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 jobs-and-testsgit 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/jobs-and-tests)<a href="https://agentmods.dev/skills/openshift-eng/ai-helpers/jobs-and-tests"><img src="https://agentmods.dev/badge/skills/openshift-eng/ai-helpers/jobs-and-tests/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/jobs-and-tests"><img src="https://agentmods.dev/badge/skills/openshift-eng/ai-helpers/jobs-and-tests.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 | $0.00038 | $0.02426 |
| Opus 5.5 | $0.00015 | $0.00970 |
| Sonnet 5.5 | $0.00008 | $0.00485 |
| Haiku 4.5 | $0.00004 | $0.00243 |
Grade A, and why
jobs-and-tests 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 — 214 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Jobs and Tests
Query and analyze prow job runs and junit test results stored in openshift-gce-devel.ci_analysis_us. This is the primary dataset for investigating test failures, flakes, regressions, and job pass rates.
Follow the foundations skill for cost safety, caching, and execution workflow.
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)
Tables
ci_analysis_us.junit
Junit test results. Massive table. Partitioned by DAY on modified_time. Clustered on release.
| Column | Type | Notes |
|---|---|---|
| prowjob_build_id | STRING | Join key to jobs table |
| file_path | STRING | Artifact path of the junit XML |
| test_name | STRING | Full test name |
| testsuite | STRING | Test suite name |
| success_val | INTEGER | 1 = pass, 0 = fail |
| success | BOOLEAN | Pass/fail |
| skipped | BOOLEAN | Whether test was skipped |
| flake_count | INTEGER | >0 means this row is part of a flake |
| modified_time | DATETIME | Partition column — always filter on this |
| release | STRING | OCP release (e.g. "4.22", "5.0"). Clustering column — always filter for ~60-70% cost reduction |
| branch | STRING | LEGACY — do not use. Use release instead |
| prowjob_name | STRING | Name of the prow job run |
| duration_ms | INTEGER | Test execution time |
| test_id | STRING | Stable test identifier |
| failure_message | STRING | Failure message from junit XML |
| failure_content | STRING | Failure body from junit XML |
| start_time | DATETIME | Test start time |
| end_time | DATETIME | Test end time |
| platform | STRING | LEGACY — do not use for filtering |
| arch | STRING | LEGACY — do not use for filtering |
| network | STRING | LEGACY — do not use for filtering |
| upgrade | STRING | LEGACY — do not use for filtering |
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 · +1 lines 2b4267a2fb86
- 16d ago First seen · 213 lines · 38 tokens per session scan A 55bd1d05df90
jobs-and-tests is a skill published in the GitHub repository openshift-eng/ai-helpers (121 stars, last pushed today), licensed Apache-2.0. It adds 38 tokens to every session and 2,426 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
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.