OpenBiliClaw: Skill for Claude Code

.claude/skills/release/SKILL.md

release is a skill for Claude Code from whiteguo233/OpenBiliClaw. It costs 18 tokens per session (662 once invoked), scanned A, original, MIT.

A controlled process for releasing a new project version, including tests, version updates, changelog edits, and release tags. A release is the prepared version of software made available to users.

In plain words
What is it for?
Use it to prepare a release, bump project or extension versions, update release notes, run the test suite, and push a verified release tag.
Why use it?
It prevents publishing when the code, branch, version, or documentation has not passed the required checks. The process stops if any verification step fails.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions CLAUDE.md.

This is whiteguo233/OpenBiliClaw's own configuration. It tells Claude Code how to work on OpenBiliClaw 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 OpenBiliClaw configures →

About the project

OpenBiliClaw is a local, open-source AI agent that learns a person's interests and discovers content across multiple social platforms and the open web. It is for people who want personalized content recommendations with their usage data kept on their own machine.

whiteguo233/OpenBiliClaw · 3,215 stars · on GitHub · whiteguo233.github.io

Reuse

Borrowing it

Nothing to install: this file belongs to whiteguo233/OpenBiliClaw. 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/whiteguo233/OpenBiliClaw/main/.claude/skills/release/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/whiteguo233/OpenBiliClaw

Made for: Claude Code.

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/whiteguo233/openbiliclaw/release.svg)](https://agentmods.dev/skills/whiteguo233/openbiliclaw/release)
Your own site
<a href="https://agentmods.dev/skills/whiteguo233/openbiliclaw/release"><img src="https://agentmods.dev/badge/skills/whiteguo233/openbiliclaw/release.svg" alt="Measured on agentmods" height="20"></a>
Per session 18 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 662 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 pass 7 Sept 2026
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 $0.00018 $0.00662
Opus 5 $0.00009 $0.00331
Sonnet 5 $0.00004 $0.00132
Haiku 4.5 $0.00002 $0.00066

Measured 8d ago against content hash 1526f07dba09, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, 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 8d 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 · 81 lines

How it starts

The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Release OpenBiliClaw

Follow all six steps in order. Stop when any gate fails; never publish a partially verified release.

1. Run pre-flight checks

Require a clean worktree on main, pull the latest commit, and run the full test suite:

git status --short
git branch --show-current
git pull --ff-only
.venv/bin/python -m pytest -q

Do not continue until git status --short is empty and the branch is main.

2. Bump mechanical versions

Use the repository tool as the only writer for mechanical version fields:

.venv/bin/python scripts/release.py --bump X.Y.Z

When the extension version changes, include --extension X.Y.Z; the flag may also be used alone for an extension-only release. Never hand-edit mechanical version fields. The changelog heading and README callout content in the next steps are deliberate hand edits.

3. Update the changelog

Hand-edit the top of docs/changelog.md with ## vX.Y.Z: theme (YYYY-MM-DD) and the release's verified changes. The final scripts/release.py --check warns if this heading is missing.

4. Replace the README callouts

Hand-edit the 📌 callouts under the recent-updates sections. Follow CLAUDE.md rule 10; the three hard limits are:

  • Use at most four bullets.
  • Replace the previous callout; never append another version callout.
  • Keep README.md and README_EN.md in lockstep with the same items and order.

Then verify every mechanical field and both user-facing version headers:

.venv/bin/python scripts/release.py --check

5. Commit and push tags individually

Review the release-only diff, stage only those files, and commit:

git commit -m "chore: release X.Y.Z" -- <release-paths>

Create the aggregate openbiliclaw-vX.Y.Z tag and the applicable backend-vX.Y.Z, extension-vX.Y.Z, and desktop-vX.Y.Z channel tags. Push one tag per git push invocation. A four-tag push previously emitted no GitHub events, leaving all four release workflows silently dead; never combine tag refspecs in one push.

Read the full file on GitHub · 81 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. 8d ago First seen · 81 lines · 18 tokens per session scan A 1526f07dba09

Subscribe to this mod's changes

release is a skill published in the GitHub repository whiteguo233/OpenBiliClaw (3,215 stars, last pushed today), licensed MIT. It adds 18 tokens to every session and 662 once invoked, about $0.0001 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.