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 foundationsgit 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/foundations)<a href="https://agentmods.dev/skills/openshift-eng/ai-helpers/foundations"><img src="https://agentmods.dev/badge/skills/openshift-eng/ai-helpers/foundations/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/foundations"><img src="https://agentmods.dev/badge/skills/openshift-eng/ai-helpers/foundations.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 | $0.00030 | $0.01132 |
| Opus 5.5 | $0.00012 | $0.00453 |
| Sonnet 5.5 | $0.00006 | $0.00226 |
| Haiku 4.5 | $0.00003 | $0.00113 |
Grade A, and why
foundations 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
BigQuery CI Data Foundations
Shared foundations for all CI data BigQuery skills. Every skill in this plugin follows these protocols.
Prerequisites
bqCLI installed and authenticated (gcloud auth login)- BigQuery read access to the relevant projects
Projects and Datasets
| Project | Dataset | Purpose |
|---|---|---|
openshift-gce-devel |
ci_analysis_us |
Primary engineering CI data (jobs, junit, variants, labels) |
openshift-gce-devel |
ci_analysis_qe |
QE CI data (same schema as ci_analysis_us, smaller) |
openshift-ci-data-analysis |
ci_data_autodl |
Auto-collected data from test runs (disruption, CPU, audit logs, risk analysis, etc.) |
Always pass --project_id=<project> explicitly to all bq commands.
Cost Safety Protocol
Non-negotiable. Every query follows this flow:
- Show the query to the user before doing anything
- Dry-run to get bytes scanned:
bq query --project_id=<project> --dry_run --use_legacy_sql=false '<query>' - Calculate cost:
bytes / 10^12 * $6.25(on-demand pricing) - If cost > $1.00: show estimated cost and bytes, ask user to confirm
- If cost <= $1.00: proceed, report cost in results
- Never loop or repeat queries. Run once, cache locally, analyze from cached data.
Partition and Clustering Filters
When a table is partitioned, every query MUST include a filter on the partition column to avoid full-table scans. Use tight date ranges. Not all tables are partitioned (e.g. job_variants is small and unpartitioned).
When a table is clustered, filter on the clustering column too for major cost reduction.
Caching Results Locally
After executing a query, save results to .work/bigquery-ci-data/ as JSON or CSV. Name files descriptively.
Always query fresh — never skip a query because a cached file with a similar name already exists. CI data changes continuously; stale cache files produce misleading results. Use cached files only for follow-up analysis of the same data within the same conversation, and re-query if more than 4 hours have passed since the cache was written.
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 · 102 lines · 30 tokens per session scan A 9c25fa8789da
foundations is a skill published in the GitHub repository openshift-eng/ai-helpers (121 stars, last pushed today), licensed Apache-2.0. It adds 30 tokens to every session and 1,132 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 skills, from other repositories
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…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
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.
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…