aurora

aurora is a skill for Claude Code, Codex from itsribbZ/Godspeed. It costs 68 tokens per session (1,351 once invoked), scanned A, original, MIT.

A sleep-time analysis tool for an AI routing system. It reads recorded decisions and proposes how often different models, task levels, and safety checks should be selected.

In plain words
What is it for?
Use it to inspect routing statistics, measure uncertainty and correction rates, review safeguard activity, and prepare configuration changes for human approval.
Why use it?
Routing choices can drift without anyone noticing whether classifications or safeguards are firing too often or too rarely. The proposals are saved for review instead of being applied automatically.

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/aurora
Any agent
npx skills add itsribbZ/Godspeed --skill aurora
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 aurora

README.md
[![agentmods](https://agentmods.dev/badge/skills/itsribbz/godspeed/aurora.svg)](https://agentmods.dev/skills/itsribbz/godspeed/aurora)
Your own site
<a href="https://agentmods.dev/skills/itsribbz/godspeed/aurora"><img src="https://agentmods.dev/badge/skills/itsribbz/godspeed/aurora.svg" alt="Measured on agentmods" height="20"></a>
Per session 68 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,351 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 $0.00068 $0.01351
Opus 5 $0.00034 $0.00675
Sonnet 5 $0.00014 $0.00270
Haiku 4.5 $0.00007 $0.00135

Measured 5d ago against content hash 85fdb785b06c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

aurora 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 5d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (aurora.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/homer/sleep/aurora/SKILL.md · 113 lines

How it starts

The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Aurora — The Dawn Tuner

Aurora was the Roman goddess of the dawn — the one who arrives before everyone else is awake. In Homer, she runs before the user wakes up, mining last night's Brain telemetry and proposing weight adjustments for the next day.

Role

Aurora is a sleep-time agent (L6). She reads Brain's decisions.jsonl and computes:

  • Tier distribution (S0-S5 counts + percentages)
  • Model recommendation distribution (haiku / sonnet / opus)
  • Guardrail fire rates (which guardrails fire how often)
  • Uncertainty escalation rate (% of prompts where classifier was unsure)
  • Correction-detected rate (% of prompts flagged as corrections)
  • Average classifier confidence

From those stats, Aurora generates proposals for routing_manifest.toml weight adjustments. She never auto-applies. Every proposal lands in a dated JSON file for the user's review.

Proposal Rules (current ruleset)

Signal Threshold Proposal
uncertainty_escalated firing > 40% Medium severity Raise fail_open_tier from S3 to S4 OR raise confidence threshold
correction_detected > 5% High severity Bump correction_keywords weight in [signals]
Any guardrail firing > 20% Low severity Review threshold — possibly over-sensitive
Any guardrail firing 0× over 100+ decisions Low severity Verify still needed or retire
avg_confidence < 0.5 Medium severity Review signal weights; may need recalibration

Each proposal in the output JSON contains:

  • id — unique identifier
  • rationale — why Aurora proposes it
  • recommendation — what to change
  • severityhigh / medium / low
  • evidence — the raw numbers the proposal is based on

Input

  • Primary: ~/.claude/telemetry/brain/decisions.jsonl (written by brain_advisor.sh UserPromptSubmit hook)
  • Secondary: ~/.claude/telemetry/brain/advisor_calls.jsonl (when it exists — written by brain advise)
  • Reference: Toke/automations/brain/routing_manifest.toml (current weights)

Read the full file on GitHub · 113 lines

Files

What ships with it

1 file 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. 5d ago First seen · 113 lines · 68 tokens per session scan A 85fdb785b06c

Subscribe to this mod's changes

aurora is a skill published in the GitHub repository itsribbZ/Godspeed (1 stars, last pushed 2mo ago), licensed MIT. It adds 68 tokens to every session and 1,351 once invoked, about $0.0003 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.