release

release is a skill for Claude Code, Codex from jukanntenn/glm-plan-usage. It costs 87 tokens per session (1,326 once invoked), scanned A, original, MIT.

A release checklist for glm-plan-usage, a Rust command-line program distributed through npm. It verifies the code, updates version numbers, syncs the lock file, and guides the publishing steps.

In plain words
What is it for?
Use it to prepare a new release, run tests and code-quality checks, review changes since the last tag, update the required package versions, and verify the release files.
Why use it?
It reduces release mistakes by checking the repository and requiring confirmation before changing version information.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/jukanntenn/glm-plan-usage/release
Any agent
npx skills add jukanntenn/glm-plan-usage --skill release
Clone the repo
git clone --depth 1 https://github.com/jukanntenn/glm-plan-usage

Made for: Claude Code, Codex.

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

README.md
[![agentmods](https://agentmods.dev/badge/skills/jukanntenn/glm-plan-usage/release.svg)](https://agentmods.dev/skills/jukanntenn/glm-plan-usage/release)
Your own site
<a href="https://agentmods.dev/skills/jukanntenn/glm-plan-usage/release"><img src="https://agentmods.dev/badge/skills/jukanntenn/glm-plan-usage/release.svg" alt="Measured on agentmods" height="20"></a>
Per session 87 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,326 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00087 $0.01326
Opus 5 $0.00044 $0.00663
Sonnet 5 $0.00017 $0.00265
Haiku 4.5 $0.00009 $0.00133

Measured 4d ago against content hash d4d9a7019cfb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 4d 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/SKILL.md · 168 lines

How it starts

The opening of the file, as written. The whole thing — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Release Process

Safe release workflow for glm-plan-usage (Rust CLI, multi-platform NPM package). Every step validates before proceeding; failures report the problem + suggestion then STOP — never auto-fix.

Prerequisites

Verify clean tree and identify current state:

git status                    # must be clean
grep '^version = ' Cargo.toml # current version
git describe --tags --abbrev=0  # last tag

Steps 1-5: Automated Phase

Step 1: Quality Checks

cargo test && cargo fmt -- --check && cargo clippy -- -D warnings

Fail → report which check failed (test/fmt/clippy) + likely cause, STOP.

Step 2: Version Bump

  1. Show commits since last tag: git log --oneline <last_tag>..HEAD
  2. Ask user to confirm new version (suggest semver bump: patch=fixes, minor=features, major=breaking)
  3. Update exactly TWO files:
    • Cargo.toml: version = "x.y.z"
    • npm/main/package.json: "version": "x.y.z"
  4. Sync Cargo.lock with the new version:
    cargo check
    
  5. Verify all three files show the same new version (Cargo.toml, npm/main/package.json, Cargo.lock)

Do NOT touch npm/platforms/*/package.json or optionalDependencies in npm/main/package.json — prepare-packages.js handles those at release time.

Step 3: Local Build

cargo build --release

Fail → report error + likely cause, STOP. Pass → target/release/glm-plan-usage exists.

Step 4: Local Publish Verification

NPM_REGISTRY=http://192.168.5.50:4873/ ./npm/publish-local.sh

This reads version from Cargo.toml, runs prepare-packages.js, copies binaries, publishes all packages to local verdaccio. Missing cross-compile binaries are expected (only current platform builds locally).

Fail → report which platform failed + error output, STOP.

Step 5: Update CHANGELOG & Verify READMEs

CHANGELOG: git log --oneline <last_tag>..HEAD → derive user-visible changes, draft entry matching existing format, present to user for review, then insert at TOP:

Read the full file on GitHub · 168 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. 4d ago First seen · 168 lines · 87 tokens per session scan A d4d9a7019cfb

Subscribe to this mod's changes

release is a skill published in the GitHub repository jukanntenn/glm-plan-usage (13 stars, last pushed 2mo ago), licensed MIT. It adds 87 tokens to every session and 1,326 once invoked, about $0.0004 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.