WorkClaw: Skill for Claude Code

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

workclaw-release-publish is a skill for Claude Code, Codex from haojing8312/WorkClaw. It costs 38 tokens per session (685 once invoked), scanned A, original, Apache-2.0.

A release-publishing procedure for the WorkClaw desktop app, used after a human has approved the version and Chinese and English release notes. It updates release files, creates a Git tag, and builds a Windows installer package.

In plain words
What is it for?
Publishing a confirmed WorkClaw release, pushing its tag to start the GitHub Windows release workflow, and producing a local .exe or .msi installer.
Why use it?
It keeps publishing tied to the approved release details and follows the required order for commits, tags, and builds.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is haojing8312/WorkClaw's own configuration. It tells Claude Code and Codex how to work on WorkClaw 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 WorkClaw configures →

Reuse

Borrowing it

Nothing to install: this file belongs to haojing8312/WorkClaw. 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/haojing8312/WorkClaw/main/.agents/skills/workclaw-release-publish/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/haojing8312/WorkClaw

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 workclaw-release-publish

README.md
[![agentmods](https://agentmods.dev/badge/skills/haojing8312/workclaw/workclaw-release-publish/github.svg)](https://agentmods.dev/skills/haojing8312/workclaw/workclaw-release-publish)
Your own site
<a href="https://agentmods.dev/skills/haojing8312/workclaw/workclaw-release-publish"><img src="https://agentmods.dev/badge/skills/haojing8312/workclaw/workclaw-release-publish/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 workclaw-release-publish

Your own site · 80×15
<a href="https://agentmods.dev/skills/haojing8312/workclaw/workclaw-release-publish"><img src="https://agentmods.dev/badge/skills/haojing8312/workclaw/workclaw-release-publish.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 685 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.
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 $0.00038 $0.00685
Opus 5 $0.00019 $0.00342
Sonnet 5 $0.00008 $0.00137
Haiku 4.5 $0.00004 $0.00068

Measured 9d ago against content hash a67e54645ae4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

workclaw-release-publish 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 9d 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/workclaw-release-publish/SKILL.md · 84 lines

How it starts

The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.

WorkClaw Release Publish

Overview

Use this skill only after the release version and bilingual release notes are confirmed. It updates release metadata, commits the release, pushes the branch, creates and pushes the tag, and produces a local Windows package.

When to Use

  • The user has already confirmed the target version
  • The user has already confirmed the Chinese + English release notes
  • The user wants the tag pushed to trigger the GitHub Windows release workflow
  • The user wants a local .exe or .msi generated as part of the release

If the version or release notes are not yet confirmed, stop and use workclaw-release-prep.

Required Inputs

  • Confirmed version in vX.Y.Z format
  • Confirmed bilingual release notes content

Files To Update

  • apps/runtime/package.json
  • apps/runtime/src-tauri/Cargo.toml
  • apps/runtime/src-tauri/tauri.conf.json
  • .github/release-windows-notes.md
  • apps/runtime/src-tauri/Cargo.lock when refreshed by build tooling

Execution Order

  1. Verify the requested tag format and confirm the version files match the intended release
  2. Re-read the approved release notes and sanity-check that they still cover the major user-visible outcomes discovered during release prep
  3. Update the release notes template with the approved bilingual content
  4. If an important user-facing outcome is missing, stop and ask for note confirmation again instead of publishing a partial summary
  5. Run release checks:
    • pnpm release:check-version <tag>
    • pnpm test:release
    • pnpm test:installer
    • pnpm test:release-docs
  6. Run user-flow or packaging verification when release surface changed:
    • pnpm test:e2e:runtime
    • pnpm build:runtime
  7. Commit the release changes
  8. Push main
  9. Create and push the tag
  10. Report local installer paths and note that the remote tag triggers .github/workflows/release-windows.yml

Required Output

Use this shape:

## Publish Summary
- Version:
- Commit:
- Tag:
- Commands run:
- Local artifacts:
- Remote trigger:

## Verification Summary
- Changed surface:
- Results:
- Still unverified:
- Verification verdict:

## Release Readiness
- Verdict:
- Blocking issues:
- Ship recommendation:

Read the full file on GitHub · 84 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. 9d ago First seen · 84 lines · 38 tokens per session scan A a67e54645ae4

Subscribe to this mod's changes

workclaw-release-publish is a skill published in the GitHub repository haojing8312/WorkClaw (140 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 38 tokens to every session and 685 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.