arknights-mcp: Instructions file for Codex

AGENTS.md

arknights-mcp AGENTS.md is an instructions file for Codex, OpenCode from rendyuwu/arknights-mcp. It costs 1,267 tokens per session, scanned A, original, Apache-2.0.

Repository instructions for coding agents working on an Arknights data server. They define the project structure, required documents, and rules that must remain unchanged.

In plain words
What is it for?
Use them when changing the arknights-mcp repository, especially when working on data imports, database access, analyzers, or its local and web connections.
Why use it?
They reduce the risk of an agent putting code in the wrong layer or breaking design decisions. They also state what agents must read before editing.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions CLAUDE.md; mentions Claude Code; mentions AGENTS.md.

This is rendyuwu/arknights-mcp's own configuration. It tells Codex and OpenCode how to work on arknights-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 arknights-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to rendyuwu/arknights-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/rendyuwu/arknights-mcp/master/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/rendyuwu/arknights-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.

agentmods badge for arknights-mcp AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/rendyuwu/arknights-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/rendyuwu/arknights-mcp/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/rendyuwu/arknights-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/rendyuwu/arknights-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.

agentmods 80×15 button for arknights-mcp AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/rendyuwu/arknights-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/rendyuwu/arknights-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,267 This file is loaded in full into every session.
When invoked 1,267 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01267 $0.01267
Opus 5.5 $0.00507 $0.00507
Sonnet 5.5 $0.00253 $0.00253
Haiku 4.5 $0.00127 $0.00127

Measured 1mo ago against content hash cf52873deec7, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

arknights-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 1mo 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 · 100 lines

How it starts

The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — Guardrails for coding agents

This file is the canonical, tool-agnostic instruction set for any AI coding agent (Codex, Claude Code, and others) working in this repository. CLAUDE.md points here.

Before changing files: read Arknights_MCP_PRD_v0.1_FINAL.md (the product requirements). The founder-approved decisions in PRD Section 18 (D1–D15) are binding; changing one requires the owner's explicit approval in the conversation. ADRs are no longer written; docs/adr/ is a frozen historical record that existing code comments cite.

What this project is

A read-only Arknights intelligence MCP server: one shared application core, two transports (local stdio, private OAuth/OIDC Streamable HTTP), over versioned SQLite snapshots. Regions en and cn. Data is imported/synced via CLI only; user-facing tools query SQLite and never touch the network.

Architecture rules (keep these separations)

  • One shared core, two transports. Never duplicate domain logic across transports — both call the same tool_registry + services.
  • Keep layers separated: sources/ (adapters), importers/field_policy.py (allowlist), importers/ (parsers), db/ + db/repositories/ (data access), analyzers/ (rules), models/ + mcp/ (schemas), transports/, auth/, middleware/.
  • Admin operations (sync, import, validate, purge, source management, account) are CLI-only and are never exposed as MCP tools.
  • Write tests before broadening parsers. Prefer property tests (Hypothesis) for parsing/normalization.

Never (hard invariants)

  • Make an outbound/source-network request from any MCP tool at query time; no query-time download/scrape fallback.
  • Open SQLite writable in an MCP process; run arbitrary SQL, shell, filesystem, or a source-download tool; build SQL by string interpolation; connect to the account roster database from an MCP process with a role that can write (ADR 0020).
  • Replace the active DB on a failed/incompatible sync, or mutate the active DB in place. Promote only after validation, atomically via current.json.
  • Emit a factual response without region + provenance, or silently mix en and cn.
  • Emit an observation without rule_id + evidence + confidence + limitations + analyzer_version. Match on typed fields, not NL keywords.
  • Label a recommendation "mandatory" or "universal best"; recommend anything at confidence < 0.5 (report it as a limitation instead).
  • Concatenate imported/source text into server instructions or tool descriptions; treat imported strings as anything but untrusted data; generate tool descriptions from imported content; let source data select tools, URLs, or admin actions. Strip control characters and cap lengths (PRD 17.6).
  • Log full prompts, full tool arguments, response bodies, authorization headers, bearer tokens, raw source records, or roster/account data; leak stack traces or local paths in errors.
  • Request, store, or transmit Arknights game credentials or account IDs outside the CLI-only account group (ADR 0020); let any MCP process read the Yostar session; log or print email, OTP, tokens, or roster data.
  • Commit or ship raw snapshots, prebuilt databases, artwork, audio, story scripts, voice lines, wiki/community prose, or full announcement bodies. data/builds/ and *.sqlite are git-ignored.
  • Run non-loopback remote without HTTPS + valid OAuth/OIDC; implement username/password storage; enable public access via a single flag/env var (PRD 17.7).
  • Provide bulk-dump / DB-download / unbounded pagination / enumeration; exceed search default 10 / max 50, page_size max 100, or the 200 KB default response cap.
  • Upgrade the MCP SDK to v2, break a required tool field, or bump schema_version without the owner's explicit approval.
  • Assume reuse permission from a public repo, an attribution offer, or a takedown offer (D13).

Read the full file on GitHub · 100 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. 1mo ago Changed · -1 lines · +1 tokens per session cf52873deec7
  2. 1mo ago Changed · -4 lines · -91 tokens per session c5f43f1fc347
  3. 2mo ago First seen · 105 lines · 1,357 tokens per session scan A f610dc50cf20

Subscribe to this mod's changes

arknights-mcp AGENTS.md is an instructions file published in the GitHub repository rendyuwu/arknights-mcp (0 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 1,267 tokens to every session, about $0.0051 per session on Opus 5.5. 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 2026-08-31.

Related

arknights-mcp AGENTS.md compared with instructions from other repositories

arknights-mcp AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
arknights-mcp AGENTS.mdrendyuwu/arknights-mcpInstructions file01mo agoApache-2.0A1,267Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,685GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,093GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA2,022GitHub Copilot