oracle
A guide for using the Oracle CLI to execute second-model code reviews and refactoring with precise file scoping.
Install
mkdir -p .claude/skills/oracle && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/689" && unzip -o skill.zip -d .claude/skills/oracle && rm skill.zipInstalls to .claude/skills/oracle
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Oracle CLI second-model review/debug/refactor/design with selected files, dry-run token checks, API or browser engine.Key capabilities
- →Bundle prompts with selected files for AI review
- →Perform dry-run token estimation
- →Manage long-context sessions in browser mode
- →Attach files and directories using glob patterns
- →Reattach to existing AI sessions
How it works
The tool bundles a prompt and specified files for a single second-model pass, supporting both API and browser-based engines for different context requirements.
Inputs & outputs
When to use oracle
- →Review code changes with AI
- →Refactor large codebases using specific files
- →Estimate token costs before execution
- →Manage long-context AI sessions
About this skill
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
- Pick a tight file set (fewest files that still contain the truth).
- Preview payload + token spend (
--dry-run+--files-report). - Use browser mode for long Pro thinking; API mode for explicit API calls.
- 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(avoidpnpxhere; 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:
--copyis 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
.gitignorewhen expanding globs. - Does not follow symlinks.
- Dotfiles filtered unless opted in via pattern (e.g.
--file ".github/**"). - Files > 1 MB rejected.
- Default-ignored dirs:
Engines (API vs browser)
- Auto-pick:
apiwhenOPENAI_API_KEYis set; otherwisebrowser. - Browser supports GPT + Gemini only; use
--engine apifor 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/**"
- Host:
Sessions + slugs
- Stored under
~/.oracle/sessions(override withORACLE_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
- List:
- Use
--slug "<3-5 words>"to keep session IDs readable. - Duplicate prompt guard exists; use
--forceonly 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).
When not to use it
- →When attaching sensitive secrets or keys
- →When files exceed 1 MB in size
- →When following symlinks
Prerequisites
Limitations
- →Does not follow symlinks
- →Filters dotfiles by default
- →One-shot execution model
How it compares
Unlike standard chat interfaces, this CLI provides explicit control over file context, token usage previews, and session persistence.
Compared to similar skills
oracle side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| oracle (this skill) | 17 | 2mo | Review | Intermediate |
| migrate-honcho-ts | 1 | 4mo | No flags | Advanced |
| agent-implementer-sparc-coder | 1 | 6mo | Review | Intermediate |
| turborepo | 61 | 2mo | Review | Intermediate |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by openclaw
View all by openclaw →You might also like
migrate-honcho-ts
plastic-labs
Migrates Honcho TypeScript SDK code from v1.6.0 to v2.0.0. Use when upgrading @honcho-ai/sdk, fixing breaking changes after upgrade, or when errors mention removed APIs like .core, getConfig, observations, or snake_case properties.
agent-implementer-sparc-coder
ruvnet
Agent skill for implementer-sparc-coder - invoke with $agent-implementer-sparc-coder
turborepo
vercel
Turborepo monorepo build system guidance. Triggers on: turbo.json, task pipelines, dependsOn, caching, remote cache, the "turbo" CLI, --filter, --affected, CI optimization, environment variables, internal packages, monorepo structure/best practices, and boundaries. Use when user: configures tasks/workflows/pipelines, creates packages, sets up monorepo, shares code between apps, runs changed/affected packages, debugs cache, or has apps/packages directories.
senior-fullstack
davila7
Comprehensive fullstack development skill for building complete web applications with React, Next.js, Node.js, GraphQL, and PostgreSQL. Includes project scaffolding, code quality analysis, architecture patterns, and complete tech stack guidance. Use when building new projects, analyzing code quality, implementing design patterns, or setting up development workflows.
codex-skill
feiskyer
Use when user asks to leverage codex, gpt-5, or gpt-5.1 to implement something (usually implement a plan or feature designed by Claude). Provides non-interactive automation mode for hands-off task execution without approval prompts.
svelte-expert
Raudbjorn
Expert Svelte/SvelteKit development assistant for building components, utilities, and applications. Use when creating Svelte components, SvelteKit applications, implementing reactive patterns, handling state management, working with stores, transitions, animations, or any Svelte/SvelteKit development task. Includes comprehensive documentation access, code validation with svelte-autofixer, and playground link generation.