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 validate-buggit 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/validate-bug)<a href="https://agentmods.dev/skills/openshift-eng/ai-helpers/validate-bug"><img src="https://agentmods.dev/badge/skills/openshift-eng/ai-helpers/validate-bug/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/validate-bug"><img src="https://agentmods.dev/badge/skills/openshift-eng/ai-helpers/validate-bug.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00029 | $0.03800 |
| Opus 5.5 | $0.00012 | $0.01520 |
| Sonnet 5.5 | $0.00006 | $0.00760 |
| Haiku 4.5 | $0.00003 | $0.00380 |
Grade A, and why
validate-bug 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 1mo 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 — 283 lines — stays where its author put it; the contents beside it link to each section on GitHub.
JIRA Bug Validator — Implementation Guide
IMPORTANT FOR AI: This is a procedural skill. Execute each phase in order. Do not skip steps. Do not invent field IDs — use only the documented custom field IDs below.
This skill replicates the validation logic of the jira-lifecycle-plugin (Prow external plugin) that applies the jira/invalid-bug label to PRs in OpenShift repositories.
Custom Field Reference
| Field | Custom Field ID | JQL Name |
|---|---|---|
| Target Version | customfield_10855 |
"Target Version" |
| Release Note Text | customfield_10783 |
— |
| Release Note Type | customfield_10785 |
— |
| Severity | customfield_10840 |
— |
The 7 Validation Checks
The jira-lifecycle-plugin runs these checks in order. A bug must pass ALL checks to get jira/valid-bug.
| # | Check | What it validates |
|---|---|---|
| 1 | Bug is open | Status is not "Closed" |
| 2 | Target version matches branch | Bug's Target Version matches the expected version for the PR's base branch |
| 3 | Bug in valid state | Status is one of: NEW, ASSIGNED, POST |
| 4 | Release notes set | Release note text is non-empty and doesn't match the default template, OR release note type is "Release Note Not Required" |
| 5 | Dependent bug states | Each dependent (linked via "Blocks") is in an allowed state |
| 6 | Dependent bug target versions | Each dependent targets an allowed version |
| 7 | Dependents exist | At least one "Blocks" link exists to a bug in the same project |
Checks 5-7 only apply to release branches (release-4.X), not main/master.
Branch-to-Version Mapping
The plugin config follows a mechanical pattern:
Target version (what the bug on the PR's branch must target):
release-4.X→4.X.z(prefix match —4.X.0also accepted)main/master→5.0.0(prefix match —5.0also accepted). Update whenmaintargets a new major version — checkopenshift/release/core-services/jira-lifecycle-plugin/config.yamlfor the current value.
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.
- 1mo ago First seen · 283 lines · 29 tokens per session scan A e6c6098fa4e9
validate-bug is a skill published in the GitHub repository openshift-eng/ai-helpers (121 stars, last pushed today), licensed Apache-2.0. It adds 29 tokens to every session and 3,800 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 2026-09-05.
Other skills, from other repositories
bug-triage
Re-evaluate open bugs — priority vs severity, assign to sprints, surface systemic trends. Run when the count grows.
systemic-issue-triage
Trigger: new issue, bug report, triage, backlog, issue flood, community report, root cause, dead-end, blocked user. Attack issues by root class, never one-by-one; fixes must shrink the system, not grow it.
triage-issue-reports
Triage Slack issue reports with one thread-only verdict, evidence review, cause-aware routing, tracker dedupe, and fail-closed ticket creation. Use only from the configured Benny triage automation.
triage-issue
Intelligently triage bug reports and error messages by searching for duplicates in Jira and offering to create new issues or add comments to existing ones. When an agent needs to: (1) Triage a bug report or error message, (2) Check if an issue is a duplicate, (3) Find similar past issues, (4) Create a new bug ticket…
moai-lane-watchdog
One lane stall watchdog iteration: measure lane progress on three channels, classify the stall cause, apply the remedy or resolve the judgment through the decision ladder — instead of waiting on a reply — then record the outcome and report. Reads the unified --auto doctrine at…
investigation
Create an investigation ticket + live-doc for sustained root-cause work (retros, bug archaeology, regression hunts).