Skip to main content
skill Claude Code CX Codex Cursor GitHub Copilot

oracle — Claude Code skill: what it does, how to install

Bundles selected project files and prompts for an independent second-model review via API or browser. Helps inspect patches and debug tricky bugs.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add openclaw/openclaw --skill oracle -a claude-code
Open on GitHub

What oracle does

This skill runs the @steipete/oracle CLI to package your prompt and selected files for a single second-model pass. It defaults to gpt-5.5-pro. Before spending tokens, you can preview the full payload and file tree using --dry-run summary --files-report.

Oracle operates in two modes: browser mode for long ChatGPT Pro thinking runs or API mode when OPENAI_API_KEY or Azure settings are present. It honors .gitignore, skips directories like node_modules or .git, and rejects files over 1 MB unless explicitly targeted.

All runs are stored under ~/.oracle/sessions. If a browser run detaches or times out, reattach with oracle session instead of running it again. Install it if you need an advisory second opinion from another model before shipping code.

What it helps with

  • review critical patches with a second independent model
  • inspect token usage and payload size before running queries
  • run long reasoning prompts through a browser session
  • reattach to detached analysis sessions without rerunning

Example prompts for the agent

  • Run an oracle dry run on src/** excluding test files
  • Ask oracle to review src/api.ts using the browser engine
  • Check status of previous oracle sessions from the last 72 hours

How to install oracle

1Skills CLI (Vercel)

npx skills add openclaw/openclaw --skill oracle -a claude-code

2Manually: put the files in place

~/.claude/skills/oracle/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/oracle/

From the same set48

The whole set →
summarize openclaw Runs a CLI tool to summarize or transcribe web articles, YouTube videos, podcasts, and local PDF documents directly within your AI assistant. Claude Code CX Codex Cursor +1 26,900installs weather openclaw This skill fetches current conditions and forecasts for a city, region, airport code, or coordinates. Use it to check rain and temperature or plan a trip. Claude Code CX Codex Cursor +1 9,300installs gog openclaw Guides an agent using the gog CLI for Gmail, Calendar, Drive, Contacts, Sheets, and Docs. Use it when Google Workspace tasks need to run from a terminal. Claude Code CX Codex Cursor +1 8,500installs tmux openclaw Lets an agent work with live tmux sessions: read pane output, send keys and text, wait for a prompt line to show up. Claude Code CX Codex Cursor +1 8,400installs openai-whisper openclaw This skill lets your agent call the Whisper CLI to transcribe audio on your own machine. No API key needed. Claude Code CX Codex Cursor +1 7,100installs nano-pdf openclaw Edit PDF pages with plain text instructions through the nano-pdf CLI. Useful when you need to fix a typo or swap a heading without leaving your terminal. Claude Code CX Codex Cursor +1 7,100installs skill-creator openclaw A skill for writing, repairing and reviewing other skills. It splits behaviour into branches, sets the frontmatter and sorts resources into folders. Useful once your skill folder gets crowded. Claude Code CX Codex Cursor +1 6,700installs coding-agent openclaw This skill sends large coding tasks to Codex, Claude Code, or OpenCode as background workers. Use it for refactors, PR reviews, and issue-to-PR work. Claude Code CX Codex Cursor +1 6,500installs

Similar

application-security-testing usestrix This skill selects tests for source code, a live web app, APIs, and CI, then turns confirmed findings into a ranked remediation plan. Use it for an AppSec review. Claude Code CX Codex Cursor +1 12,300installs security-best-practices github.com/openai/skills A skill that reviews code against security best practices for Python, JavaScript/TypeScript and Go, then suggests fixes. Claude Code CX Codex Cursor +1 357installs open-code-review alibaba Skill runs the ocr CLI to review Git changes with AI. Produces line-level comments and can apply fixes on request. Claude Code CX Codex Cursor +1 6,800installs claude-md-improver official Anthropic This skill audits CLAUDE.md files, produces a quality report, and suggests focused edits. Use it when project instructions need a careful review. Claude Code 12,558installs fix react The skill formats changed files and checks for remaining lint issues before a commit. Use it when code needs to pass CI checks. Claude Code CX Codex Cursor +1 2,300installs improve-codebase-architecture Matt Pocock This skill scans a codebase for architectural friction, then builds a visual HTML report with refactoring candidates. Use it before a deeper architecture review. Claude Code 1,163,035installs tdd Matt Pocock Guides the red-green TDD loop: ensures tests are written first, keep them at public interfaces, and avoid coupling to implementation details. Claude Code 1,141,062installs triage Matt Pocock This skill moves issues and external PRs through triage states, verification, and agent briefs. It fits maintainers managing an issue queue. Claude Code 990,453installs

Questions about oracle

How to install oracle in Claude Code?

Run npx skills add openclaw/openclaw --skill oracle -a claude-code in your terminal. You will also need the @steipete/oracle package installed.

What does the oracle skill do?

It bundles selected files and a prompt into a standalone pass for an advisory review by a second LLM.

When should I use browser mode instead of API?

Browser mode suits long ChatGPT Pro runs and works without an API key, while API mode handles explicit calls and models outside GPT or Gemini.

Source text

SKILL.md · MIT
---
name: oracle
description: "Oracle CLI second-model review/debug/refactor/design with selected files, dry-run token checks, API or browser engine."
homepage: https://askoracle.dev
metadata:
  {
    "openclaw":
      {
        "emoji": "🧿",
        "requires": { "bins": ["oracle"] },
        "install":
          [
            {
              "id": "node",
              "kind": "node",
              "package": "@steipete/oracle",
              "bins": ["oracle"],
              "label": "Install oracle (node)",
            },
          ],
      },
  }
---

# oracle

Oracle bundles a prompt + selected files for one second-model pass. Treat output as advisory; verify against code + tests.

## Main path

Current CLI default model: `gpt-5.5-pro`. Browser engine is useful for long ChatGPT Pro runs; API engine is useful when `OPENAI_API_KEY` or Azure config is ready.

Recommended defaults:

- Preview first: `--dry-run summary --files-report`
- Browser long run: `--engine browser --model gpt-5.5-pro`
- API explicit: `--engine api --model gpt-5.5`

## 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 long Pro thinking; API mode for explicit API calls.
4. If the run detaches/timeouts: reattach to the stored session. Do not blindly 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-5.5-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 + Pro often does). If the CLI times out: do not 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").

## Attachments

- Leave `.env`, key files, and auth tokens out of attachments unless the user asks to include them.

## "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).

© openclaw · MIT · openclaw/openclaw

See also

Project sponsors

Companies that keep this analytics open
Gold sponsor

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor