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 odh-llm-d-releasegit 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/odh-llm-d-release)<a href="https://agentmods.dev/skills/opendatahub-io/ai-helpers/odh-llm-d-release"><img src="https://agentmods.dev/badge/skills/opendatahub-io/ai-helpers/odh-llm-d-release/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/odh-llm-d-release"><img src="https://agentmods.dev/badge/skills/opendatahub-io/ai-helpers/odh-llm-d-release.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 | $0.00124 | $0.03231 |
| Opus 5 | $0.00062 | $0.01615 |
| Sonnet 5 | $0.00025 | $0.00646 |
| Haiku 4.5 | $0.00012 | $0.00323 |
Grade A, and why
odh-llm-d-release 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 12d 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.
compatibility: Requires gh (authenticated), yq, jq, curl, git. How it starts
The opening of the file, as written. The whole thing — 292 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ODH llm-d Release Orchestrator
Runs once per ODH release cycle by the release manager. Drives release branch creation, the Konflux onboarder workflow, onboarder-PR validation and merge, Quay image verification, KServe metadata PR, and the tracker comment — for every llm-d component in one shot.
Single input: --version v3.5-ea2. Three values derive from it:
| Use | Value |
|---|---|
| ODH release branch on each component repo | release-v3.5-ea2 |
Konflux onboarder version input + Quay image tag |
v3.5-ea2 |
| GitHub release tag on each component repo | odh-v3.5-ea2 |
Value flow (for --version v3.5-ea2)
This diagram shows where the version goes, what name it takes at each stop,
and which script flag receives it. Three derived values are colored below:
B = release branch, T = image tag (unchanged from VERSION),
R = GitHub release tag.
release manager
└─ /odh-llm-d-release --version v3.5-ea2
orchestrator (SKILL.md)
VERSION = v3.5-ea2
RELEASE_BRANCH= release-v3.5-ea2 (B = release_branch_prefix + VERSION)
IMAGE_TAG = v3.5-ea2 (T = VERSION, unchanged)
RELEASE_TAG = odh-v3.5-ea2 (R = github_release_tag_prefix + VERSION)
│
├── per-component sub-agent (one per component, in parallel)
│ step 1 create-release-branch.sh --branch B → branch release-v3.5-ea2
│ step 2 onboarder-trigger-gha.sh --version T → Konflux builds quay.io/.../<image>:v3.5-ea2
│ step 6 release-image-checker.sh --tag T → verifies quay.io/.../<image>:v3.5-ea2
│ step 7 create-github-release.sh --tag R → draft GH release tagged odh-v3.5-ea2
│
└── KServe metadata sub-agent
open-kserve-metadata-pr.sh --version VERSION → PR title/branch use v3.5-ea2
(the upstream component versions in --updates
are SEPARATE — collected from the release
manager via AskUserQuestion in step 1)
What ships with it
14 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.
- references/components.yaml 6.9 KB
- references/kserve-pr-task.md 2.0 KB
- references/per-component-task.md 6.1 KB
- scripts/create-github-release.sh 2.4 KB runs code
- scripts/create-release-branch.sh 3.0 KB runs code
- scripts/onboarder-pr-finder.sh 4.5 KB runs code
- scripts/onboarder-pr-merge.sh 3.3 KB runs code
- scripts/onboarder-pr-validator.sh 6.6 KB runs code
- scripts/onboarder-trigger-gha.sh 3.6 KB runs code
- scripts/open-kserve-metadata-pr.sh 8.0 KB runs code
- scripts/release-image-checker.sh 2.9 KB runs code
- scripts/tools-checker.sh 1.6 KB runs code
- scripts/tracker-issue-comments.sh 1.6 KB runs code
- scripts/tracker-issue-finder.sh 3.5 KB runs code
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.
- 12d ago First seen · 292 lines · 124 tokens per session scan A b6d89a22dec4
odh-llm-d-release is a skill published in the GitHub repository opendatahub-io/ai-helpers (37 stars, last pushed 5d ago), licensed Apache-2.0. It adds 124 tokens to every session and 3,231 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 2026-08-30.
Other skills, from other repositories
Finishing a Development Branch
Clean branch finalization, squashing commits, and updating changelogs before merging.
agent-release-manager
Agent skill for release-manager - invoke with $agent-release-manager.
agent-release-swarm
Agent skill for release-swarm - invoke with $agent-release-swarm.
agent-github-modes
Agent skill for github-modes - invoke with $agent-github-modes.
github-automation
GitHub workflow automation, PR management, issue tracking, and code review coordination. Integrates with GitHub Actions and repository management. Use when: PR creation, code review, issue management, release automation, workflow setup. Skip when: local-only changes, non-GitHub repositories.
agent-framework-py-release
Use when cutting a Python release for the microsoft/agent-framework monorepo. Triggers on "bump py versions", "cut a python release", "prepare release PR for python", "release py packages", "bump python to X.Y.Z", or similar requests to bump Python package versions and prepare a release PR. Handles all four lifecycle…