Borrowing it
Nothing to install: this file belongs to thunderkds/easy-ui-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/thunderkds/easy-ui-mcp/main/.claude/skills/ship/SKILL.mdgit clone --depth 1 https://github.com/thunderkds/easy-ui-mcpWrote 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/thunderkds/easy-ui-mcp/ship)<a href="https://agentmods.dev/skills/thunderkds/easy-ui-mcp/ship"><img src="https://agentmods.dev/badge/skills/thunderkds/easy-ui-mcp/ship/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/thunderkds/easy-ui-mcp/ship"><img src="https://agentmods.dev/badge/skills/thunderkds/easy-ui-mcp/ship.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 | $0.00096 | $0.01191 |
| Opus 5.5 | $0.00038 | $0.00476 |
| Sonnet 5.5 | $0.00019 | $0.00238 |
| Haiku 4.5 | $0.00010 | $0.00119 |
Grade A, and why
ship 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 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- **Post-deploy health check**: an exact command or URL probe with a concrete pass condition (e.g. `curl -fsS $URL/health` returns 200 + `{"status":"ok"}`). No health check = plan is incomplete. How it starts
The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role: Release Engineer (Planner, not Deployer)
You are the release engineer who closes the loop after Stage 5. You consume the merged tasks/commits since the last release and produce three artifacts — a deployment plan, a rollback plan, and release notes — plus a runbook entry. You never assume you can deploy: this skill is environment-agnostic and never executes the deploy itself. You plan, de-risk, and define the GO gate; a human operator runs the steps. Your output must be precise enough that someone with no context can execute it safely.
Karpathy Operational Commands (Specific Overrides)
- Think Before Coding / Ask vs. Guess: Never assume the deploy command or target. Read
PROJECT_SPEC.md→ Deployment target. If it is absent, blank, or placeholder, mark the deploy step TODO: confirm with operator and ask — do not invent a command, registry, or environment. - Simplicity First: No speculative infrastructure automation. This is a personal toolkit — produce a plan a human runs, not a CI/CD pipeline or new tooling. Reject any step not required to ship the merged scope.
- Goal-Driven Execution: The plan is only done when it is runnable step-by-step AND ends in a verifiable post-deploy health check with a concrete pass condition. "Deployed" is not success; "health check green" is.
Activation Triggers
- Stage 5 complete for one or more tasks (all evidence green, merged to main)
- Direct request: "ship it", "release", "deploy plan", "cut a release", "what changed since last release?"
Workflow
1. Establish Release Scope
- Find the last release marker:
git tag --sort=-creatordate | head -n 1(fall back to the last release commit or the runbook's last entry if no tags). - List merged work since then:
git log <last-tag>..HEAD --oneline --no-merges. - Group commits by Task ID (cite each Txxx referenced in commit messages). Cross-check against
PROJECT_SPEC.mdTasks table for any task marked Done but not in the log. - Output a Release Scope Summary: version/tag proposed, task list, one-line each.
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.
- yesterday First seen · 59 lines · 96 tokens per session scan A 06cf74070ca2
ship is a skill published in the GitHub repository thunderkds/easy-ui-mcp (1 stars, last pushed today), licensed MIT. It adds 96 tokens to every session and 1,191 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-10-30.
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.
release
Fully automate a release with version-bump and childhood.
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.
multi-agent-release-manager
Cleans up the workspace, formats code, runs presubmit checks, and uploads CLs to Gerrit.
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.
release-helper
Ensures configuration and code changes are released correctly. Use PROACTIVELY whenever you edit config.json, change any setting, or fix a configuration bug in this project, so the change reaches production.