search-before-build: Skill for Claude Code

.agents/skills/publish-npm-release/SKILL.md

publish-npm-release is a skill for Claude Code, Codex from user-w-ui/search-before-build. It costs 55 tokens per session (753 once invoked), scanned A, original, MIT.

A release workflow for publishing a completed JavaScript package to npm, the public package registry commonly used by Node.js projects.

In plain words
What is it for?
Use it to synchronize package versions, commit and tag the release, push it to the repository, and publish a stable npm version.
Why use it?
It checks registry versions and authentication so the next release version is based on what is actually published, while also validating the release steps.

Skill for Claude CodeCodex

Written for Claude Code and Codex: shipped in a Claude Code plugin, but also agents/openai.yaml present. Also seen: installed under .agents/ (shared by several agents); mentions AGENTS.md; mentions Codex.

This is user-w-ui/search-before-build's own configuration. It tells Claude Code and Codex how to work on search-before-build 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 search-before-build configures →

Part of the search-before-build plugin — 3 skills shipped together

Reuse

Borrowing it

Nothing to install: this file belongs to user-w-ui/search-before-build. 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/user-w-ui/search-before-build/main/.agents/skills/publish-npm-release/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/user-w-ui/search-before-build

Made for: Claude Code, Codex.

Or install search-before-build, the plugin that ships this one along with the rest of its 3 skills.

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 publish-npm-release

README.md
[![agentmods](https://agentmods.dev/badge/skills/user-w-ui/search-before-build/publish-npm-release/github.svg)](https://agentmods.dev/skills/user-w-ui/search-before-build/publish-npm-release)
Your own site
<a href="https://agentmods.dev/skills/user-w-ui/search-before-build/publish-npm-release"><img src="https://agentmods.dev/badge/skills/user-w-ui/search-before-build/publish-npm-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.

agentmods 80×15 button for publish-npm-release

Your own site · 80×15
<a href="https://agentmods.dev/skills/user-w-ui/search-before-build/publish-npm-release"><img src="https://agentmods.dev/badge/skills/user-w-ui/search-before-build/publish-npm-release.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 55 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 753 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 high

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 →

  • high Tool Misuse · line 40
    Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).
    Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
  • medium Excessive Agency · line 24
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 $0.00055 $0.00753
Opus 5 $0.00028 $0.00377
Sonnet 5 $0.00011 $0.00151
Haiku 4.5 $0.00006 $0.00075

Measured 11d ago against content hash ee534659d991, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

publish-npm-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 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.

.agents/skills/publish-npm-release/SKILL.md · 41 lines

How it starts

The opening of the file, as written. The whole thing — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Publish an npm release

Treat invocation as authority to perform the complete stable release workflow, including a Git commit, annotated tag, remote push, and npm publish. The caller has already completed product changes and updated npm authentication.

Version policy

  1. Read package.json to obtain the package name and local version. Read AGENTS.md, package scripts, and existing release scripts before changing anything.
  2. Run npm whoami, then query the registry for the package's latest version and complete published-version list. Handle a 404 as a first release.
  3. Select the target version from registry evidence, never by incrementing an arbitrary local value:
    • Keep the local version when it is valid SemVer, unpublished, and greater than npm latest.
    • Otherwise use the next patch version after npm latest.
    • If the caller explicitly requests minor or major, increment that component from npm latest instead.
    • Stop for prereleases unless the caller explicitly supplies the intended npm dist-tag. Do not publish a prerelease as latest by default.
  4. Update package.json and every current release-metadata surface that repository validation requires to equal the target version. Prefer a repository-provided version-sync command. Otherwise inspect exact-version references and update only manifests or runtime client metadata, never historical documentation, fixtures, or changelogs.

Validate and commit

  1. Run all release-relevant checks documented by AGENTS.md, package scripts, and existing release scripts. Include repository tests, syntax checks, plugin validation when present, npm pack --dry-run, and git diff --check.
  2. Stop before committing if any validation fails. Diagnose and fix only release/version issues; do not alter completed product behavior without asking.
  3. Review git status --short. Stage only the caller's completed changes plus the release-version updates. Stop if unrelated or ambiguous changes cannot be separated safely.
  4. Commit with Release v<target-version> if the target-version changes are not already committed. Push the current branch and require its push to succeed before tagging.

Read the full file on GitHub · 41 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 41 lines · 55 tokens per session scan A ee534659d991

Subscribe to this mod's changes

publish-npm-release is a skill published in the GitHub repository user-w-ui/search-before-build (122 stars, last pushed 5d ago), licensed MIT. It adds 55 tokens to every session and 753 once invoked, about $0.0003 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.