trustclaw CLAUDE.md

trustclaw CLAUDE.md is an instructions file for Claude Code from ComposioHQ/trustclaw. It costs 6,071 tokens per session, scanned A, original, MIT.

A project instruction file for TrustClaw, a self-hosted personal AI agent with memory, connected tools, and a Telegram bot, built with Next.js.

In plain words
What is it for?
Use it when changing the dashboard, login system, server procedures, AI integrations, memory, or Telegram-related features.
Why use it?
It gives the agent the project's architecture and tells it where backend logic, authentication, date handling, and library documentation belong.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions CLAUDE.md.

Install

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.

agentmods
npx agentmods add instructions/composiohq/trustclaw/claude-md
Clone the repo
git clone --depth 1 https://github.com/ComposioHQ/trustclaw

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 trustclaw CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/composiohq/trustclaw/claude-md.svg)](https://agentmods.dev/instructions/composiohq/trustclaw/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/composiohq/trustclaw/claude-md"><img src="https://agentmods.dev/badge/instructions/composiohq/trustclaw/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 6,071 This file is loaded in full into every session.
When invoked 6,071 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.06071 $0.06071
Opus 5 $0.03036 $0.03036
Sonnet 5 $0.01214 $0.01214
Haiku 4.5 $0.00607 $0.00607

Measured 6d ago against content hash 7caca3c66715, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

trustclaw 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.

CLAUDE.md · 652 lines

How it starts

The opening of the file, as written. The whole thing — 652 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Product overview

TrustClaw - a self-hostable personal AI agent with vector memory, Composio tools, and a Telegram bot.

Tech Stack

When you need to look up documentation for any of these libraries, use the Context7 MCP (mcp__plugin_context7_context7__resolve-library-idmcp__plugin_context7_context7__query-docs) to get up-to-date docs. For shadcn/ui specifically, use the shadcn MCP tools instead.

Architecture

This dashboard uses a single tRPC backend running within Next.js. Auth is handled by Better Auth with username/password. Composio functionality is accessed server-side using a global API key. All LLM and embedding calls route through Vercel AI Gateway via plain string model IDs (e.g., 'claude-sonnet-4-5-20250929'). Auth uses VERCEL_OIDC_TOKEN on Vercel deployments, or AI_GATEWAY_API_KEY for local dev.

tRPC (Backend)

  • Runs within the Next.js app (src/server/api/)
  • Handles all data fetching, mutations, and business logic
  • Access via trpc.* hooks from ~/clients/trpc/react
  • Composio SDK calls happen inside tRPC procedures using the global COMPOSIO_API_KEY

Better Auth

  • Server config at src/server/auth.ts
  • Route handler at src/app/api/auth/[...all]/route.ts
  • Client module at src/clients/auth/react.tsx (exports authClient from better-auth/react)
  • Username/password login via Better Auth (no OAuth providers)
  • Session model: { user, session } (no org/project)
┌─────────────────────────────────────────────────────────┐
│                    Next.js Dashboard                    │
├─────────────────────────────────────────────────────────┤
│  tRPC Client          │       Better Auth Client        │
│  ~/clients/trpc       │       ~/clients/auth            │
└──────────┬────────────┴──────────────┬──────────────────┘
           │                           │
           ▼                           ▼
┌──────────────────────┐    ┌─────────────────────────────┐
│   tRPC Server        │    │     Better Auth Server      │
│   (Next.js API)      │    │   src/server/auth.ts        │
│                      │    │   + username/password       │
└──────────────────────┘    └─────────────────────────────┘

Read the full file on GitHub · 652 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. 6d ago First seen · 652 lines · 6,071 tokens per session scan A 7caca3c66715

Subscribe to this mod's changes

trustclaw CLAUDE.md is an instructions file published in the GitHub repository ComposioHQ/trustclaw (890 stars, last pushed 1mo ago), licensed MIT. It adds 6,071 tokens to every session, about $0.0304 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.

Related

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).

microsoft/vscode · 6,785 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 · 5,182 tokens

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).

microsoft/vscode · 5,001 tokens

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.

github/spec-kit · 7,104 tokens

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

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.

langchain-ai/langchain · 4,469 tokens