toke

toke is a command for coding agents from itsribbZ/Godspeed. It costs 20 tokens per session (933 once invoked), scanned B, original, MIT.

A command that displays a one-screen status dashboard for the Toke workbench. It reports Brain and Homer status, current session tokens, a progress counter, and pipeline files.

In plain words
What is it for?
Use `/toke` to check the default status, or provide a subcommand when supported by the workbench.
Why use it?
It gathers several separate status checks into one compact view, so you do not need to inspect each part manually.

Command

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 commands/itsribbz/godspeed/toke
Clone the repo
git clone --depth 1 https://github.com/itsribbZ/Godspeed

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 toke

README.md
[![agentmods](https://agentmods.dev/badge/commands/itsribbz/godspeed/toke.svg)](https://agentmods.dev/commands/itsribbz/godspeed/toke)
Your own site
<a href="https://agentmods.dev/commands/itsribbz/godspeed/toke"><img src="https://agentmods.dev/badge/commands/itsribbz/godspeed/toke.svg" alt="Measured on agentmods" height="20"></a>
Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 933 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 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 $0.00020 $0.00933
Opus 5 $0.00010 $0.00466
Sonnet 5 $0.00004 $0.00187
Haiku 4.5 $0.00002 $0.00093

Measured 4d ago against content hash b6d1cbc086e7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

toke scanned grade B 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 4d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

4. `cat ~/.claude/telemetry/brain/godspeed_count.txt 2>&1` — godspeed tick
toke/commands/toke.md · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/toke — Toke Meta-Automation Workbench

Arguments received: $ARGUMENTS

You are running the /toke workbench command. Treat the user's argument (if any) as the subcommand. Default is status. Run the appropriate commands below in parallel where possible and render ONE compact dashboard at the end — no preamble, no narration.

Subcommand: status (default)

Run these in parallel via the Bash tool, then render the dashboard:

  1. python $TOKE_ROOT/automations/brain/brain_cli.py scan 2>&1 | head -35 — Brain cost + v2 learning state
  2. python $TOKE_ROOT/automations/homer/homer_cli.py status 2>&1 — Homer layer readiness
  3. python $TOKE_ROOT/tokens/token_snapshot.py --current 2>&1 — current session tokens
  4. cat ~/.claude/telemetry/brain/godspeed_count.txt 2>&1 — godspeed tick
  5. ls $TOKE_ROOT/pipeline/ $TOKE_ROOT/tokens/ 2>&1 — charter coverage

Render output in this exact format (ASCII, no emojis unless the user asked):

╔═════════════════════════════════════════════════════════════╗
║  TOKE WORKBENCH — <date>                                   ║
╠═════════════════════════════════════════════════════════════╣
║ BRAIN    $<total>/mo | 30d Opus <pct>% | decisions <N>     ║
║ HOMER    <shipped>/<total> layers | VAULT <N> checkpoints  ║
║ SESSION  <turns> turns | <cache_hit>% hit | $<est>         ║
║ PIPELINE <n>/7 stages  | TOKENS <n> files                  ║
║ TICK     <count> | next auto-scan at <next>                 ║
╠═════════════════════════════════════════════════════════════╣
║  v2 LEARNING: <N> decisions | <M> tools | <K> overrides    ║
║  ACHIEVABLE SAVINGS: $<x>/mo (Zone 2)                       ║
║  THEATER (confirmed): 4 kills parked, per-item greenlight   ║
╚═════════════════════════════════════════════════════════════╝

Followed by a single line: Next best move: <one specific next action from project_status.md or obvious gap>.

Subcommand: scan

Run python $TOKE_ROOT/automations/brain/brain_cli.py scan and echo its full output. No additional rendering.

Read the full file on GitHub · 71 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. 4d ago First seen · 71 lines · 20 tokens per session scan B b6d1cbc086e7

Subscribe to this mod's changes

toke is a command published in the GitHub repository itsribbZ/Godspeed (1 stars, last pushed 2mo ago), licensed MIT. It adds 20 tokens to every session and 933 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.