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 cohere-ai/vllm-skills --skill auto-rebasegit clone --depth 1 https://github.com/cohere-ai/vllm-skillsWrote 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/cohere-ai/vllm-skills/auto-rebase)<a href="https://agentmods.dev/skills/cohere-ai/vllm-skills/auto-rebase"><img src="https://agentmods.dev/badge/skills/cohere-ai/vllm-skills/auto-rebase/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/cohere-ai/vllm-skills/auto-rebase"><img src="https://agentmods.dev/badge/skills/cohere-ai/vllm-skills/auto-rebase.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 | $0.00068 | $0.01121 |
| Opus 5 | $0.00034 | $0.00561 |
| Sonnet 5 | $0.00014 | $0.00224 |
| Haiku 4.5 | $0.00007 | $0.00112 |
Grade A, and why
auto-rebase 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 11d 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 — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Auto Rebase
Check whether a newer upstream vllm release exists and, if so, rebase the
current fork branch onto it automatically. Uses the same notation as
rebase-assistant: v1/v2 for upstream tags, b1/b2 for the
branch before/after rebase.
Step 0: Prerequisites
Verify required tools are installed and authenticated before starting.
# gh CLI — needed to query upstream releases
gh auth status 2>/dev/null || echo "ERROR: gh not authenticated"
If gh auth status fails, prompt the user to run gh auth login and wait
for confirmation before proceeding. The git-tag fallback in Step 2 works
without gh, but release metadata (pre-release flags, release notes) is
only available through the GitHub API.
Step 1: Detect Current Upstream Base
The current branch is b1. Use the detect-upstream-base skill to
identify v1 — the upstream tag that b1 is based on. See
detect-upstream-base.
Confirm v1 with the user before proceeding.
Step 2: Check for New Upstream Releases
Fetch the latest tags and compare against v1.
git fetch upstream --tags
List upstream release tags newer than v1:
git tag --list "v*" --sort=-version:refname \
| while read -r tag; do
git merge-base --is-ancestor "upstream/$V1" "$tag" 2>/dev/null \
&& [ "$tag" != "$V1" ] \
&& echo "$tag"
done
Alternatively, use gh for a cleaner check:
gh release list --repo vllm-project/vllm --limit 10 \
| awk '{print $1}'
Pick the latest stable release as the candidate v2. Skip pre-release or release-candidate tags unless the user opts in.
Present to user:
- Current base: v1
- Latest upstream release: v2
- Release notes link:
https://github.com/vllm-project/vllm/releases/tag/$V2
If v1 == v2 (already up to date), report that and stop.
Ask: "A new release $V2 is available. Proceed with rebase?"
Wait for confirmation before proceeding.
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.
- 11d ago First seen · 140 lines · 68 tokens per session scan A e27b0365492c
auto-rebase is a skill published in the GitHub repository cohere-ai/vllm-skills (6 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 68 tokens to every session and 1,121 once invoked, about $0.0003 per session on Opus 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 2026-08-31.
Other skills, from other repositories
release-announcement
Write a release announcement — changelog, blog post, in-app note, or social post — that leads with user impact, names the audience, and includes upgrade/migration steps without filler.
multi-agent-release-manager
Cleans up the workspace, formats code, runs presubmit checks, and uploads CLs to Gerrit.
release-notes
Generate user-facing release notes from tickets, PRDs, or changelogs. Creates clear, engaging summaries organized by category (new features, improvements, fixes). Use when writing release notes, creating changelogs, announcing product updates, or summarizing what shipped.
pack-submit
Package one of this agent's own skills as a standalone community pack and submit it to the aeon registry as a PR.
updater_guide
Guidance for checking for and installing Row-Bot updates.
nvca-chart-release
Release NVCA Operator chart changes from the native monorepo source to the vendored Helm chart. Use when updating the vendored NVCA Operator chart, changing NVCA image refs, publishing helm-nvca-operator, or validating the chart against a self-managed control plane.