Oracle

Use the @steipete/oracle CLI to bundle a prompt plus the right files and get a second-model review (API or browser) for debugging, refactors, design checks, or cross-validation.

Security Scan

The SKILL.md is coherent about how to use the @steipete/oracle CLI, but the instructions reference environment variables, local session storage, and runtime downloads (npx) that are not declared by the skill metadata — this mismatch and the fact that the workflow will upload local files to an external model warrant caution.

Purpose & Capability

The name/description (wrap the @steipete/oracle CLI to bundle prompts+files for a second-model review) matches the instructions: the SKILL.md explains CLI commands and workflows. It legitimately needs to read files and send them to a model, so the core purpose is consistent.

Instruction Scope

The runtime instructions tell the agent/user to run 'npx -y @steipete/oracle' and to provide file globs (including excludes), reattach to stored browser sessions, and potentially upload/paste files to remote browser automation or API models. The doc explicitly references OPENAI_API_KEY and remote tokens and shows a local session directory (~/.oracle/sessions) — none of these env vars or config paths are declared in the skill metadata. Because the instructions will cause local files to be bundled and transmitted to external services, the absence of declared env/config requirements is a notable inconsistency.

Install Mechanism

There is no install spec in the skill bundle (instruction-only), which is low risk for the skill package itself. However, the instructions repeatedly call 'npx -y @steipete/oracle' which will download and execute code from npm at runtime; that runtime download is outside the skill metadata but is operationally significant and worth the user's attention.

Credentials

The skill metadata declares no required env vars, yet the SKILL.md references OPENAI_API_KEY (engine auto-pick), ORACLE_HOME_DIR override, and remote-token/--token for remote-host usage. These environment/config touches are relevant to the described functionality but should have been declared; the mismatch reduces transparency and could lead to accidental credential use or unexpected data flows.

Persistence & Privilege

always:false and user-invocable:true (defaults) are appropriate. The instructions say the CLI stores sessions under ~/.oracle/sessions (overrideable via ORACLE_HOME_DIR) — that local persistence is reasonable for the tool's workflow but is not declared in the skill metadata and may retain copies of bundled files/prompts, so users should be aware.

What to consider before installing

This skill is an instruction-only wrapper around an external npm CLI; it will cause 'npx -y @steipete/oracle' to fetch and run code and will bundle and send local files to a remote model (browser automation or API). Before using: (1) verify the npm package and its homepage/repo (ensure @steipete/oracle is the intended publisher), (2) prefer --dry-run and --files-report to preview exactly which files will be sent, (3) avoid attaching secrets or private keys and explicitly exclude dotfiles/.env, (4) be aware sessions are stored under ~/.oracle/sessions (set ORACLE_HOME_DIR if you want a different location), (5) only set OPENAI_API_KEY or remote tokens when you intend an API run, and (6) if you need stronger guarantees, run the CLI in an isolated environment (container/VM) and inspect the package source before executing. The main problem here is a transparency mismatch — the SKILL.md references env vars and local storage but the skill metadata doesn't declare them — so proceed with caution.

Oracle (CLI) — 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 outputs as advisory: verify against the codebase + tests.

Main use case (browser, GPT‑5.2 Pro)

Default workflow here: --engine browser with GPT‑5.2 Pro in ChatGPT. This is the “human in the loop” path: it can take ~10 minutes to ~1 hour; expect a stored session you can reattach to.

Recommended defaults:

• Engine: browser (--engine browser)
• Model: GPT‑5.2 Pro (either --model gpt-5.2-pro or a ChatGPT picker label like --model "5.2 Pro")
• Attachments: directories/globs + excludes; avoid secrets.

Golden path (fast + reliable)

1. Pick a tight file set (fewest files that still contain the truth).
2. Preview what you’re about to send (--dry-run + --files-report when needed).
3. Run in browser mode for the usual GPT‑5.2 Pro ChatGPT 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)

• Show help (once/session):

  • npx -y @steipete/oracle --help

• Preview (no tokens):

  • npx -y @steipete/oracle --dry-run summary -p "<task>" --file "src/**" --file "!**/*.test.*"
  • npx -y @steipete/oracle --dry-run full -p "<task>" --file "src/**"

• Token/cost sanity:

  • npx -y @steipete/oracle --dry-run summary --files-report -p "<task>" --file "src/**"

• Browser run (main path; long-running is normal):

  • npx -y @steipete/oracle --engine browser --model gpt-5.2-pro -p "<task>" --file "src/**"

• Manual paste fallback (assemble bundle, copy to clipboard):

  • npx -y @steipete/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/**" (directory glob)
  • --file src/index.ts (literal file)
  • --file docs --file README.md (literal directory + file)

• Exclude (prefix with !):

  • --file "src/**" --file "!src/**/*.test.ts" --file "!**/*.snap"

• Defaults (important behavior from the implementation):

  • Default-ignored dirs: node_modules, dist, coverage, .git, .turbo, .next, build, tmp (skipped unless you explicitly pass them as literal dirs/files).
  • Honors .gitignore when expanding globs.
  • Does not follow symlinks (glob expansion uses followSymbolicLinks: false).
  • Dotfiles are filtered unless you explicitly opt in with a pattern that includes a dot-segment (e.g. --file ".github/**").
  • Hard cap: files > 1 MB are rejected (split files or narrow the match).

Budget + observability

• Target: keep total input under ~196k tokens.
• Use --files-report (and/or --dry-run json) to spot the token hogs before spending.
• If you need hidden/advanced knobs: npx -y @steipete/oracle --help --verbose.

Engines (API vs browser)

• Auto-pick: uses api when OPENAI_API_KEY is set, otherwise browser.
• Browser engine supports GPT + Gemini only; use --engine api for Claude/Grok/Codex or multi-model runs.
• API runs require explicit user consent before starting because they incur usage costs.
• Browser attachments:
  • --browser-attachments auto|never|always (auto pastes inline up to ~60k chars then uploads).
• Remote browser host (signed-in machine runs automation):
  • 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 (don’t lose work)

• 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, dependency boundaries).
• Exact question + what you tried + the error text (verbatim).
• Constraints (“don’t change X”, “must keep public API”, “perf budget”, etc).
• Desired output (“return patch plan + tests”, “list risky assumptions”, “give 3 options with tradeoffs”).

“Exhaustive prompt” pattern (for later restoration)

When you know this will be a long investigation, write a prompt that can stand alone later:

• Top: 6–30 sentence project briefing + current goal.
• Middle: concrete repro steps + exact errors + what you already tried.
• Bottom: attach all context files needed so a fresh model can fully understand (entrypoints, configs, key modules, docs).

If you need to reproduce the same context later, re-run with the same prompt + --file … set (Oracle runs are one-shot; the model doesn’t remember prior runs).

Safety

• Don’t attach secrets by default (.env, key files, auth tokens). Redact aggressively; share only what’s required.
• Prefer “just enough context”: fewer files + better prompt beats whole-repo dumps.