oracle

Best practices for using the oracle CLI (prompt + file bundling, engines, sessions, and file attachment patterns).

Best use case

oracle is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Best practices for using the oracle CLI (prompt + file bundling, engines, sessions, and file attachment patterns).

Teams using oracle should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/oracle/SKILL.md --create-dirs "https://raw.githubusercontent.com/stevengonsalvez/agents-in-a-box/main/toolkit/packages/skills/oracle/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/oracle/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How oracle Compares

Feature / AgentoracleStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Best practices for using the oracle CLI (prompt + file bundling, engines, sessions, and file attachment patterns).

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

# 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

1. Pick a tight file set (fewest files that still contain the truth).
2. Preview payload + token spend (`--dry-run` + `--files-report`).
3. Use browser mode for the usual GPT‑5.2 Pro workflow; use API only when you explicitly want it.
4. 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.

## Engines (API vs browser)

- Auto-pick: `api` when `OPENAI_API_KEY` is set; otherwise `browser`.
- Browser supports GPT + Gemini only; use `--engine api` for Claude/Grok/Codex or multi-model runs.
- Browser attachments:
  - `--browser-attachments auto|never|always` (auto pastes inline up to ~60k chars then uploads).
- Remote browser host:
  - Host: `oracle serve --host 0.0.0.0 --port 9473 --token <secret>`
  - Client: `oracle --engine browser --remote-host <host:port> --remote-token <secret> -p "<task>" --file "src/**"`

## Sessions + slugs

- Stored under `~/.oracle/sessions` (override with `ORACLE_HOME_DIR`).
- Runs may detach or take a long time (browser + GPT‑5.2 Pro often does). If the CLI times out: don’t re-run; reattach.
  - List: `oracle status --hours 72`
  - Attach: `oracle session <id> --render`
- Use `--slug "<3-5 words>"` to keep session IDs readable.
- Duplicate prompt guard exists; use `--force` only when you truly want a fresh run.

## Prompt template (high signal)

Oracle starts with **zero** project knowledge. Assume the model cannot infer your stack, build tooling, conventions, or “obvious” paths. Include:

- Project briefing (stack + build/test commands + platform constraints).
- “Where things live” (key directories, entrypoints, config files, boundaries).
- Exact question + what you tried + the error text (verbatim).
- Constraints (“don’t change X”, “must keep public API”, etc).
- Desired output (“return patch plan + tests”, “give 3 options with tradeoffs”).

## Safety

- Don’t attach secrets by default (`.env`, key files, auth tokens). Redact aggressively; share only what’s required.

## “Exhaustive prompt” restoration pattern

For long investigations, write a standalone prompt + file set so you can rerun days later:

- 6–30 sentence project briefing + the goal.
- Repro steps + exact errors + what you tried.
- Attach all context files needed (entrypoints, configs, key modules, docs).

Oracle runs are one-shot; the model doesn’t remember prior runs. “Restoring context” means re-running with the same prompt + `--file …` set (or reattaching a still-running stored session).

Related Skills

workflow

8
from stevengonsalvez/agents-in-a-box

Guide through structured delivery workflow with plan, implement, validate phases

webapp-testing

8
from stevengonsalvez/agents-in-a-box

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.

validate

8
from stevengonsalvez/agents-in-a-box

Verify implementation against specifications

ui-ux-pro-max

8
from stevengonsalvez/agents-in-a-box

UI/UX design intelligence. 67 styles, 96 palettes, 57 font pairings, 25 charts, 13 stacks (React, Next.js, Vue, Svelte, Astro, Nuxt, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui, Jetpack Compose). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app, .html, .tsx, .vue, .svelte. Elements: button, modal, navbar, sidebar, card, table, form, chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, flat design. Topics: color palette, accessibility, animation, layout, typography, font pairing, spacing, hover, shadow, gradient.

tui-style-guide

8
from stevengonsalvez/agents-in-a-box

TUI style guide for consistent terminal interface design

token-usage

8
from stevengonsalvez/agents-in-a-box

Show Claude Code token usage across sessions — daily, weekly, per-project, and per-session breakdowns. Parses {{HOME_TOOL_DIR}}/projects/**/*.jsonl for consumption data. Use when the user asks about token usage, costs, how many tokens were used, session statistics, or wants a usage report.

tmux-status

8
from stevengonsalvez/agents-in-a-box

Show status of all tmux sessions including dev environments, spawned agents, and running processes

tmux-monitor

8
from stevengonsalvez/agents-in-a-box

Monitor and report status of all tmux sessions including dev environments, spawned agents, and running processes. Uses tmuxwatch for enhanced visibility.

tmux-message

8
from stevengonsalvez/agents-in-a-box

Reliable peer-to-peer message delivery to other Claude Code instances via tmux send-keys. Use as a fallback when claude-peers MCP send_message fails to surface in the receiver's inbox (delivered server-side but receiver never picks it up — observed behaviour). Also use when sending a directive to a known Claude Code TUI session by tmux session name or fuzzy hint, or when injecting a multi-line directive into a peer's prompt and submitting it. Trigger phrases — "claude-peers fallback", "tmux send-keys", "send to peer via tmux", "inject directive", "deliver to nanoclaw/hermes peer", "peer message". Tmux-only — won't reach peers running outside tmux.

test-driven-development

8
from stevengonsalvez/agents-in-a-box

Use when implementing any feature or bugfix, before writing implementation code. Enforces RED-GREEN-REFACTOR cycle with test-first approach.

test-ainb

8
from stevengonsalvez/agents-in-a-box

Run tests for the ainb (agents-in-a-box) Rust workspace via a 5-layer strategy — unit, insta snapshot, mock-plugin compositing, real-plugin spawn, vhs recording. Wraps cargo + insta + vhs into one CLI. Use when Stevie says "/test-ainb", "test ainb", "run ainb tests", "snapshot <component>", "regenerate vhs tapes", or any phrasing about validating ainb test layers. The skill autodetects which ainb-tui worktree the cwd sits in and dispatches to scripts/run.sh.

sync-learnings

8
from stevengonsalvez/agents-in-a-box

Sync user-level agent config changes back to toolkit repository (works for Claude, Codex, Copilot)