Now liveThe Skillselion MCP - thousands of ranked skills, loaded into your agent mid-task. No install.Get it →
steipete avatar

Oracle

  • 3.1k installs
  • 385k repo stars
  • Updated August 3, 2026
  • steipete/clawdis

oracle is an agent skill for the oracle CLI that sends a prompt plus selected files to a second model with dry-run previews and session reattach.

About

Oracle is an agent skill for the oracle CLI that bundles a prompt plus selected files into one second-model advisory pass. Default model is gpt-5.5-pro with browser engine for long ChatGPT Pro runs or API engine when OPENAI_API_KEY or Azure config is ready. Golden path picks a tight file set, previews payload with dry-run summary and files-report, then runs browser or API mode without re-running on detach; reattach stored sessions instead. File attachment supports globs, excludes, gitignore honoring, and one megabyte size limits with default ignored directories. Sessions persist under ~/.oracle/sessions with status and attach commands. Prompt guidance stresses zero project knowledge assumptions, stack briefing, repro steps, verbatim errors, constraints, and desired output format. Safety rules forbid attaching secrets from .env or key files. Install via npm @steipete/oracle. Use it for design review, debug second opinions, refactors, or long investigations you may need to rerun days later.

  • Second-model review via oracle CLI with browser or API engines.
  • Dry-run summary and files-report token preview before spending credits.
  • Glob-based file attachment with excludes, gitignore, and size limits.
  • Session reattach workflow when browser Pro runs detach or timeout.
  • Exhaustive prompt pattern for rerunnable long investigations.

Oracle by the numbers

  • 3,053 all-time installs (skills.sh)
  • +165 installs in the week ending Aug 2, 2026 (Skillselion tracking)
  • Ranked #58 of 1,354 Code Review & Quality skills by installs in the Skillselion catalog
  • Security screen: HIGH risk (skills.sh audit)
  • Data as of Aug 3, 2026 (Skillselion catalog sync)
At a glance

oracle capabilities & compatibility

Capabilities
dry run summary and full payload preview · glob file selection with exclude patterns · browser and api engine execution paths · session list, attach, and slug management · remote browser host serve and client mode · safety guidance against secret attachments
Works with
openai · azure
Use cases
code review · debugging · planning
From the docs

What oracle says it does

Oracle bundles a prompt + selected files for one second-model pass. Treat output as advisory; verify against code + tests.
SKILL.md
If the run detaches/timeouts: reattach to the stored session. Do not blindly re-run.
SKILL.md
npx skills add https://github.com/steipete/clawdis --skill oracle

Add your badge

Show developers this skill is listed on Skillselion. Paste this into your README.

Listed on Skillselion
Installs3.1k
repo stars385k
Security audit3 / 3 scanners passed
Last updatedAugust 3, 2026
Repositorysteipete/clawdis

How do I get a second-model review on selected code with controlled token spend and rerunnable context?

Run a second-model Oracle CLI review on selected files with dry-run token checks via browser or API engines.

Who is it for?

Developers wanting a second opinion on refactors, bugs, or design with explicit file context.

Skip if: Skip when you need automated CI linting or guaranteed patch application without human verification.

When should I use this skill?

User mentions oracle CLI, second-model review, dry-run files-report, or reattaching Oracle sessions.

What you get

Advisory Oracle output from a scoped file set with dry-run validation and optional session reattach.

  • Second-model advisory review output

Files

SKILL.mdMarkdownGitHub ↗

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").

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

Forks & variants (1)

Oracle has 1 known copy in the catalog totaling 1 installs. They canonicalize to this original listing.

How it compares

Use oracle for a quick second-model pass on a bounded file set; use full code-review skills when structured multi-category analysis from the primary agent is sufficient.

FAQ

Should I rerun if the CLI times out?

No. Reattach the stored session with oracle session id --render instead of re-running.

How do I preview token usage?

Use --dry-run summary with --files-report before the real browser or API run.

Can I attach .env files?

No. Do not attach secrets; redact aggressively and share only required context.

Is Oracle safe to install?

skills.sh reports 3 of 3 security scanners passed. Review the Security Audits panel on this page before installing in production.

This week in AI coding

Five minutes, every Monday - the tools, releases and tactics for developers.

unsubscribe anytime.