local

local is a skill for Claude Code, Codex from itsribbZ/Godspeed. It costs 100 tokens per session (1,029 once invoked), scanned A, original, MIT.

A local-language-model workbench that routes some prompts to a Qwen model running through Ollama, a tool for running models on your own computer.

In plain words
What is it for?
Classifying prompts by tier, handling selected work with a local model, monitoring its confidence, and requesting approval before a critical handoff to Claude.
Why use it?
It lets suitable work stay on the local machine and sends control back to Claude when confidence is low and the user approves.

Skill for Claude CodeCodex

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/local
Any agent
npx skills add itsribbZ/Godspeed --skill local
Clone the repo
git clone --depth 1 https://github.com/itsribbZ/Godspeed

Made for: Claude Code, Codex.

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 local

README.md
[![agentmods](https://agentmods.dev/badge/skills/itsribbz/godspeed/local.svg)](https://agentmods.dev/skills/itsribbz/godspeed/local)
Your own site
<a href="https://agentmods.dev/skills/itsribbz/godspeed/local"><img src="https://agentmods.dev/badge/skills/itsribbz/godspeed/local.svg" alt="Measured on agentmods" height="20"></a>
Per session 100 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,029 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.

ModelPer sessionOnce invoked
Fable 5 $0.00100 $0.01029
Opus 5 $0.00050 $0.00515
Sonnet 5 $0.00020 $0.00206
Haiku 4.5 $0.00010 $0.00103

Measured 4d ago against content hash 74c050c4a447, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

local 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 4d ago.

The scan reads SKILL.md. This mod also ships 5 executable files (claude_override.py, confidence_monitor.py, local_cli.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.

toke/automations/local/SKILL.md · 115 lines

How it starts

The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Toke Local — Workbench

This skill is the entry point for Toke's local LLM automation. It runs alongside the existing Brain router — Brain classifies the prompt's tier, Local decides whether to handle it on-device.

Architecture

prompt
  ▼
brain.classify()           ← existing Toke brain
  ▼
tier ∈ {S0,S1,S2}? ────────────────────► local Qwen via Ollama
                                              ▼
tier ∈ {S3,S4,S5} ──► Claude (default)        confidence_monitor
                                              ▼
                                    is_critical (< 12.5%) ?
                                              │
                                          yes │   no
                                              ▼   ▼
                                       claude_override   return
                                          gate (y/n)
                                              ▼
                                       approved? → Claude
                                       declined? → use local

Canonical paths

  • CLI: $TOKE_ROOT/automations/local/local_cli.py
  • Manifest: $TOKE_ROOT/automations/local/local_manifest.toml
  • Decisions: ~/.claude/telemetry/local/local_decisions.jsonl

Commands

local query "prompt"

Run a prompt through the full pipeline: brain classification → local-eligible check → Qwen generation → confidence monitor → optional override.

python "$TOKE_ROOT/automations/local/local_cli.py" query "summarize the routing manifest"

local ping

Health check: is Ollama serving? Is the configured model present?

python "$TOKE_ROOT/automations/local/local_cli.py" ping

local stats [N]

Show aggregate stats from the last N decisions: override rate, approval rate, avg confidence, token savings vs all-Claude.

python "$TOKE_ROOT/automations/local/local_cli.py" stats 100

local config [key=value]

Show or update local_manifest.toml settings. With no args, prints current config.

Read the full file on GitHub · 115 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.

  1. 4d ago First seen · 115 lines · 0 tokens per session scan A 74c050c4a447

Subscribe to this mod's changes

local is a skill published in the GitHub repository itsribbZ/Godspeed (1 stars, last pushed 2mo ago), licensed MIT. It adds 100 tokens to every session and 1,029 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.

Related

Other skills, from other repositories

nano-banana-prompting

This skill should be used when crafting prompts for Nano Banana Pro (Gemini image generation). Use when users want help writing image generation prompts, need guidance on prompt structure, or want to optimize their prompts for better results.

NikiforovAll/claude-code-rules · 51 tokens

nano-banana

This skill should be used for Python scripting and Gemini image generation. Use when users ask to generate images, create AI art, edit images with AI, or run Python scripts with uv. Trigger phrases include "generate an image", "create a picture", "draw", "make an image of", "nano banana", or any image generation…

NikiforovAll/claude-code-rules · 73 tokens

optimize-prompt-token-efficiency

Iteratively optimizes prompts for token efficiency by maximizing information density - reduces verbosity, removes redundancy, tightens phrasing while preserving semantic content. Use when asked to compress, shorten, reduce tokens, tighten, maximize density, increase information density, or make a prompt more concise.

doodledood/manifest-dev · 63 tokens

compress-prompt

Compresses prompts/skills into minimal goal-focused instructions. Trusts the model, drops what it already knows, maximizes action space. Use when asked to compress, condense, or minimize a prompt.

doodledood/manifest-dev · 45 tokens

meta-prompting

Enhanced reasoning patterns via slash commands (/think, /verify, /adversarial, /edge, /compare, /confidence, /budget, /constrain, /json, /flip, /assumptions, /tensions, /analyze, /trade) or natural language ("argue against", "what could break", "show reasoning", "deep review", "meta-prompts", "thinking modes"…

iliaal/whetstone · 104 tokens

prompt-engineering

Create, update, review, or discuss an LLM prompt — a system prompt, a skill, or an agent. Use when writing or improving a prompt, discussing a skill or agent, diagnosing prompt failures, or when the user says a prompt needs work.

doodledood/manifest-dev · 56 tokens