Borrowing it
Nothing to install: this file belongs to richardkmichael/mcp-tailwindplus. 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/richardkmichael/mcp-tailwindplus/development/.claude/skills/release/SKILL.mdgit clone --depth 1 https://github.com/richardkmichael/mcp-tailwindplusWrote 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/richardkmichael/mcp-tailwindplus/release)<a href="https://agentmods.dev/skills/richardkmichael/mcp-tailwindplus/release"><img src="https://agentmods.dev/badge/skills/richardkmichael/mcp-tailwindplus/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/richardkmichael/mcp-tailwindplus/release"><img src="https://agentmods.dev/badge/skills/richardkmichael/mcp-tailwindplus/release.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 | $0.00087 | $0.02560 |
| Opus 5.5 | $0.00035 | $0.01024 |
| Sonnet 5.5 | $0.00017 | $0.00512 |
| Haiku 4.5 | $0.00009 | $0.00256 |
Grade A, and why
release 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 2d 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 — 219 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Release Skill
Invocation
/release rc: published pre-release (RC)/release: published final release/release draft rc: draft pre-release (RC)/release draft: draft final release
Conventions
- Versions follow PEP 440, Python's version specification:
X.Y.Zfor a final release,X.Y.ZrcNfor a release candidate. - A tag is
vfollowed by the version inpyproject.toml:vX.Y.ZorvX.Y.ZrcN. - Annotated tags only:
git tag -a <tag> -m "<tag>" - Before tagging, bump
pyproject.tomlto the version being released and syncuv.lock, in a commit of its own. - The
latesttag tracks the newest final release: its own annotated tag, overwritten each final release, so its tagger and date record when it moved. Only final releases move it; RCs never do. - Version bump commits are titled
Bump version to <version>, as in the history.
Every build reports its own version: the server reads it from package metadata and gives it to MCP
clients when they connect. An RC whose pyproject.toml still held the previous release would be
indistinguishable from it.
Preconditions
Both workflows tag a commit and publish it, so the branch must be in sync with the remote before anything is tagged. Check first, and abort if it is not:
git fetch origin
git rev-list --left-right --count origin/development...HEAD # expect: 0 0
Anything other than 0 0 aborts the release. Commits ahead of the remote mean tagging history
nobody else has; commits behind mean releasing without work already on the remote. Say which side
is out of sync and stop. Pushing or pulling on the user's behalf is their call, not the skill's.
The tests must pass on the commit being released. CI runs them on Linux, macOS and Windows for
every push to development; check the latest run for HEAD before going further:
gh run list --branch development --commit "$(git rev-parse HEAD)" --json conclusion,status
A run that failed aborts the release. A run still in progress means waiting for it. Say which, and stop until it has passed.
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.
- 2d ago First seen · 219 lines · 87 tokens per session scan A ffb8931b585c
release is a skill published in the GitHub repository richardkmichael/mcp-tailwindplus (43 stars, last pushed 3d ago), licensed MIT. It adds 87 tokens to every session and 2,560 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-11-07.
release compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| releaserichardkmichael/mcp-tailwindplus | Skill | 43 | 3d ago | MIT | A | 87 | Claude Code |
| release-announcementpaperclipai/paperclip | Skill | 113k | today | MIT | A | 42 | Claude Code, Codex |
| releasethedotmack/claude-mem | Skill | 115k | today | Apache-2.0 | A | 13 | Claude Code |
| release-notesphuryn/pm-skills | Skill | 28k | yesterday | MIT | A | 57 | Claude Code |
| multi-agent-release-managerchromium/chromium | Skill | 25k | today | BSD-3-Clause | A | 27 | Claude Code, Codex |
| pack-submitaeonfun/aeon | Skill | 790 | today | MIT | A | 27 | Claude Code, Codex |
| updater_guidesiddsachar/row-bot | Skill | 1.7k | today | Apache-2.0 | A | 22 | Claude Code, Codex |