A workbench that classifies coding tasks by difficulty and recommends different language models for them. It also analyzes model usage and projected savings.

Use it to scan model costs, score prompts, audit skills, pin routing choices, apply environment settings, and run routing tests.

It helps route simpler work to less expensive models while reserving more capable models for harder tasks.

brain — Skill for Claude Code and Codex by itsribbZ: A workbench that classifies coding tasks by difficulty and…

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 skills/itsribbz/godspeed/brain

Any agent

npx skills add itsribbZ/Godspeed --skill brain

Clone the repo

git clone --depth 1 https://github.com/itsribbZ/Godspeed

Made for: Claude Code, Codex.

Or install godspeed, the plugin that ships this one along with the rest of its 18 skills, 3 commands, 1 agent, 5 hooks.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/itsribbz/godspeed/brain.svg)](https://agentmods.dev/skills/itsribbz/godspeed/brain)

Your own site

<a href="https://agentmods.dev/skills/itsribbz/godspeed/brain"><img src="https://agentmods.dev/badge/skills/itsribbz/godspeed/brain.svg" alt="Measured on agentmods" height="20"></a>

Per session 99 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,032 The whole file, excluding the scripts and references it only reads on demand.

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.

Model	Per session	Once invoked
Fable 5	$0.00099	$0.01032
Opus 5	$0.00049	$0.00516
Sonnet 5	$0.00020	$0.00206
Haiku 4.5	$0.00010	$0.00103

Measured 3d ago against content hash 9ce7297b4e89, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

brain 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 3d ago.

The scan reads SKILL.md. This mod also ships 4 executable files (brain_cli.py, brain_learner.py, manifest_to_json.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

plugins/godspeed/automations/brain/SKILL.md · 97 lines

How it starts

The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Brain — Workbench

This skill is the user-facing entry point for the Brain model router. All commands are thin wrappers around brain_cli.py.

Canonical location

${CLAUDE_PLUGIN_ROOT}/automations/brain/brain_cli.py

The Brain has three layers:

Classifier — severity_classifier.py (pure Python, stdlib only)
Manifest — routing_manifest.toml (single source of truth for weights, tiers, guardrails, skill assignments)
Workbench — brain_cli.py (this skill's backend)

Plus two hooks that wire into Claude Code:

brain_advisor.sh (UserPromptSubmit) — logs classification + emits model advisory
brain_tools_hook.sh (PostToolUse) — logs tool call metadata for brain scan

Commands

`brain scan`

30-day cost analysis + routing savings projection. Reads ~/.claude/stats-cache.json and applies current Anthropic pricing to compute actual cost, then projects what would be saved by routing 50% of Opus → Sonnet and 20% → Haiku.

python "${CLAUDE_PLUGIN_ROOT}/automations/brain/brain_cli.py" scan

`brain score TEXT`

Classify an arbitrary prompt and show the full signal breakdown with bar chart.

python "${CLAUDE_PLUGIN_ROOT}/automations/brain/brain_cli.py" score "refactor auth module across 5 files"

`brain audit-skills`

Show every skill and its assigned routing tier. Flags any skills in ~/.claude/skills/ that don't have a tier assigned yet.

python "${CLAUDE_PLUGIN_ROOT}/automations/brain/brain_cli.py" audit-skills

`brain pin SKILL [--write]`

Add model: and effort: frontmatter to a skill file based on its assigned tier in the manifest. Dry-run by default; add --write to apply.

# Dry-run
python "${CLAUDE_PLUGIN_ROOT}/automations/brain/brain_cli.py" pin verify

# Apply
python "${CLAUDE_PLUGIN_ROOT}/automations/brain/brain_cli.py" pin verify --write

`brain apply-env`

Print shell env exports to source. These enable Zone 2 automatic routing:

CLAUDE_CODE_SUBAGENT_MODEL=sonnet — all subagents default to Sonnet
CLAUDE_CODE_EFFORT_LEVEL=max — persist /effort max across sessions
ANTHROPIC_DEFAULT_HAIKU_MODEL — pin background Haiku version

Read the full file on GitHub · 97 lines

Files

What ships with it

6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

3d ago First seen · 97 lines · 99 tokens per session scan A 9ce7297b4e89

Subscribe to this mod's changes

brain is a skill published in the GitHub repository itsribbZ/Godspeed (1 stars, last pushed 2mo ago), licensed MIT. It adds 99 tokens to every session and 1,032 once invoked, about $0.0005 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.

Analytics and metrics Cost Optimization Data and AI ai-agents anthropic claude claude-code claude-code-plugin

clawrouter

Hosted-gateway LLM router — save 84% on inference costs. A local proxy that forwards each request to the blockrun.ai gateway, which routes to the cheapest capable model across 76 models from OpenAI, Anthropic, Google, DeepSeek, xAI, Z.AI, and more. 7 free open-weight models included. Also exposes realtime market data…

BlockRunAI/ClawRouter · 222 tokens

brain