Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/apocryphalword/kindroidmcp/claude-mdgit clone --depth 1 https://github.com/ApocryphalWord/KindroidMCPWrote 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.
[](https://agentmods.dev/instructions/apocryphalword/kindroidmcp/claude-md)<a href="https://agentmods.dev/instructions/apocryphalword/kindroidmcp/claude-md"><img src="https://agentmods.dev/badge/instructions/apocryphalword/kindroidmcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.01040 | $0.01040 |
| Opus 5 | $0.00520 | $0.00520 |
| Sonnet 5 | $0.00208 | $0.00208 |
| Haiku 4.5 | $0.00104 | $0.00104 |
Grade A, and why
KindroidMCP CLAUDE.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 6d 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.
How it starts
The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Project Overview
Kindroid MCP Server — a TypeScript MCP (Model Context Protocol) server that enables Claude to interact with the Kindroid AI platform. Supports two deployment modes: local (stdio) and remote (HTTP with OAuth 2.1).
Build & Run
npm run build # Compile TypeScript (tsc)
npm run start # Run production server (node dist/index.js)
npm run dev # Watch mode for development (tsc --watch)
No test or lint scripts are configured.
Project Structure
src/
index.ts # Server entry point, stdio/HTTP transport setup
kindroid-client.ts # Kindroid API client wrapper (api.kindroid.ai/v1)
oauth.ts # OAuth 2.1 + PKCE implementation for remote mode
tools/ # MCP tool definitions (19 tools, one per file, Zod schemas)
index.ts # Tool registration entry point
tool-utils.ts # Shared error-handling wrapper for tool handlers
manifest.json # MCP manifest for mcpb packaging
Output compiles to dist/. Docker + Railway deployment supported via Dockerfile and railway.json.
Key Conventions
- TypeScript strict mode enabled (
tsconfig.json). Target ES2022, module Node16. - Three runtime dependencies:
@modelcontextprotocol/sdk,express,zod. - No test framework or linter currently configured.
- Environment variables:
KINDROID_API_KEY(required),OAUTH_CLIENT_ID+OAUTH_CLIENT_SECRET(required for remote),PORT(default 3000),TRANSPORT(set to "stdio" for local mode). See.env.example. - OAuth tokens are in-memory only — they reset on server restart.
- Tools are registered in
src/tools/index.tsusing Zod for parameter validation. - API calls go through
src/kindroid-client.tswith Bearer token auth. Most endpoints are POST; the client also supports GET viarequestGetWithRetry(used byget_chat_messages).
MCP Tools
send_message— Send a message to a Kin (supports media attachments)create_kin— Create a new Kindroid AI companionupdate_kin— Update a Kin's profile (backstory, memories, directives, context, avatar settings)request_selfie— Request a solo selfie image of a Kinrequest_group_selfie— Request a group selfie of multiple Kins and/or the userchat_break— Clear conversation historycheck_subscription— Check account subscription statuscreate_journal_entry— Create a journal entry with key phrases for contextual Kin recallcreate_groupchat— Create a group chat with multiple Kins (name, context, directive, turn-taking, memory settings)update_groupchat— Update a group chat's settings (participants, name, context, directive, memory settings)send_groupchat_message— Send a user message to a group chatgroupchat_get_turn— Get which Kin should respond next in a group chatgroupchat_ai_response— Request a specific Kin to respond in a group chatsuggest_user_message— Get a suggested message for the user to send to a Kinsuggest_user_group_message— Get a suggested message for the user to send in a group chatupdate_user_profile— Update user profile fields (name, gender, backstory, avatar) or set the active personaget_chat_messages— Retrieve chat history for a Kin or group chat (oldest first, cursor pagination)rewind_messages— Remove the most recent messages from a Kin's solo chat or a group chat (an undo)groupchat_chat_break— Start a new conversation in a group chat, resetting short-term memory (greeting required)
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.
- 6d ago First seen · 74 lines · 1,040 tokens per session scan A 19c40b1cc412
KindroidMCP CLAUDE.md is an instructions file published in the GitHub repository ApocryphalWord/KindroidMCP (10 stars, last pushed 3mo ago), licensed MIT. It adds 1,040 tokens to every session, about $0.0052 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 2026-08-31.
Other instructions, from other repositories
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
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.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.