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 triage-fixed-cvesgit 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/triage-fixed-cves)<a href="https://agentmods.dev/skills/openshift-eng/ai-helpers/triage-fixed-cves"><img src="https://agentmods.dev/badge/skills/openshift-eng/ai-helpers/triage-fixed-cves/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/triage-fixed-cves"><img src="https://agentmods.dev/badge/skills/openshift-eng/ai-helpers/triage-fixed-cves.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 | $0.00127 | $0.03576 |
| Opus 5 | $0.00063 | $0.01788 |
| Sonnet 5 | $0.00025 | $0.00715 |
| Haiku 4.5 | $0.00013 | $0.00358 |
Grade A, and why
triage-fixed-cves scanned grade A 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 4d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s "https://vuln.go.dev/ID/<GO_ID>.json" How it starts
The opening of the file, as written. The whole thing — 352 lines — stays where its author put it; the contents beside it link to each section on GitHub.
triage-fixed-cves
Analyze an OpenShift release image to determine which Go standard library CVE Jira tickets have been addressed by the Go version used to build each component. Produces a per-CVE, per-component cross-reference report.
The user provides a release image pullspec (e.g.
quay.io/openshift-release-dev/ocp-release:4.17.0-x86_64).
Execute every step below in order. Do not skip steps.
Step 1 — Extract component images from the release
oc adm release info <RELEASE_IMAGE> --output=json
Parse the JSON output to get the list of component image references. Each
entry in .references.spec.tags[] provides a name (component name) and
.from.name (image pullspec).
Each tag also carries .annotations metadata. Extract the
io.openshift.build.source-location annotation — this is the canonical
source GitHub repository URL for that component (e.g.
https://github.com/openshift/cluster-version-operator). Also extract
io.openshift.build.commit.id which gives the exact source commit SHA
the image was built from. Record both for every component — they are used
in Steps 2 and 4.
Auth failure: If oc adm release info fails due to an authentication
error, STOP immediately. Report the auth failure to the user and do not
proceed. Do not attempt to locate pull secrets, probe environment variables,
or try alternative credential paths — the RWS pod's registry proxy handles
authentication transparently, so an auth failure means the proxy does not
have credentials for this registry and manual intervention is required.
Collect the full list of (component_name, image_pullspec, source_repo, source_commit) tuples before proceeding.
Step 2 — Identify the built binary per component via Dockerfile
For each component, identify exactly which binary is built and where it lands in the final image by looking up the component's Dockerfile. Do NOT scan the entire image for all ELF binaries.
CI images (most components)
Look up the ci-operator config at
github.com/openshift/release/ci-operator/config/openshift/<repo>/.
Match the correct config file for the release branch and build variant (e.g.
openshift-cluster-version-operator-release-4.17.yaml). The config's
images.items[] specifies the dockerfile_path for each image. Fetch that
Dockerfile from the component's own repository at the exact source commit
recorded in io.openshift.build.commit.id from Step 1 — do not use
tree/main or the branch tip, as the release image may have been built from
an older revision.
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.
- 4d ago First seen · 352 lines · 127 tokens per session scan A 269c27810e92
triage-fixed-cves is a skill published in the GitHub repository openshift-eng/ai-helpers (116 stars, last pushed yesterday), licensed Apache-2.0. It adds 127 tokens to every session and 3,576 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-05.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…