oracle

oracle is a skill for Claude Code, Codex from itsribbZ/Godspeed. It costs 60 tokens per session (1,494 once invoked), scanned B, original, MIT.

A review tool for checking generated Markdown against a fixed set of quality and safety rules. It gives the text a score, a pass or fail result, and notes suspicious claims or changes from a baseline.

In plain words
What is it for?
Use it to evaluate generated reports, plans, or other Markdown text, compare results with earlier versions, and identify sections that need revision.
Why use it?
It helps catch exaggerated wording, unsafe actions, missing evidence, and quality regressions before generated content is accepted.

Skill for Claude CodeCodex

Part of the godspeed plugin — 18 skills, 3 commands, 1 agent, 5 hooks shipped together

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/oracle
Any agent
npx skills add itsribbZ/Godspeed --skill oracle
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.

agentmods badge for oracle

README.md
[![agentmods](https://agentmods.dev/badge/skills/itsribbz/godspeed/oracle.svg)](https://agentmods.dev/skills/itsribbz/godspeed/oracle)
Your own site
<a href="https://agentmods.dev/skills/itsribbz/godspeed/oracle"><img src="https://agentmods.dev/badge/skills/itsribbz/godspeed/oracle.svg" alt="Measured on agentmods" height="20"></a>
Per session 60 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,494 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 $0.00060 $0.01494
Opus 5 $0.00030 $0.00747
Sonnet 5 $0.00012 $0.00299
Haiku 4.5 $0.00006 $0.00149

Measured 5d ago against content hash ce650fb47472, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

oracle 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 5d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (oracle.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.

Recursive force deletemediumDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

| **#2 No delete** | hard | "I deleted", "rm -rf", "unilaterally deleted" (mitigated by "backed up", "greenlit", "explicit consent") |

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

plugins/godspeed/automations/homer/oracle/SKILL.md · 126 lines

How it starts

The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Oracle — The Critic of Homer

Oracle scores every Homer output. Nothing ships without her verdict. She is Homer's introspection layer — the moat against hype, theater, and sacred-rule drift.

Role

Oracle is Homer L7. Zeus invokes Oracle during Phase 4 (eval) to score a synthesized output. Oracle returns a ScoreReport with:

  • Overall score (0.0-1.0)
  • VerdictPASS / SOFT_FAIL / HARD_FAIL
  • Sacred rule checks — per-rule pass/fail + flagged patterns
  • Rubric score — quality floor (length / receipts / citations)
  • Theater flags — suspect sections and recommendation
  • Regressions — deltas against a baseline if provided

If verdict is HARD_FAIL or the score drops below 0.7, Zeus Phase 4 returns to Phase 1 for re-plan with Oracle's notes attached.

The 10 Sacred Rule Detection Heuristics

Rule Severity Red-flag patterns
#1 Truthful soft "amazing", "perfect", "100% guaranteed", "definitely"
#2 No delete hard "I deleted", "rm -rf", "unilaterally deleted" (mitigated by "backed up", "greenlit", "explicit consent")
#3 No revert hard "reverted the fix", "undid this", "rolled back the confirmed"
#4 Only asked hard "while I was at it", "took the liberty of", "took the opportunity to"
#5 Diagnostics are features hard "removed debug", "cleaned up diagnostic", "stripped out logger"
#6 No creative content hard "I wrote the dialogue", "invented names", "made up the character"
#7 Edit not Write hard "used Write to overwrite", "clobbered the file"
#8 No auto-close hard "auto-closing session", "ran close-session without"
#9 No options soft "option 1:", "three approaches to consider", "here are three ways"
#11 AAA quality soft "good enough", "this will do", "close enough", "quick and dirty"

Rules #10 (godspeed trigger) and #12 (rosetta) are structural — not detectable from output text alone — and are checked at the runtime level, not by Oracle.

Read the full file on GitHub · 126 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 · 126 lines · 60 tokens per session scan B ce650fb47472

Subscribe to this mod's changes

oracle is a skill published in the GitHub repository itsribbZ/Godspeed (1 stars, last pushed 2mo ago), licensed MIT. It adds 60 tokens to every session and 1,494 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.