Appflowy-MCP-Server: Instructions file for Codex

AGENTS.md

Appflowy-MCP-Server AGENTS.md is an instructions file for Codex, OpenCode from Rahulk644/Appflowy-MCP-Server. It costs 833 tokens per session, scanned A, original, MIT.

Repository instructions for the Appflowy-MCP-Server project, documenting files to read, architecture limits, compatibility, release checks, and data-handling rules. MCP is a standard way for an AI agent to connect to tools or services.

In plain words
What is it for?
Use it as guidance when developing, validating, deploying, or reviewing Appflowy-MCP-Server. It does not provide enough information to describe additional concrete jobs.
Why use it?
It gives maintainers and coding agents durable project context and prevents changes that violate the repository's documented boundaries. The supplied description does not indicate a standalone user-facing feature.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md.

This is Rahulk644/Appflowy-MCP-Server's own configuration. It tells Codex and OpenCode how to work on Appflowy-MCP-Server 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 Appflowy-MCP-Server configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Rahulk644/Appflowy-MCP-Server. 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/Rahulk644/Appflowy-MCP-Server/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/Rahulk644/Appflowy-MCP-Server

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 Appflowy-MCP-Server AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/rahulk644/appflowy-mcp-server/agents-md/github.svg)](https://agentmods.dev/instructions/rahulk644/appflowy-mcp-server/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/rahulk644/appflowy-mcp-server/agents-md"><img src="https://agentmods.dev/badge/instructions/rahulk644/appflowy-mcp-server/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 Appflowy-MCP-Server AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/rahulk644/appflowy-mcp-server/agents-md"><img src="https://agentmods.dev/badge/instructions/rahulk644/appflowy-mcp-server/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 833 This file is loaded in full into every session.
When invoked 833 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 $0.00833 $0.00833
Opus 5.5 $0.00333 $0.00333
Sonnet 5.5 $0.00167 $0.00167
Haiku 4.5 $0.00083 $0.00083

Measured today against content hash ac4a1ec8e9f9, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

Appflowy-MCP-Server 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 today.

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 · 70 lines

How it starts

The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repository context

This file is durable context for maintainers and coding agents. It describes the current project; temporary progress and conversation summaries do not belong here.

Read first

  • README.md: supported installation and user interface.
  • ARCHITECTURE.md: module boundaries and integrity constraints.
  • COMPATIBILITY.md: exact validated deployment and unvalidated paths.
  • ROADMAP.md: open tasks, priority and completion criteria.
  • CONTRIBUTING.md / RELEASING.md: development and publication checks.

Project invariants

  • Python 3.11+, official MCP 2.3+ MCPServer, native async network I/O.
  • Compact: 11 tools, 12 only with experimental AI enabled. Legacy: 34 separate names. Read-only compact: five tools. Never register aliases alongside compact.
  • ALLOWED_WORKSPACE_IDS is server-wide. Approved HTTP users share the bot's AppFlowy identity; do not claim per-client page scopes or AppFlowy user roles.
  • Collab changes send incremental diffs. Never write an empty replacement after a decode error. Keep pycrdt 0.13.0 pinned until representative fixtures justify change.
  • OAuth refreshes rotate within a persisted login family. Replays revoke that family. Keep the JSON store single-process; do not issue tokens before a successful commit.
  • Preserve root compatibility entry points and documented commands.
  • PyPI publication is explicitly deferred; retain the unconditional workflow guard.
  • Change release versions only in appflowy_mcp/__init__.py, then stamp/check server.json with scripts/release_metadata.py. Dependencies belong in pyproject.
  • Keep action references pinned to reviewed release commits with version comments. Validate action upgrades independently, including artifact upload/download checks.
  • Cloud/AI checks require suitable disposable deployments. Self-hosted success is not SaaS certification. Do not commit credentials or raw private response bodies.
  • DateTime cells store the timestamp in data and range/time attributes beside it; JSON serialized into data can persist successfully while rendering an empty date.
  • Keep compact command validators aligned with consumed inputs. Reject meaningful unused fields before mutation; optional defaults may be supplied by MCP clients.
  • Field deletion must reject active local schema/view references before mutation. Only order/direct settings are cleaned automatically; Relation deletion needs reciprocal cleanup in AppFlowy. Do not claim cross-database dependency inspection.
  • Keep documents.py and collab.py independent of network/session state. Their helpers operate on fetched snapshots; uploads still use backend incremental diffs.
  • Preserve returned list/tree cursors when bounding responses. Export entries must be complete files; oversized documents carry a separate chunked fetch request. Markdown offsets count Unicode characters; compare hashes across chunks. Neither tree export nor repeated snapshot fetches provide atomic multi-request reads.
  • api.py owns AppFlowy token/client state and workspace guards. Patch the owner in tests; server helper aliases do not mirror mutable globals or override behavior.

Read the full file on GitHub · 70 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. today First seen · 70 lines · 833 tokens per session scan A ac4a1ec8e9f9

Subscribe to this mod's changes

Appflowy-MCP-Server AGENTS.md is an instructions file published in the GitHub repository Rahulk644/Appflowy-MCP-Server (8 stars, last pushed today), licensed MIT. It adds 833 tokens to every session, about $0.0033 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 2026-11-10.

Related

Appflowy-MCP-Server AGENTS.md compared with instructions from other repositories

Appflowy-MCP-Server AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
Appflowy-MCP-Server AGENTS.mdRahulk644/Appflowy-MCP-ServerInstructions file8todayMITA833Codex, 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 file195ktodayMITA5,649GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,093GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA2,022GitHub Copilot