oracle-author

oracle-author is an agent for Claude Code from sliamh11/Deus. It costs 0 tokens per session (1,307 once invoked), scanned A, original, MIT.

A test-writing role that creates the expected-behaviour test from the specification before anyone writes the code. It stays separate from the implementation so the test can independently check the result.

In plain words
What is it for?
Use it to define red-green tests for changes that could affect many parts of a system, without inspecting the planned implementation.
Why use it?
It reduces the risk that the same person makes matching mistakes in both the code and its tests. The test is advisory rather than a required commit check.

Agent for Claude Code

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 agents/sliamh11/deus/oracle-author
Clone the repo
git clone --depth 1 https://github.com/sliamh11/Deus

Made for: Claude Code.

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-author

README.md
[![agentmods](https://agentmods.dev/badge/agents/sliamh11/deus/oracle-author.svg)](https://agentmods.dev/agents/sliamh11/deus/oracle-author)
Your own site
<a href="https://agentmods.dev/agents/sliamh11/deus/oracle-author"><img src="https://agentmods.dev/badge/agents/sliamh11/deus/oracle-author.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,307 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 $0.00000 $0.01307
Opus 5 $0.00000 $0.00654
Sonnet 5 $0.00000 $0.00261
Haiku 4.5 $0.00000 $0.00131

Measured 3d ago against content hash 74d14ec43e23, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

oracle-author 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.

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.

.claude/agents/oracle-author.md · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Dispatch note (2026-07-15): this role runs on GPT-5.6-Sol via scripts/dispatch-oracle-author.sh, not the model: sonnet default above — that frontmatter field is no longer the live dispatch route for this role. The point is model diversity from whichever model implements the change, so the oracle's errors don't correlate with the implementation's. The instructions below are unchanged and apply regardless of which model executes them.

You are the oracle-author Warden. You write the discriminating test — the oracle — for a change, from the specification, before any implementation exists. You do not implement. Your entire value is independence: if the same agent writes the code and the test, their errors correlate and the test rubber-stamps the bug. By authoring the oracle blind to the implementation, you make the test's failures independent of the implementation's failures — which is what makes a passing test actually mean something.

At invocation, read first

  1. Standards~/deus/.claude/wardens/standards.md. The quality floor and mindset.
  2. Rules~/deus/.claude/wardens/oracle-rules.md. The oracle-quality checklist. Apply every item; this spec does not restate it.

Inputs (what the caller must pass you)

  • The spec — the requirement, acceptance criteria, or issue body for the change under test.
  • The existing public surface (read-only) — current signatures, schemas, and call sites that predate this change, so you can write a test that compiles against the real API.
  • NOT the implementation — the new production code for this change must never enter your context. A caller who includes it poisons your independence (see the guard below).

The Iron Law

NO IMPLEMENTATION. You produce a failing test and the expected behavior — never the code that makes it pass.

Invocation-order guard

You must run before the implementation exists; seeing it destroys your independence. STOP and refuse if ANY of these appear in your context:

Read the full file on GitHub · 79 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. 3d ago First seen · 79 lines · 0 tokens per session scan A 74d14ec43e23

Subscribe to this mod's changes

oracle-author is an agent published in the GitHub repository sliamh11/Deus (51 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,307 tokens. 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 2026-08-30.

Related

Other agents, from other repositories

gtd-research-processor

Autonomous research agent that fetches URLs, analyzes content, creates literature notes with progressive summarization, and generates atomic zettels. Invoked by ai-task-executor for :AI:research: tagged tasks.

datacore-one/datacore · 50 tokens

ai-task-executor

Core 24/7 autonomous task execution hub that scans nextactions.org for :AI: tagged tasks, routes them to specialized GTD agents based on task type, handles execution outcomes, logs to journal, and updates org-mode task states. Returns JSON responses with detailed success/failure reporting.

datacore-one/datacore · 63 tokens

create-module

Create or convert code into a spec-aligned Datacore module. Use cases: Create a new module from scratch Convert existing code to a module Audit an existing module for spec alignment This agent ensures modules follow best practices: Conversational commands (not CLI wrappers) Proper settings in module.yaml Layered…

datacore-one/datacore · 90 tokens

gtd-content-writer

Autonomous content generation agent that creates blog posts, emails, social media content, documentation, and marketing materials. Generates drafts ready for human review. Invoked by ai-task-executor for :AI:content: tagged tasks.

datacore-one/datacore · 51 tokens

gtd-inbox-processor

Use this agent when you need to process individual entries from inbox.org in a GTD (Getting Things Done) system. This agent should be invoked:\n\n- After capturing new items to inbox.org and wanting to process them into the appropriate action lists\n- When conducting a GTD review and need to clear the inbox…

datacore-one/datacore · 572 tokens

gtd-project-manager

Autonomous project coordination agent that tracks project status, identifies blockers and dependencies, calculates completion percentages, flags timeline risks, and suggests follow-up tasks. Proactively escalates blockers older than 7 days. Invoked by ai-task-executor for :AI:pm: tagged tasks.

datacore-one/datacore · 61 tokens