response
Coordinate production incident triage, mitigation, investigation, recovery, and follow-up. Use when responding to outages or other incidents that require structured operational coordination.
cwv-optimizer
Diagnose and fix Core Web Vitals issues on AEM Edge Delivery Services pages. Goes deeper than generic CWV advice by understanding EDS-specific performance patterns including the 100KB LCP budget, E-L-D loading phases, block rendering behavior, and third-party script impact. Produces specific fixes for LCP, CLS, and…