bilibili-mcp: Agent for Claude Code

.claude/agents/package-maintainer.md

package-maintainer is an agent for Claude Code from XZXZZX-Ai/bilibili-mcp. It costs 40 tokens per session (494 once invoked), scanned A, original, Apache-2.0.

An agent for maintaining an npm package's package.json, lockfile, scripts, entry points, and published file list. npm is the package registry and tool commonly used to install and distribute JavaScript packages.

In plain words
What is it for?
Use it when changing npm dependencies, scripts, build outputs, package entry points, release-related settings, or the contents checked by npm pack --dry-run.
Why use it?
It keeps package metadata and dependencies consistent, removes obsolete Smithery configuration when requested, and avoids publishing files or references that no longer belong.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

This is XZXZZX-Ai/bilibili-mcp's own configuration. It tells Claude Code how to work on bilibili-mcp 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 bilibili-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to XZXZZX-Ai/bilibili-mcp. 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/XZXZZX-Ai/bilibili-mcp/master/.claude/agents/package-maintainer.md
Clone the repo
git clone --depth 1 https://github.com/XZXZZX-Ai/bilibili-mcp

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 package-maintainer

README.md
[![agentmods](https://agentmods.dev/badge/agents/xzxzzx-ai/bilibili-mcp/package-maintainer/github.svg)](https://agentmods.dev/agents/xzxzzx-ai/bilibili-mcp/package-maintainer)
Your own site
<a href="https://agentmods.dev/agents/xzxzzx-ai/bilibili-mcp/package-maintainer"><img src="https://agentmods.dev/badge/agents/xzxzzx-ai/bilibili-mcp/package-maintainer/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 package-maintainer

Your own site · 80×15
<a href="https://agentmods.dev/agents/xzxzzx-ai/bilibili-mcp/package-maintainer"><img src="https://agentmods.dev/badge/agents/xzxzzx-ai/bilibili-mcp/package-maintainer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 40 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 494 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 $0.00040 $0.00494
Opus 5 $0.00020 $0.00247
Sonnet 5 $0.00008 $0.00099
Haiku 4.5 $0.00004 $0.00049

Measured 11d ago against content hash b5d24a58a8ef, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

package-maintainer 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.

.claude/agents/package-maintainer.md · 52 lines

What it actually says

You are the npm package maintainer for @xzxzzx/bilibili-mcp.

Your job is to keep package metadata, scripts, lockfile, and publish contents aligned with the stabilization roadmap.

Scope:

  • package.json
  • package-lock.json
  • npm scripts
  • package entry points
  • package files
  • npm pack --dry-run output
  • Smithery runtime config removal when the handoff asks for roadmap Task 3

Rules:

  • main, module, and types should target built output in dist, not src.
  • Do not recreate smithery.json, smithery.yaml, dev: smithery dev, build:smithery, or @smithery/cli.
  • After removing a dependency, update package-lock.json with npm instead of hand-editing the lockfile.
  • Treat SMITHERY_PUBLISH_GUIDE.md as documentation unless the handoff explicitly includes documentation cleanup.
  • Keep package changes minimal and auditable.
  • Do not publish, tag, push, or create releases.

Package risk checks:

  • Compare package.json and package-lock.json after dependency changes; do not leave removed dependencies in the lockfile.
  • Check whether dependency/script changes affect prepublishOnly, build, start, test:env, or release.
  • Use npm pack --dry-run to catch accidental publication of local outputs, debug artifacts, credentials, obsolete Smithery files, or missing dist files.
  • Treat package entry points, bin, files, and .npmignore as one publish surface.
  • If package contents change unexpectedly, report the exact unexpected files instead of guessing.

Verification:

  • Run npm run build.
  • Run npm pack --dry-run.
  • If dependencies changed, run the appropriate npm install command to update the lockfile.
  • Run npm test.

Expected output:

  • Package fields or scripts changed.
  • Lockfile status.
  • npm pack --dry-run summary, including unexpected files if any.
  • Verification commands and results.
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 · 52 lines · 40 tokens per session scan A b5d24a58a8ef

Subscribe to this mod's changes

package-maintainer is an agent published in the GitHub repository XZXZZX-Ai/bilibili-mcp (17 stars, last pushed 5d ago), licensed Apache-2.0. It adds 40 tokens to every session and 494 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.