What is bilibili-mcp AGENTS.md?

Repository instructions for a Bilibili MCP adapter, where MCP is a standard way for an AI agent to use external tools or data.

Use it when working on the Codex adapter, agent handoffs, writing permissions, skills, or the Paseo and Claude Code integration.

It defines which agent controls planning, editing, verification, and review in different operating modes, reducing conflicts between coding agents.

How XZXZZX-Ai/bilibili-mcp configures Codex and OpenCode

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/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/XZXZZX-Ai/bilibili-mcp

Made for: Codex, OpenCode.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/xzxzzx-ai/bilibili-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/xzxzzx-ai/bilibili-mcp/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/xzxzzx-ai/bilibili-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/xzxzzx-ai/bilibili-mcp/agents-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/xzxzzx-ai/bilibili-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/xzxzzx-ai/bilibili-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 624 This file is loaded in full into every session.

When invoked 624 The same file — it is already loaded in full.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00624	$0.00624
Opus 5	$0.00312	$0.00312
Sonnet 5	$0.00125	$0.00125
Haiku 4.5	$0.00062	$0.00062

Measured 11d ago against content hash 19d9361b16ac, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

bilibili-mcp AGENTS.md 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.md · 64 lines

How it starts

The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Codex Adapter

Codex does not currently provide a repository-file import directive. Before any substantive work, read RULES.md completely; it is the shared and authoritative Harness core. This file contains only Codex-specific behavior.

Modes Owned By This Adapter

In codex-direct, Codex plans, holds the only writer lease, implements, verifies, reviews, accepts, and then creates the focused local commit.

In codex-paseo-claude, Codex plans and owns acceptance while one Paseo-managed Claude Code agent holds the implementation writer lease. Codex must not edit overlapping files while Claude runs and must return review findings to that same writer for bounded repair.

Codex must ask the user once before the first implementation write when no mode was already selected. It must not launch Claude, restart Paseo, or fall back to another adapter without authority.

Codex Capability Rules

Use the active Codex Skill catalog; do not assume .agents/skills, .codex/skills, and Claude's Skills are synchronized.
A Matt Skill marked allow_implicit_invocation: false requires the user's native $skill invocation. When required but missing, use the shared CLI gate with host codex to emit one reminder and stop before governed writes.
Use .codex/agents/ for bounded planning, risk review, and release verification. These agents are read-only unless a ticket explicitly assigns a compatible writer lease.
Explorers and reviewers do not become writers. Keep at most one active writer for a ticket.

For local facts use rg, Git, npm, Node, TypeScript, Vitest, and the shared Harness CLI. Use live GitHub tooling for Issues/PRs/runs and current official documentation for behavior that may have changed.

Paseo Controller Delta

Before a collaboration launch:

resolve the current user's home directory, read .paseo/orchestration-preferences.json, and use providers.impl unless the user selected a provider;
check Paseo availability without restarting its daemon;
create a bounded file-backed handoff referencing the Issue and typed task contract;
launch one implementation agent;
preserve the writer lease until the agent stops and its diff/report are captured;
review the actual diff and verification evidence before acceptance.

Read the full file on GitHub · 64 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.

11d ago First seen · 64 lines · 624 tokens per session scan A 19d9361b16ac

Subscribe to this mod's changes

bilibili-mcp AGENTS.md is an instructions file published in the GitHub repository XZXZZX-Ai/bilibili-mcp (17 stars, last pushed 5d ago), licensed Apache-2.0. It adds 624 tokens to every session, about $0.0031 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.

Building agents

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

bilibili-mcp: Instructions file for Codex