OpenShell: Skill for Claude Code

.agents/skills/watch-github-actions/SKILL.md

watch-github-actions is a skill for Claude Code, Codex from NVIDIA/OpenShell. It costs 73 tokens per session (3,190 once invoked), scanned A, original, Apache-2.0.

A guide for checking and following GitHub Actions, the service that runs automated tests, builds, and deployments for a repository.

In plain words
What is it for?
Use it to list workflow runs, watch a build until it finishes, inspect job details, and read logs for failed runs or pull requests.
Why use it?
It removes the need to repeatedly open GitHub and inspect workflow logs by hand when checking whether a change passed.

Skill for Claude CodeCodex ✓ vendor

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents); mentions Codex.

This is NVIDIA/OpenShell's own configuration. It tells Claude Code and Codex how to work on OpenShell itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything OpenShell configures →

About the project

OpenShell is a runtime for autonomous AI agents that executes them in sandboxed environments governed by declarative policies. It is used to restrict agents' access to files, credentials, data, and network resources, and the catalogue includes skills and workflows for operating and contributing to it.

NVIDIA/OpenShell · 21,172 stars · on GitHub · docs.nvidia.com

Reuse

Borrowing it

Nothing to install: this file belongs to NVIDIA/OpenShell. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/NVIDIA/OpenShell/main/.agents/skills/watch-github-actions/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/NVIDIA/OpenShell

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for watch-github-actions

README.md
[![agentmods](https://agentmods.dev/badge/skills/nvidia/openshell/watch-github-actions/github.svg)](https://agentmods.dev/skills/nvidia/openshell/watch-github-actions)
Your own site
<a href="https://agentmods.dev/skills/nvidia/openshell/watch-github-actions"><img src="https://agentmods.dev/badge/skills/nvidia/openshell/watch-github-actions/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.

agentmods 80×15 button for watch-github-actions

Your own site · 80×15
<a href="https://agentmods.dev/skills/nvidia/openshell/watch-github-actions"><img src="https://agentmods.dev/badge/skills/nvidia/openshell/watch-github-actions.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 73 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,190 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • Snyk pass 7 Sept 2026
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00073 $0.03190
Opus 5.5 $0.00029 $0.01276
Sonnet 5.5 $0.00015 $0.00638
Haiku 4.5 $0.00007 $0.00319

Measured yesterday against content hash f2f2a46def95, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

watch-github-actions 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.

.agents/skills/watch-github-actions/SKILL.md · 347 lines

How it starts

The opening of the file, as written. The whole thing — 347 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Watch GitHub Actions

Monitor GitHub Actions workflow runs using the gh CLI.

Prerequisites

  • The gh CLI must be authenticated (gh auth status)
  • You must be in a git repository with a GitHub remote

Quick Status Check

List recent workflow runs for the current branch:

gh run list --branch "$(git branch --show-current)"

List all recent runs:

gh run list

Watch a Run in Real Time

Watch a workflow run until it completes:

gh run watch

Watch a specific run:

gh run watch <run-id>

This will continuously update the status until the run finishes (success, failure, or cancelled).

View Run Details

View a specific run with job details:

gh run view <run-id>

View with full log output:

gh run view <run-id> --log

View a failed job's log:

gh run view <run-id> --log-failed

Check Runs for a Specific Branch

Current branch:

gh run list --branch "$(git branch --show-current)"

Specific branch:

gh run list --branch main
gh run list --branch feature-branch

Check Runs for a PR

List workflow runs associated with a PR:

# Get the head branch of the PR, then list runs
BRANCH=$(gh pr view <pr-number> --json headRefName --jq '.headRefName')
gh run list --branch "$BRANCH"

Or view the checks directly on the PR:

gh pr checks <pr-number>

List Recent Runs

List runs for the current project:

gh run list

Filter by status:

gh run list --status failure
gh run list --status success
gh run list --status in_progress

Filter by workflow:

gh run list --workflow "CI"

JSON output for scripting:

gh run list --json databaseId,status,headBranch,url --jq '.[] | {id: .databaseId, status: .status, branch: .headBranch, url: .url}'

View Job Logs

For Kubernetes app-listener E2E failures during kind setup, inspect the uploaded results/app-listener/cni-setup/ evidence. It includes node and Calico pod descriptions, events, and current/previous container logs. A CNI rollout timeout occurs before the listener tests run; use these diagnostics to distinguish image pulls, init failures, and readiness failures.

Read the full file on GitHub · 347 lines

Changes

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.

  1. yesterday Changed · +7 lines f2f2a46def95
  2. 2d ago Changed f7df78b4375f
  3. 3d ago Changed · +6 lines 9c88801a5ae1
  4. 6d ago Changed · +7 lines 687e8ff90032
  5. 8d ago Changed c4944bc34c14
  6. 9d ago Changed · +2 lines ebe71523511a
  7. 10d ago Changed · +7 lines 2438d293ca2c
  8. 17d ago Changed · +4 lines 9b250601fc06
  9. 18d ago Changed · +20 lines 18ed78decdf6
  10. 22d ago First seen · 294 lines · 73 tokens per session scan A 55790c170c9c

Subscribe to this mod's changes

watch-github-actions is a skill published in the GitHub repository NVIDIA/OpenShell (21,172 stars, last pushed yesterday), licensed Apache-2.0. It adds 73 tokens to every session and 3,190 once invoked, about $0.0003 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 2026-08-30.

Related

watch-github-actions compared with skills from other repositories

watch-github-actions next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
watch-github-actionsNVIDIA/OpenShellSkill21kyesterdayApache-2.0A73Claude Code, Codex
chinese-git-workflowjnMetaCode/superpowers-zhSkill8.5k11d agoMITA69Claude Code
atmos-profilescloudposse/atmosSkill1.4ktodayApache-2.0A35Claude Code
webhook-managementhoangsonww/Claude-Code-Agent-MonitorSkill1.1kyesterdayMITA56Claude Code, Codex
monorepo-managementwshobson/agentsSkill42kyesterdayMITC54Claude Code
managing-github-actions-secretsPostHog/posthog-fossSkill728todayMITA67Claude Code, Codex
postman-newman-automationLambdaTest/agent-skillsSkill390yesterdayMITA156Claude Code, Codex