Agent skill

Release

Ship a modelprint release the same way every time - gates, version stamp, changelog, tag, GitHub release, deploy, verify.

MITAuto-check passedDevelopment

Install Release

skills CLI

$ npx skills add unclecode/modelprint --skill release -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install unclecode/modelprint release --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/unclecode/modelprint.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/release .claude/skills/release && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Paste into Claude Code

Install the "release" agent skill from https://github.com/unclecode/modelprint/tree/main/.claude/skills/release into .claude/skills/release/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "release", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/unclecode/modelprint/tree/main/.claude/skills/release

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add unclecode/modelprint --skill release -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install unclecode/modelprint release --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/unclecode/modelprint.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.claude/skills/release .agents/skills/release && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "release" agent skill from https://github.com/unclecode/modelprint/tree/main/.claude/skills/release into .agents/skills/release/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "release", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add unclecode/modelprint --skill release -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install unclecode/modelprint release --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/unclecode/modelprint.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.claude/skills/release .cursor/skills/release && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "release" agent skill from https://github.com/unclecode/modelprint/tree/main/.claude/skills/release into .cursor/skills/release/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "release", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/unclecode/modelprint.git --path .claude/skills/release

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add unclecode/modelprint --skill release -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install unclecode/modelprint release --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/unclecode/modelprint.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.claude/skills/release .gemini/skills/release && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "release" agent skill from https://github.com/unclecode/modelprint/tree/main/.claude/skills/release into .gemini/skills/release/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "release", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install unclecode/modelprint release

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add unclecode/modelprint --skill release -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/unclecode/modelprint.git skills-src && mkdir -p .github/skills && cp -r skills-src/.claude/skills/release .github/skills/release && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "release" agent skill from https://github.com/unclecode/modelprint/tree/main/.claude/skills/release into .github/skills/release/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "release", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add unclecode/modelprint --skill release -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install unclecode/modelprint release --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/unclecode/modelprint.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.claude/skills/release .opencode/skills/release && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "release" agent skill from https://github.com/unclecode/modelprint/tree/main/.claude/skills/release into .opencode/skills/release/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "release", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: release
GitHub stars: 127
Token cost: ~1.2k tokens
SKILL.md length: 508 words
Files: 1
Skills in repo: 1
Repo updated: Oct 6, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

Ship a modelprint release the same way every time - gates, version stamp, changelog, tag, GitHub release, deploy, verify.

Works in 9 steps: Clean state → Both gates → Stamp the version → …
The user says release
SKILL.md covers Before you start, The order. Do not reorder., Rules that do not bend and After the release
Calls git, node and curl; reaches modelprint.ai and github.com

What it does

Release is an agent skill from unclecode/modelprint. Ship a modelprint release the same way every time - gates, version stamp, changelog, tag, GitHub release, deploy, verify. Use when the user says "release", "ship it", "deploy", "cut a version", or after merging pull requests that should reach the public page.

Its SKILL.md is about 1.2k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Development, covering Changelog and release notes and Pull requests. It works with GitHub and OpenRouter. The repository describes itself as: Who is really behind that API? Fingerprint any OpenAI-compatible endpoint in the browser: 9 infrastructure probes, side-by-side comparison, community-extensible. The licence is MIT.

When your agent uses it

The user says release
After merging pull requests that should reach the public page

Example prompts

“release”
“ship it”
“deploy”
“/release”

Requirements

Node.js

Workflow steps

9 steps, taken from the step headings in SKILL.md.

Clean state
Both gates
Stamp the version
Write the changelog entry
Commit, tag, push
GitHub release
Verify the deploy, do not assume it
Worker, only if worker/ changed
Tell the user

What it can do on your machine

Read from SKILL.md and the folder at commit fa11a85. It shows what the files ask for, not the result of running them.

Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
- git
- node
- curl
- gh
- npx
From the folder's file list and the shell code blocks in SKILL.md.
Network
Hosts in commands or code, which the agent is likely to contact:
- modelprint.ai
- github.com
- modelprint-api.unclecode.workers.dev
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Release loads about 1.2k tokens when it runs. Until then it costs about 67 tokens; SKILL.md has 508 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~67
When it runs · the whole SKILL.md, loaded when a task matches: ~1.2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from unclecode/modelprint at commit fa11a85, republished under its MIT licence (© unclecode). 508 words, ~1,195 tokens.

Download SKILL.mdSave it as .claude/skills/release/SKILL.md (or your agent's skills folder).

name: release
description: Ship a modelprint release the same way every time - gates, version stamp, changelog, tag, GitHub release, deploy, verify. Use when the user says "release", "ship it", "deploy", "cut a version", or after merging pull requests that should reach the public page.

Release modelprint

One command, one order, no step skipped. The public page and the GitHub release must always agree, and a release must never carry an untested probe.

Repo: /Users/unclecode/devs/modelprint. The page is GitHub Pages from main. The backend is a Cloudflare Worker in worker/, released separately.

Before you start

Ask the user which kind of release this is, unless they already said:

patch (0.7.3 to 0.7.4): only fixes.
minor (0.7.3 to 0.8.0): anything new. New probes are minor, always.
major: reserved for a break in the probe contract.

Never guess the number. Read VERSION for the current one.

The order. Do not reorder.

1. Clean state

bash

cd /Users/unclecode/devs/modelprint
git checkout main && git pull -q origin main
git status --short          # must be empty of surprises

If uncommitted work exists, STOP and ask. Committing someone's half-finished work into a release is worse than a delayed release.

2. Both gates

bash

node probe-check.mjs        # free, must end "0 failed"
node probe-bench.mjs        # live, costs money, read the HEALTH block

probe-check failing stops the release. In probe-bench, read:

crashed: must be none
unstable (fluctuate on same model): must be none

A probe that fluctuates creates false differences in the table. That is a release blocker, not a note.

3. Stamp the version

bash

node bump.mjs 0.8.0         # writes VERSION and stamps index.html

The script fails loudly if it cannot stamp both places. Never edit the version by hand.

4. Write the changelog entry

Add a section at the top of CHANGELOG.md, under the header:

## [0.8.0] - YYYY-MM-DD

### Added
- What a user can now do, in plain words. Real numbers.

### Fixed
- What was wrong, and what it did to the user. Not the file name.

### Security
- Only when a real security property changed.

Rules for the text:

Write for a reader who does not know the code. Say the effect, not the file.
Credit every contributor by handle and pull request number: by [@name](https://github.com/name) (#3).
Use real numbers. "Waited up to 25 seconds" beats "was slow".
No jargon, short sentences.

5. Commit, tag, push

bash

git add -A
git commit -m "release 0.8.0

<the changelog entry body, plain text>"
git tag -a v0.8.0 -m "0.8.0"
git push origin main
git push origin v0.8.0

The tag is annotated (-a), never lightweight.

6. GitHub release

bash

gh release create v0.8.0 \
  --title "0.8.0 - <three or four words>" \
  --notes "<the changelog entry, markdown>"

Add --latest. The notes are the same words as the changelog, so a reader never sees two versions of the truth.

Show full SKILL.md (222 more words)Show less

7. Verify the deploy, do not assume it

GitHub Pages takes about a minute. Poll until the live page reports the new version, then confirm the engine really changed:

bash

for i in $(seq 1 12); do
  LIVE=$(curl -s https://modelprint.ai/index.html | grep -o 'v0\.[0-9.]*' | head -1)
  [ "$LIVE" = "v0.8.0" ] && break
  sleep 10
done
echo "live: $LIVE"
curl -s "https://modelprint.ai/probes/index.js" | grep -c '\.js"'

If the live version does not match after two minutes, say so plainly. Do not report a release as done on hope.

8. Worker, only if `worker/` changed

bash

cd worker && npx wrangler deploy
curl -s https://modelprint-api.unclecode.workers.dev/proxy/status

The worker version is not the page version. Say which one you deployed.

9. Tell the user

Report, short:

version and tag
what a user gets, in one or two sentences
contributors credited, by name
the live page confirmed at the new version
whether the worker was deployed too

Rules that do not bend

Never release with a failing or unstable gate. The whole product is trust in the comparison table.
Never hand-edit the version. Use bump.mjs.
Never write release notes that differ from the changelog.
Always credit contributors, in the changelog, in CONTRIBUTORS.md, and in the release notes.
Never claim the deploy worked without checking the live URL.
If a community probe is in this release, confirm both gates named in CONTRIBUTING.md passed for it: security (no direct network access) and determinism (same model, same value).

After the release

If the release is worth telling people about, say so, but do not post anything. Posting is the user's decision and needs his exact words.

Files

Just SKILL.md in .claude/skills/release of unclecode/modelprint.

Open the folder on GitHubat commit fa11a85

Compare with similar skills

Release next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Release compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Release this skillunclecode/modelprint	127	—	~1.2k	Automated safety check: Pass	MIT	yesterday
Verdaccio Pull Request Workflowverdaccio/verdaccio	18k	—	~1.9k	Automated safety check: Pass	MIT	yesterday
Plannotator Release Preparationbacknotprop/plannotator	9.2k	—	~4.6k	Automated safety check: Pass	Apache-2.0	yesterday
Ansible Pull Request Reviewansible/ansible	71k	—	~570	Automated safety check: Pass	GPL-3.0	yesterday
Plane Release Notes Generatormakeplane/plane	60k	—	~2.5k	Automated safety check: Pass	AGPL-3.0	yesterday
Pair GitHub PRNVIDIA/Personal-AI-Router	1.6k	—	~1.3k	Automated safety check: Pass	Apache-2.0	yesterday

Similar skills

Verdaccio Pull Request Workflow
verdaccio/verdaccio
Takes a change through a verdaccio pull request: branch, local checks, changeset, title and body, labels, CI and review rounds, and ports to other release lines.
18k GitHub stars~1.9k tokensUpdated yesterday
DevelopmentAuto-check passed
Plannotator Release Preparation
backnotprop/plannotator
Drafts Plannotator release notes with full contributor credit, bumps versions in dependency order, builds, and starts the tag-driven release pipeline, in four reviewed phases.
9.2k GitHub stars~4.6k tokensUpdated yesterday
DevelopmentAuto-check passed
Ansible Pull Request Review
ansible/ansible
Reviews an Ansible pull request by number, following the steps in the project's CLAUDE.md, with early checks for changelog fragments and tests.
71k GitHub stars~570 tokensUpdated yesterday
DevelopmentAuto-check passed
Plane Release Notes Generator
makeplane/plane
Builds categorized release notes for a Plane release pull request from its commits and writes them into the PR description, for both the plane-cloud and plane-ee repos.
60k GitHub stars~2.5k tokensUpdated yesterday
DevelopmentAuto-check passed
Pair GitHub PR
NVIDIA/Personal-AI-Router
Official
Fills GitHub pull request descriptions with the required PAIR pair-release-intent:v1 block so the release-intent check passes.
1.6k GitHub stars~1.3k tokensUpdated yesterday
DevelopmentAuto-check passed
Handsontable Changelog Entry
handsontable/handsontable
Decides whether a code change needs a changelog entry and creates the JSON file in .changelogs with the right type, framework and user-facing title.
22k GitHub stars~1.6k tokensUpdated yesterday
DevelopmentAuto-check passed

Works with

Questions about Release

What does Release do?

Ship a modelprint release the same way every time - gates, version stamp, changelog, tag, GitHub release, deploy, verify. Release is an agent skill from unclecode/modelprint. Ship a modelprint release the same way every time - gates, version stamp, changelog, tag, GitHub release, deploy, verify.

When should I use Release?

Release fits situations like: the user says release; after merging pull requests that should reach the public page.

How do I install Release in Claude Code?

Run `npx skills add unclecode/modelprint --skill release -a claude-code`. Or copy the skill folder (.claude/skills/release in unclecode/modelprint) into .claude/skills/release in your project. Claude Code loads it when a task matches its description.

How do I install Release in Codex?

Run `npx skills add unclecode/modelprint --skill release -a codex`. Or copy the skill folder (.claude/skills/release in unclecode/modelprint) into .agents/skills/release in your project. Codex loads it when a task matches its description.

Can I use Release in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add unclecode/modelprint --skill release -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/release, .gemini/skills/release, .github/skills/release and .opencode/skills/release in your project.

What does Release need to run?

Going by SKILL.md and its folder, Release needs the command-line tools its instructions call (git, node, curl, gh and npx). Our summary lists: Node.js.

Does Release access the network?

SKILL.md names 3 domains. In commands or code: modelprint.ai, github.com and modelprint-api.unclecode.workers.dev; the agent is likely to contact these when it follows the instructions. This is read from the text; nothing was executed.

Is Release safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Release use?

Release is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Release use?

About 1.2k tokens (SKILL.md is roughly 4.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Release?

Skills that share tags, products or a category with Release: Verdaccio Pull Request Workflow (verdaccio/verdaccio, 18k stars), Plannotator Release Preparation (backnotprop/plannotator, 9.2k stars), Ansible Pull Request Review (ansible/ansible, 71k stars) and Plane Release Notes Generator (makeplane/plane, 60k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Release?

unclecode (a GitHub user) maintains it in unclecode/modelprint, which has 127 GitHub stars. The repository was last updated on October 6, 2026.

Source: unclecode/modelprint on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Release

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Release modelprint

Before you start

The order. Do not reorder.

1. Clean state

2. Both gates

3. Stamp the version

4. Write the changelog entry

5. Commit, tag, push

6. GitHub release

7. Verify the deploy, do not assume it

8. Worker, only if worker/ changed

9. Tell the user

Rules that do not bend

After the release

Files

Compare with similar skills

Similar skills

Verdaccio Pull Request Workflow

Plannotator Release Preparation

Ansible Pull Request Review

Plane Release Notes Generator

Pair GitHub PR

Handsontable Changelog Entry

Related

Questions about Release

8. Worker, only if `worker/` changed