oracle

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

npx skills add https://github.com/firecrawl/openclaw --skill oracle

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).

More skills from firecrawl

firecrawl-monitor
firecrawl
Detect when content on a website changes and get notified by webhook or email — no cron jobs, scrapers, or diff scripts required. Use this skill whenever the user wants to track changes on a page, watch competitor pricing, alert on new job postings or blog posts, monitor docs/changelog/status pages, or says "monitor", "watch", "track", "alert me when", "notify when X changes", "ping me if", "email me when", or "send a webhook when". A built-in AI judge filters out formatting, timestamp, and...
officialweb-scrapingresearch
firecrawl-deep-research
firecrawl
Run multi-source deep research with Firecrawl. Use when the user asks to research a topic, compare perspectives, produce a sourced briefing, investigate a technical or market question, or synthesize web evidence across many sources.
officialresearchweb-scraping
firecrawl-research-papers
firecrawl
Find and synthesize research papers, whitepapers, PDFs, technical reports, and academic sources with Firecrawl. Use when the user wants a literature review, paper summary, research landscape, or sourced synthesis from PDFs and scholarly/industry publications.
officialresearchweb-scraping
firecrawl-market-research
firecrawl
Extract market, financial, earnings, industry, and company metrics with Firecrawl. Use when the user asks for market research, industry trends, public company data, financial comparisons, earnings research, or structured market reports.
officialresearchweb-scraping
firecrawl-website-design-clone
firecrawl
Extract any website's design system into an agent-ready DESIGN.md using Firecrawl scrape evidence. Use when the user wants colors, fonts, spacing, components, layout patterns, or brand/UI guidance from a website so AI agents can create new websites, clone a look, or build pages inspired by that design.
officialdesignweb-scraping
firecrawl-knowledge-base
firecrawl
Build a knowledge base from web content with Firecrawl. Use for local reference docs, RAG-ready chunks, fine-tuning datasets, documentation mirrors, topic corpora, or LLM-ready markdown organized from web sources.
officialweb-scrapingresearch
firecrawl-lead-research
firecrawl
Produce pre-meeting lead intelligence briefs with Firecrawl. Use when the user needs company research, person research, recent news, talking points, pain points, or outreach preparation before a sales call, partnership meeting, investor conversation, or customer interview.
officialresearchweb-scraping
firecrawl-dashboard-reporting
firecrawl
Pull metrics from analytics dashboards and internal web tools with Firecrawl browser. Use when the user needs dashboard reporting, cross-platform metric summaries, authenticated analytics extraction, date-range reports, or structured metrics from web dashboards.
officialbrowser-automationdata-analysis