A command-line tool that sends a prompt together with selected project files to another AI model for advice. It supports saved sessions and can use a browser-based model or an API.

Getting a second opinion on code, debugging, design, or repository questions while attaching only the files that contain the relevant context.

It gives the other model the specific repository context needed to reason about a coding task. Previewing the selected files helps avoid sending irrelevant code.

oracle — Skill for Claude Code and Codex by geezerrrr/motive

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.

Any agent

npx skills add geezerrrr/motive --skill oracle

Clone the repo

git clone --depth 1 https://github.com/geezerrrr/motive

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/geezerrrr/motive/oracle/github.svg)](https://agentmods.dev/skills/geezerrrr/motive/oracle)

Your own site

<a href="https://agentmods.dev/skills/geezerrrr/motive/oracle"><img src="https://agentmods.dev/badge/skills/geezerrrr/motive/oracle/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/geezerrrr/motive/oracle"><img src="https://agentmods.dev/badge/skills/geezerrrr/motive/oracle.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 25 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,315 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin 97% copy Near-identical to another mod 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 5.1	$0.00025	$0.01315
Opus 5.5	$0.00010	$0.00526
Sonnet 5.5	$0.00005	$0.00263
Haiku 4.5	$0.00003	$0.00131

Measured 1mo ago against content hash 903a053178a3, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

oracle 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 1mo 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.

Origin

This is a copy

97% identical to oracle — 4 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

Motive/Resources/Skills.bundle/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 — best use

Oracle bundles your prompt + selected files into one “one-shot” request so another model can answer with real repo context (API or browser automation). Treat output as advisory: verify against code + tests.

Main use case (browser, GPT‑5.2 Pro)

Default workflow here: --engine browser with GPT‑5.2 Pro in ChatGPT. This is the common “long think” path: ~10 minutes to ~1 hour is normal; expect a stored session you can reattach to.

Recommended defaults:

Engine: browser (--engine browser)
Model: GPT‑5.2 Pro (--model gpt-5.2-pro or --model "5.2 Pro")

Golden path

Pick a tight file set (fewest files that still contain the truth).
Preview payload + token spend (--dry-run + --files-report).
Use browser mode for the usual GPT‑5.2 Pro workflow; use API only when you explicitly want it.
If the run detaches/timeouts: reattach to the stored session (don’t re-run).

Commands (preferred)

Help:
- oracle --help
- If the binary isn’t installed: npx -y @steipete/oracle --help (avoid pnpx here; sqlite bindings).
Preview (no tokens):
- oracle --dry-run summary -p "<task>" --file "src/**" --file "!**/*.test.*"
- oracle --dry-run full -p "<task>" --file "src/**"
Token sanity:
- oracle --dry-run summary --files-report -p "<task>" --file "src/**"
Browser run (main path; long-running is normal):
- oracle --engine browser --model gpt-5.2-pro -p "<task>" --file "src/**"
Manual paste fallback:
- oracle --render --copy -p "<task>" --file "src/**"
- Note: --copy is a hidden alias for --copy-markdown.

Attaching files (`--file`)

--file accepts files, directories, and globs. You can pass it multiple times; entries can be comma-separated.

Include:
- --file "src/**"
- --file src/index.ts
- --file docs --file README.md
Exclude:
- --file "src/**" --file "!src/**/*.test.ts" --file "!**/*.snap"
Defaults (implementation behavior):
- Default-ignored dirs: node_modules, dist, coverage, .git, .turbo, .next, build, tmp (skipped unless explicitly passed as literal dirs/files).
- Honors .gitignore when expanding globs.
- Does not follow symlinks.
- Dotfiles filtered unless opted in via pattern (e.g. --file ".github/**").
- Files > 1 MB rejected.

Read the full file on GitHub · 126 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.

1mo ago First seen · 126 lines · 25 tokens per session scan A 903a053178a3

Subscribe to this mod's changes

oracle is a skill published in the GitHub repository geezerrrr/motive (118 stars, last pushed 15d ago), licensed MIT. It adds 25 tokens to every session and 1,315 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 97% identical to oracle, differing in 4 lines, and is treated as a copy.

Building agents Claude Code ai-agent ai-agents ai-tools cowork gemini-cli

issue-maintenance

Writes to a repo's open GitHub issues: fixes type and lifecycle labels, re-scores priority, fills sizing labels, cleans up issue prose, and proposes merging clusters of small issues. Auto-applies safe changes, flags the rest. Trigger on: "run issue maintenance", "tidy the backlog", "re-prioritize open issues"…

jerseycheese/agent-skills · 81 tokens

test-reaper

Finds and removes dead or trivial tests: duplicates, mock-only asserts, render checks that prove nothing. Also finds over-mocked tests and seam gaps, where no test sends a realistic payload across a boundary. Trigger on: "reap tests", "our tests don't test anything", "too much mocking", "why didn't tests catch this".

jerseycheese/agent-skills · 73 tokens

evidence-check

Honesty gate that backs claims with real evidence instead of stating guesses as fact. Runs always-on as a self-check before technical claims and recommendations. Invoke explicitly on: "show your work", "prove it", "how do you know that", "what's your source".

jerseycheese/agent-skills · 59 tokens

ci-fix-with-memory

Automatically invoke when CI checks fail on a PR. Do NOT wait for the user to ask; invoke as soon as a CI failure is confirmed. Reads session handoffs and a known-issues log so failed fixes aren't retried. Trigger on: "CI is failing", "red checks", "GitHub Actions failed", "fix CI".

jerseycheese/agent-skills · 74 tokens

comment-reaper

Finds and removes comments that add nothing: ones that restate the code, cite issue numbers, narrate refactor history, or pad a one-liner with JSDoc. Keeps the WHY comments. Trigger on: "reap comments", "remove unnecessary comments", "too many comments", "comment audit".

jerseycheese/agent-skills · 68 tokens

plain-language-audit

Sweeps comments, docstrings, docs, and UI copy for jargon, AI writing tells, and wordy text. Auto-fixes clear swaps and surfaces judgment calls. Prose and tone only. Trigger on: "plain language audit", "find jargon", "sounds like AI wrote this", "too wordy".

jerseycheese/agent-skills · 69 tokens