rome: Skill for Claude Code

.claude/skills/release-rome-image/SKILL.md

release-rome-image is a skill for Claude Code from rome-os/rome. It costs 81 tokens per session (905 once invoked), scanned A, original, MIT.

A release procedure for publishing a new Rome runtime image, which is the packaged environment used to run Rome, to Docker Hub.

In plain words
What is it for?
Checking the main branch, choosing a semantic version tag such as v1.2.3, publishing the image, and confirming that Docker Hub received it.
Why use it?
It reduces the risk of publishing an image from the wrong commit or before continuous integration has passed. It also keeps runtime-image releases separate from desktop and npm package releases.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter.

This is rome-os/rome's own configuration. It tells Claude Code how to work on rome 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 rome configures →

Reuse

Borrowing it

Nothing to install: this file belongs to rome-os/rome. 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/rome-os/rome/main/.claude/skills/release-rome-image/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/rome-os/rome

Made for: Claude Code.

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 release-rome-image

README.md
[![agentmods](https://agentmods.dev/badge/skills/rome-os/rome/release-rome-image/github.svg)](https://agentmods.dev/skills/rome-os/rome/release-rome-image)
Your own site
<a href="https://agentmods.dev/skills/rome-os/rome/release-rome-image"><img src="https://agentmods.dev/badge/skills/rome-os/rome/release-rome-image/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 release-rome-image

Your own site · 80×15
<a href="https://agentmods.dev/skills/rome-os/rome/release-rome-image"><img src="https://agentmods.dev/badge/skills/rome-os/rome/release-rome-image.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 81 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 905 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, 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 Excessive Agency · line 9
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 $0.00081 $0.00905
Opus 5 $0.00041 $0.00452
Sonnet 5 $0.00016 $0.00181
Haiku 4.5 $0.00008 $0.00090

Measured 9d ago against content hash 8d9ca240bf2a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

release-rome-image 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 9d 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.

curl -fsSL "https://hub.docker.com/v2/repositories/yunfanye/rome/tags?page_size=20" | jq -r '.results[].name'
.claude/skills/release-rome-image/SKILL.md · 94 lines

How it starts

The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Release a new Rome image

A pushed vX.Y.Z tag is the release. .github/workflows/docker-publish.yml builds the multi-arch image and publishes it to yunfanye/rome, with no approval gate between the push and Docker Hub. Get explicit confirmation before the push. Verify the published image after it.

The tagging contract covering the semver gate, tag immutability, and latest movement lives in docs/releases.md.

Out of scope

  • Desktop releases use the desktop-v* tag and a separate pipeline.
  • npm package releases belong to release-please. Never create those tags by hand.

1. Preflight

The tag lands on origin/main, and docker-publish.yml runs no CI gate of its own.

  1. Read the commit that the tag will point at.

    git fetch origin --tags && git rev-parse origin/main
    
  2. List the recent CI runs.

    gh run list --branch main --workflow CI --limit 5
    
  3. Find the run for the exact commit from step 1 and confirm the status is success. CI cancels superseded runs, so a rapid series of merges leaves cancelled runs on real commits. If the run failed, was cancelled, or is still running, stop and report it.

  4. Confirm no release is already in flight.

    gh run list --workflow "Docker Hub Publish" --limit 3
    

2. Pick the version

  1. Read the current stable tags.

    git tag --list 'v[0-9]*' | sort -V | tail -5
    
  2. For a patch release, use the helper in step 3. The helper computes the next patch version.

  3. For a minor or major release, take the version from the user.

  4. For a prerelease, use vX.Y.Z-rc.N. A prerelease publishes its own docker tag and never moves latest.

Two constraints decide the number. A published version is immutable, so re-pushing a released version fails and the fix for a bad release is the next version up. latest moves only when the new version is the highest stable version in the registry.

3. Cut the tag

Read the full file on GitHub · 94 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. 9d ago First seen · 94 lines · 81 tokens per session scan A 8d9ca240bf2a

Subscribe to this mod's changes

release-rome-image is a skill published in the GitHub repository rome-os/rome (483 stars, last pushed today), licensed MIT. It adds 81 tokens to every session and 905 once invoked, about $0.0004 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.