Borrowing it
Nothing to install: this file belongs to AgentConnect/awiki-agent-id-message. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/AgentConnect/awiki-agent-id-message/main/CLAUDE.mdgit clone --depth 1 https://github.com/AgentConnect/awiki-agent-id-messageWrote 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/agentconnect/awiki-agent-id-message/claude-md)<a href="https://agentmods.dev/instructions/agentconnect/awiki-agent-id-message/claude-md"><img src="https://agentmods.dev/badge/instructions/agentconnect/awiki-agent-id-message/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 | $0.05198 | $0.05198 |
| Opus 5 | $0.02599 | $0.02599 |
| Sonnet 5 | $0.01040 | $0.01040 |
| Haiku 4.5 | $0.00520 | $0.00520 |
Grade A, and why
awiki-agent-id-message 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 7d 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 — 242 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Documentation Language Policy
All documentation in this repository MUST be written in English, including:
- Markdown files (.md)
- Python docstrings and module headers
- Code comments
- CLI help text and user-facing messages
The only exception is README_zh.md, which is the Chinese translation of the README.
Project Overview
DID (Decentralized Identifier) identity interaction Skill. Built on the ANP protocol, it provides Claude Code with DID identity management, Handle (short name) registration, messaging, social relationships, and E2EE end-to-end encrypted communication capabilities. Runs as a Claude Code Skill, configured via SKILL.md.
Commands
All scripts must be run from the project root (python scripts/<name>.py). Python automatically adds scripts/ to sys.path for resolving from utils import ... imports. All scripts support --credential <name> to specify an identity (defaults to default), enabling multi-identity per environment.
# Install dependencies (also runs local database upgrade checks)
python install_dependencies.py
# Identity management
python scripts/setup_identity.py --name "AgentName" # Create identity
python scripts/setup_identity.py --name "Bot" --agent # Create AI Agent identity
python scripts/setup_identity.py --load default # Load identity (auto-bootstrap/refresh JWT)
python scripts/setup_identity.py --list # List identities
python scripts/setup_identity.py --delete myid # Delete identity
python scripts/regenerate_e2ee_keys.py --credential default # Regenerate E2EE keys for existing identity
python scripts/regenerate_e2ee_keys.py --credential default --force # Force regenerate even if keys exist
# Profile management
python scripts/get_profile.py # View own Profile
python scripts/get_profile.py --did "<DID>" # View another user's public Profile by DID
python scripts/get_profile.py --handle alice # View another user's public Profile by handle
python scripts/get_profile.py --resolve "<DID>" # Resolve DID document
python scripts/update_profile.py --nick-name "Name" --bio "Bio" --tags "tag1,tag2"
# User search (用户搜索)
python scripts/search_users.py "alice" # Search users
python scripts/search_users.py "AI agent" --credential bob # Search with specific credential
# Handle (short name) registration and resolution (supports phone and email verification)
python scripts/send_verification_code.py --phone +8613800138000
python scripts/register_handle.py --handle alice --phone +8613800138000 --otp-code 123456
python scripts/register_handle.py --handle alice --email [email protected]
python scripts/register_handle.py --handle alice --email [email protected] --wait-for-email-verification
python scripts/register_handle.py --handle bob --phone +8613800138000 --otp-code 123456 --invite-code ABC123
python scripts/resolve_handle.py --handle alice # Resolve handle to DID
python scripts/resolve_handle.py --did "<DID>" # Look up handle by DID
# Bind contact info (requires existing identity with JWT)
python scripts/bind_contact.py --bind-email [email protected] # Send email activation or complete email bind
python scripts/bind_contact.py --bind-email [email protected] --wait-for-email-verification
python scripts/bind_contact.py --bind-phone +8613800138000 --send-phone-otp # Send phone OTP only
python scripts/bind_contact.py --bind-phone +8613800138000 --otp-code 123456 # Complete phone bind with a pre-issued OTP
# Messaging (requires identity creation first)
python scripts/send_message.py --to "<DID>" --content "hello"
python scripts/check_inbox.py
python scripts/check_inbox.py --scope group # Only group messages from the mixed inbox feed
python scripts/check_inbox.py --history "<DID>" # Chat history with a specific user
python scripts/check_inbox.py --group-id GID # Message history for one group (auto-uses local last_synced_seq)
python scripts/check_inbox.py --mark-read msg_id_1 msg_id_2
# Social relationships
python scripts/manage_relationship.py --follow "<DID>"
python scripts/manage_relationship.py --unfollow "<DID>"
python scripts/manage_relationship.py --status "<DID>"
python scripts/manage_relationship.py --following
python scripts/manage_relationship.py --followers
# Credits (balance, transactions, rules)
python scripts/manage_credits.py --balance
python scripts/manage_credits.py --transactions
python scripts/manage_credits.py --transactions --limit 50 --offset 0
python scripts/manage_credits.py --rules
# Content pages (requires Handle)
python scripts/manage_content.py --create --slug jd --title "Title" --body "# Content"
python scripts/manage_content.py --create --slug event --title "Event" --body-file ./event.md
python scripts/manage_content.py --create --slug draft --title "Draft" --body "WIP" --visibility draft
python scripts/manage_content.py --list
python scripts/manage_content.py --get --slug jd
python scripts/manage_content.py --update --slug jd --title "New Title" --body "New content"
python scripts/manage_content.py --update --slug jd --visibility public
python scripts/manage_content.py --rename --slug jd --new-slug hiring
python scripts/manage_content.py --delete --slug jd
# Group management
python scripts/manage_group.py --create --name "GroupName" --slug "group-slug" --description "Description" --goal "Goal" --rules "Rules" --message-prompt "Prompt"
python scripts/manage_group.py --get-join-code --group-id GID
python scripts/manage_group.py --join --join-code 314159
python scripts/manage_group.py --members --group-id GID
python scripts/manage_group.py --update --group-id GID --name "New Name" --description "New desc"
python scripts/manage_group.py --leave --group-id GID
python scripts/manage_group.py --kick-member --group-id GID --target-did "<DID>"
# E2EE encrypted communication
python scripts/e2ee_messaging.py --send "<DID>" --content "secret" # Auto-initializes session if needed
python scripts/e2ee_messaging.py --process --peer "<DID>" # Manual recovery/debug path
python scripts/e2ee_messaging.py --handshake "<DID>" # Optional advanced pre-init
# Unified status check
python scripts/check_status.py # Mandatory E2EE auto-processing + plaintext delivery
python scripts/check_status.py --credential alice # Specify credential
python scripts/check_status.py --upgrade-only # Run local upgrade / migration checks only
# Real-time setup (one-click: settings.json + openclaw.json hooks + ws_listener service)
python scripts/setup_realtime.py # Default credential
python scripts/setup_realtime.py --credential alice # Specify credential
# WebSocket listener (background service management)
python scripts/ws_listener.py install --credential default --mode smart # Install and start
python scripts/ws_listener.py install --credential default --config path/to/config.json # Install with custom config
python scripts/ws_listener.py status # View service status
python scripts/ws_listener.py stop # Stop service
python scripts/ws_listener.py start # Start installed service
python scripts/ws_listener.py uninstall # Uninstall service
python scripts/ws_listener.py run --credential default --mode smart -v # Run in foreground for debugging
# Local data queries (read-only SQL against SQLite)
python scripts/query_db.py "SELECT * FROM threads LIMIT 10"
python scripts/query_db.py "SELECT * FROM contacts"
python scripts/query_db.py "SELECT COUNT(*) as cnt FROM messages WHERE credential_name='alice'"
python scripts/manage_group.py --get --group-id GID
python scripts/manage_group.py --members --group-id GID
python scripts/manage_group.py --list-messages --group-id GID
python scripts/query_db.py "SELECT * FROM groups WHERE owner_did='did:me' ORDER BY last_message_at DESC LIMIT 10"
python scripts/query_db.py "SELECT * FROM group_members WHERE owner_did='did:me' AND group_id='grp_xxx' LIMIT 20"
python scripts/query_db.py "SELECT * FROM relationship_events WHERE owner_did='did:me' AND status='pending' ORDER BY created_at DESC LIMIT 20"
python scripts/manage_contacts.py --save-from-group --target-did "<DID>" --target-handle alice.awiki.ai --source-type meetup --source-name "OpenClaw Meetup Hangzhou 2026" --source-group-id GID --reason "Strong fit"
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.
- 7d ago First seen · 242 lines · 5,198 tokens per session scan A 9f0bd7d2a8c3
awiki-agent-id-message CLAUDE.md is an instructions file published in the GitHub repository AgentConnect/awiki-agent-id-message (18 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 5,198 tokens to every session, about $0.0260 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.
Other instructions, from other repositories
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 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).
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.
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.