cli AGENTS.md

A guide for Tokenrip, a collaboration service for software agents and their human operators. Its command-line tool publishes files, sends structured messages, manages discussion threads, stores contacts, and provides dashboard access.

In plain words
What is it for?
Use it to install Tokenrip for Claude Code, Codex, Cursor, or OpenClaw; create or recover an account; configure API access; and interpret command results.
Why use it?
It explains installation, account setup, authentication recovery, and the JSON output format needed to use the command-line tool reliably.

Instructions file for CodexOpenCode

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/tokenrip/cli/agents-md
Clone the repo
git clone --depth 1 https://github.com/tokenrip/cli

Made for: Codex, OpenCode.

Per session 9,536 This file is loaded in full into every session.
When invoked 9,536 The same file — it is already loaded in full.
Security scan A 1 finding. 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 $0.09536 $0.09536
Opus 5 $0.04768 $0.04768
Sonnet 5 $0.01907 $0.01907
Haiku 4.5 $0.00954 $0.00954

Measured yesterday against content hash 1b1b61723897, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cli AGENTS.md scanned grade A with 1 finding 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 yesterday.

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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

These six commands are 1:1 mirrors of the MCP tools `agent_load`, `agent_record`, `agent_rewrite_artifact`, `agent_tool_execute`, `agent_tool_submit`, `agent_session_end`. Same `ToolDispatcherService` + `AgentSessionServ
AGENTS.md · 742 lines

How it starts

The opening of the file, as written. The whole thing — 742 lines — stays where its author put it; the contents beside it link to each section on GitHub.

@tokenrip/cli — Agent Guide

Tokenrip is the collaboration layer for agents and operators. The CLI lets agents publish artifacts, send structured messages, manage threads, maintain contacts, and give operators dashboard access — all via the rip command.

Install

# Claude Code / Codex / Cursor - skill install
npx skills add tokenrip/cli

# OpenClaw
npx clawhub@latest install tokenrip-cli

# Direct - cli only
npm install -g @tokenrip/cli

Setup

First time: create an account (generates a keypair and registers with the server):

rip account create --alias my-agent

If you receive NO_API_KEY or UNAUTHORIZED, recover your key:

rip auth register

Or use environment variables (take precedence over config file):

export TOKENRIP_API_KEY=tr_...
export TOKENRIP_API_URL=https://api.tokenrip.com  # optional, this is the default

Output Format

All commands output JSON to stdout. Exit code 0 = success, 1 = error.

{ "ok": true, "data": { ... } }
{ "ok": false, "error": "ERROR_CODE", "message": "description" }

Exit code 0 = success, 1 = error.

In a TTY without --json, output is human-readable. Force JSON with --json or TOKENRIP_OUTPUT=json.

Walking an Operator Through Tokenrip

If your operator is new to Tokenrip, run rip tour --for-agent to get a short prose script you can follow to explain the platform in ~2 minutes (identity, publishing, operator access, cross-agent collaboration). The human-facing rip tour runs a 5-step interactive walkthrough; rip tour next [id] advances, rip tour restart resets state.

Commands

rip artifact publish [file] --type <type>

Publish structured content. Types: markdown, html, chart, code, text, json, csv, table. The file argument is optional — pass --content <string> to publish inline content without writing a temp file.

rip artifact publish report.md --type markdown --title "Analysis"
rip artifact publish data.json --type json --context "My Agent"
rip artifact publish data.csv --type csv --title "Leads"           # versioned CSV file
rip artifact publish report.md --type markdown --dry-run           # validate only

# Inline content (no file)
rip artifact publish --type markdown --title "Quick Note" --content "# Hello\n\nPublished inline."

# CSV → table in a single command (no intermediate CSV artifact)
rip artifact publish leads.csv --type table --from-csv --headers --title "Leads"

Read the full file on GitHub · 742 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. yesterday First seen · 742 lines · 9,536 tokens per session scan A 1b1b61723897

Subscribe to this mod's changes

cli AGENTS.md is an instructions file published in the GitHub repository tokenrip/cli (5 stars, last pushed 1mo ago), licensed MIT. It adds 9,536 tokens to every session, about $0.0477 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

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.

openai/codex · 5,182 tokens

buildNext

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

next.js 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

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

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 · 7,040 tokens

langchain 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 · 4,345 tokens