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 opendatahub-io/ai-helpers --skill konflux-sandbox-onboardinggit clone --depth 1 https://github.com/opendatahub-io/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/opendatahub-io/ai-helpers/konflux-sandbox-onboarding)<a href="https://agentmods.dev/skills/opendatahub-io/ai-helpers/konflux-sandbox-onboarding"><img src="https://agentmods.dev/badge/skills/opendatahub-io/ai-helpers/konflux-sandbox-onboarding/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/opendatahub-io/ai-helpers/konflux-sandbox-onboarding"><img src="https://agentmods.dev/badge/skills/opendatahub-io/ai-helpers/konflux-sandbox-onboarding.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 | $0.00061 | $0.01412 |
| Opus 5.5 | $0.00024 | $0.00565 |
| Sonnet 5.5 | $0.00012 | $0.00282 |
| Haiku 4.5 | $0.00006 | $0.00141 |
Grade A, and why
konflux-sandbox-onboarding 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 — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Konflux Sandbox Onboarding
Guide the engineer from access verification to one successful build while keeping every user- and project-specific value configurable.
Constraints
- Work only in the AIPCC sandbox tenant on Konflux staging.
- Use sandbox-scoped repositories, credentials, and image destinations; if a supplied target is production, stop and ask for a non-production substitute.
- Never invent or retain an engineer's identity, GitHub handle, organization, repository, branch, local path, Application name, or Component name.
- Discover values from authenticated tools when practical; otherwise ask for only the missing values. Confirm inferred values before mutations.
- Never request, print, persist, or quote access tokens, kubeconfig contents, secret values, or GitHub App private data.
- Use Konflux Staging (
konflux-staging), not Konflux Staging Internal. - Use the AIPCC sandbox Applications page for the UI workflow. Do not substitute a production console or guess a new endpoint if this staging URL is unavailable.
- Treat
konflux-release-dataas the source of truth for tenant provisioning and RBAC. Do not apply tenant or RoleBinding manifests directly to the cluster. - Scope GitHub App installation to selected repositories. Do not propose organization-wide installation unless the engineer explicitly requests it and has authority to approve it.
- Preserve existing repository files. Before copying the dummy project, inspect the target and stop if a file would be overwritten.
- Treat installing an App, editing or pushing
konflux-release-data, opening or merging a GitLab change, creating cluster resources, pushing a branch, opening or merging a pull request, triggering a build, and deleting resources as mutations. Confirm the intended target immediately before performing them.
Workflow routing
- Resolve the directory containing this
SKILL.mdasSKILL_DIRand use its resources through paths derived from that directory. - Determine whether the engineer needs access setup, project onboarding, pipeline execution, troubleshooting, or the full workflow. Resume at their current phase instead of repeating completed steps.
- Read references/access.md when access is not yet verified. If the tenant or maintainer binding is missing, use its release-data change workflow or produce an access request before attempting project creation. Proceed only after the effective permission checks pass.
What ships with it
7 files 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.
- 1mo ago First seen · 114 lines · 61 tokens per session scan A 1dafcb598133
konflux-sandbox-onboarding is a skill published in the GitHub repository opendatahub-io/ai-helpers (39 stars, last pushed 3d ago), licensed Apache-2.0. It adds 61 tokens to every session and 1,412 once invoked, about $0.0002 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 2026-09-17.
Other skills, from other repositories
turborepo-caching
Configure Turborepo for efficient monorepo builds with local and remote caching. Use when setting up Turborepo, optimizing build pipelines, or implementing distributed caching.
agent-github-modes
Agent skill for github-modes - invoke with $agent-github-modes.
secrets-management
Implement secure secrets management for CI/CD pipelines using Vault, AWS Secrets Manager, or native platform solutions. Use when handling sensitive credentials, rotating secrets, or securing CI/CD environments.
deployment-pipeline-design
Design multi-stage CI/CD pipelines with approval gates, security checks, and deployment orchestration. Use this skill when designing zero-downtime deployment pipelines, implementing canary rollout strategies, setting up multi-environment promotion workflows, or debugging failed deployment gates in CI/CD.
github-actions-templates
Create production-ready GitHub Actions workflows for automated testing, building, and deploying applications. Use when setting up CI/CD with GitHub Actions, automating development workflows, or creating reusable workflow templates.
gitlab-ci-patterns
Build GitLab CI/CD pipelines with multi-stage workflows, caching, and distributed runners for scalable automation. Use when implementing GitLab CI/CD, optimizing pipeline performance, or setting up automated testing and deployment.