tapo: Skill for Claude Code

.claude/skills/release-openclaw-skill/SKILL.md

release-openclaw-skill is a skill for Claude Code from mihai-dinculescu/tapo. It costs 47 tokens per session (563 once invoked), scanned A, original, MIT.

A release procedure for publishing a new version of an OpenClaw skill to ClawHub, a package registry for OpenClaw skills.

In plain words
What is it for?
Use it to release the skill in tapo-mcp/openclaw-skill, update its version metadata, review recent changes, commit them, and publish with npx clawhub.
Why use it?
It coordinates version changes, server compatibility pins, changelog information, commits, and publishing steps in one process.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: built for openclaw.

This is mihai-dinculescu/tapo's own configuration. It tells Claude Code how to work on tapo 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 tapo configures →

Reuse

Borrowing it

Nothing to install: this file belongs to mihai-dinculescu/tapo. 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/mihai-dinculescu/tapo/main/.claude/skills/release-openclaw-skill/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/mihai-dinculescu/tapo

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-openclaw-skill

README.md
[![agentmods](https://agentmods.dev/badge/skills/mihai-dinculescu/tapo/release-openclaw-skill/github.svg)](https://agentmods.dev/skills/mihai-dinculescu/tapo/release-openclaw-skill)
Your own site
<a href="https://agentmods.dev/skills/mihai-dinculescu/tapo/release-openclaw-skill"><img src="https://agentmods.dev/badge/skills/mihai-dinculescu/tapo/release-openclaw-skill/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-openclaw-skill

Your own site · 80×15
<a href="https://agentmods.dev/skills/mihai-dinculescu/tapo/release-openclaw-skill"><img src="https://agentmods.dev/badge/skills/mihai-dinculescu/tapo/release-openclaw-skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 47 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 563 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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: 2 findings, 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 MCP Rug Pull · line 3
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
  • medium MCP Rug Pull · line 35
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
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 $0.00047 $0.00563
Opus 5 $0.00023 $0.00282
Sonnet 5 $0.00009 $0.00113
Haiku 4.5 $0.00005 $0.00056

Measured 11d ago against content hash 028e479fad71, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

release-openclaw-skill 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.

.claude/skills/release-openclaw-skill/SKILL.md · 42 lines

What it actually says

Release OpenClaw skill

Release a new version of the OpenClaw skill in tapo-mcp/openclaw-skill/ to ClawHub.

Steps

  1. Determine the new version. Read:

    • The current skill version from the version: field in tapo-mcp/openclaw-skill/SKILL.md frontmatter.
    • The current tapo-mcp server version from tapo-mcp/Cargo.toml.

    Suggest matching the tapo-mcp version. Ask the user to confirm or supply a different version. ClawHub validates version uniqueness on publish (not monotonic ordering) — any semver string that hasn't been published before for this skill is accepted.

  2. Bump the version.

    • If the new version differs from the existing version: in tapo-mcp/openclaw-skill/SKILL.md, update the frontmatter.
    • Update the "v0.X.X or later" minimum-server pin in the Setup section of tapo-mcp/openclaw-skill/SKILL.md to match the current tapo-mcp server version from step 1. This is a separate field from the skill's own version: — the pin tracks the MCP server version, not the skill version.
  3. Determine the changelog summary. Look at recent commits affecting the skill directory:

    git log --oneline -10 -- tapo-mcp/openclaw-skill/
    

    Propose a one-sentence summary of what's new in this release and ask the user to confirm or refine. This text is passed to --changelog at publish time and stored on ClawHub per version.

  4. Commit pending changes. If the version bump (or any other prep) left uncommitted changes, run /commit with message chore(tapo-mcp): release openclaw skill vX.X.X. Skip this step if there is nothing to commit.

  5. Publish. Ask the user for confirmation, then:

    npx clawhub publish tapo-mcp/openclaw-skill \
      --slug tapo \
      --name "Tapo" \
      --version X.X.X \
      --tags "tapo,smart-home,iot,mcporter" \
      --changelog "<summary from step 3>"
    
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. 11d ago First seen · 42 lines · 47 tokens per session scan A 028e479fad71

Subscribe to this mod's changes

release-openclaw-skill is a skill published in the GitHub repository mihai-dinculescu/tapo (799 stars, last pushed yesterday), licensed MIT. It adds 47 tokens to every session and 563 once invoked, about $0.0002 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 2026-08-30.