Borrowing it
Nothing to install: this file belongs to broadinstitute/viral-ngs. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/broadinstitute/viral-ngs/main/.agents/skills/claude-on-vertex-ci/SKILL.mdgit clone --depth 1 https://github.com/broadinstitute/viral-ngsWrote 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/broadinstitute/viral-ngs/claude-on-vertex-ci)<a href="https://agentmods.dev/skills/broadinstitute/viral-ngs/claude-on-vertex-ci"><img src="https://agentmods.dev/badge/skills/broadinstitute/viral-ngs/claude-on-vertex-ci/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/broadinstitute/viral-ngs/claude-on-vertex-ci"><img src="https://agentmods.dev/badge/skills/broadinstitute/viral-ngs/claude-on-vertex-ci.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Agent Snooping · line 18 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 214 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00000 | $0.02305 |
| Opus 5 | $0.00000 | $0.01153 |
| Sonnet 5 | $0.00000 | $0.00461 |
| Haiku 4.5 | $0.00000 | $0.00231 |
Grade A, and why
claude-on-vertex-ci 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 13d 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 — 221 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude on Vertex AI from GitHub Actions
Reusable infrastructure for invoking Claude (via anthropics/claude-code-action)
on Google Vertex AI from GitHub Actions workflows in this repo. Authentication
is via Workload Identity Federation — no long-lived secrets.
When to Use
Add a new Claude-in-CI use case (PR review, CVE triage, dependency-update analysis, automated docs generation, etc.) when:
- The task is well-suited to an LLM with tool use (reading files, running CLI
commands, calling
gh) - The task fires on a GitHub event (schedule, workflow_dispatch, push, PR)
- You want an issue, PR comment, or artifact as the output
The first use case (and template) is the CVE triage step in
container-scan.yml — see .agents/skills/container-vulns/SKILL.md.
What's Already Provisioned
GCP project: viral-seq-ai
| Resource | Identifier |
|---|---|
| Workload Identity Pool | github-actions-pool (global) |
| OIDC provider | broadinstitute-github |
| Provider attribute condition | assertion.repository_owner == 'broadinstitute' |
| Required APIs | aiplatform.googleapis.com, iamcredentials.googleapis.com |
Service accounts (one per use case):
| SA email | Use case | Workflow |
|---|---|---|
[email protected] |
Weekly CVE triage | .github/workflows/container-scan.yml |
The pool + provider are reusable across use cases. Add a new SA per use case (principle of least privilege; easier to audit and disable individually).
Adding a New Claude-in-CI Use Case
You need GCP IAM Admin on viral-seq-ai for steps 1–3.
1. Create a service account scoped to the use case
gcloud iam service-accounts create <use-case-name> \
--project=viral-seq-ai \
--display-name="<Human-readable name>" \
--description="Used by <workflow-file>.yml to invoke Claude on Vertex AI for <purpose>"
2. Grant minimum roles
Vertex invocation requires both:
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.
- 13d ago First seen · 221 lines · 0 tokens per session scan A b72d42405125
claude-on-vertex-ci is a skill published in the GitHub repository broadinstitute/viral-ngs (197 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,305 tokens. 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 2026-08-30.
Other skills, from other repositories
atmos-hooks
Atmos hooks: lifecycle events, hook kinds, command/store/git/security hooks, step/steps hooks, when: conditions, scoping and overrides, toolchain integration, --skip-hooks, and Atmos Pro/local output.
atmos-modernization
Atmos Modernization: migrate deprecated or legacy Atmos patterns to current names, Native CI, Atmos Pro drift detection, dependencies.components, nametemplate, and declared secrets.
atmos-pro
Atmos Pro setup and workflows: settings.pro, GitHub OIDC, affected and inventory uploads, stack locks, pro commit, workflow dispatch, merge queues, and drift detection.
atmos-sbom
Atmos SBOM provenance: CycloneDX and SPDX generation from vendor and Terraform evidence, coverage diagnostics, NTIA validation, and native CI workflow-artifact publication.
atmos-version
Atmos Version Tracker: version tracks, lock files, managed external dependency versions, atmos version track commands, !version, file managers, update policy, pinning, and CI verification.
atmos-cache
Atmos caching: CI cache configuration and commands, GitHub Actions cache integration, Terraform registry cache mirror/list/prune/stats/trust, and cache modernization guidance.