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 analyze-cvegit 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/analyze-cve)<a href="https://agentmods.dev/skills/openshift-eng/ai-helpers/analyze-cve"><img src="https://agentmods.dev/badge/skills/openshift-eng/ai-helpers/analyze-cve/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/analyze-cve"><img src="https://agentmods.dev/badge/skills/openshift-eng/ai-helpers/analyze-cve.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 | $0.00213 | $0.02050 |
| Opus 5.5 | $0.00085 | $0.00820 |
| Sonnet 5.5 | $0.00043 | $0.00410 |
| Haiku 4.5 | $0.00021 | $0.00205 |
Grade B, and why
analyze-cve scanned grade B with 1 finding 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 23d 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
- `graphviz` for visual call graph generation (`brew install graphviz` or `sudo apt-get install graphviz`) How it starts
The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
analyze-cve
Performs comprehensive security vulnerability analysis for Go projects. Given a CVE identifier — supplied directly, or resolved from a Jira ticket — it resolves and clones the affected repository, gathers vulnerability intelligence, analyzes the codebase for impact, generates a risk report, optionally applies fixes, and optionally opens a GitHub pull request after a verified fix.
Explicit invocation uses the following argument syntax:
/compliance:analyze-cve <CVE-ID> [--repo=<url-or-component>] [--algo=vta|rta|cha|static] [--auto-approve=yes|no]
/compliance:analyze-cve --jira=<PROJ-NNN> [--repo=...] [--algo=...] [--auto-approve=yes|no]
/compliance:analyze-cve --jql="<JQL query>" [--repo=...] [--algo=...] [--auto-approve=yes|no]
Repository resolution works in four ways, in priority order: (1) an explicit --repo= (full URL or short image/component name), (2) in direct-CVE mode only, exactly one pre-cloned repository already present in this workspace's repos/ directory when --repo= was not passed — in Jira/JQL mode that sole candidate is instead validated against the ticket's resolved image/branch before reuse, never assumed, (3) an image name extracted from a Jira ticket's summary/labels/custom fields when --jira=/--jql= was used, or (4) an interactive prompt for the repository URL or image name. See Phase 0.7 in the implementation reference for the full resolution and cloning logic.
Designed for both interactive use and headless execution (e.g. claude --print "/compliance:analyze-cve --jira=OCPBUGS-12345 --auto-approve=yes") for scheduled/periodic runs.
Arguments
Exactly one of the following input modes is required:
<CVE-ID>— Direct CVE identifier (format:CVE-YYYY-NNNNN, case-insensitive). Use when you already know the CVE.--jira=PROJ-NNN— Jira ticket key (e.g.--jira=OCPBUGS-12345). This skill fetches the ticket and extracts the CVE ID, affected image name, and enrichment context (CVSS, CWE, priority, workarounds) from it.--jql="..."— JQL query (e.g.--jql="project = OCPBUGS AND labels = needs-cve-analysis"). Fetches a batch of matching issues, filters out any already labeledai-cve-analyzed, and processes exactly one of the remainder per run (see Phase 0.3). Re-running the same JQL periodically works through the queue over multiple invocations.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 23d ago First seen · 115 lines · 213 tokens per session scan B 8266cf36dd83
analyze-cve is a skill published in the GitHub repository openshift-eng/ai-helpers (121 stars, last pushed today), licensed Apache-2.0. It adds 213 tokens to every session and 2,050 once invoked, about $0.0009 per session on Opus 5.5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-29.
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…