Oracle

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

• Token/cost sanity:
• npx -y @steipete/oracle --dry-run summary --files-report -p "" --file "src/**"

• Browser run (main path; long-running is normal):
• npx -y @steipete/oracle --engine browser --model gpt-5.2-pro -p "" --file "src/**"

• Manual paste fallback (assemble bundle, copy to clipboard):
• npx -y @steipete/oracle --render --copy -p "" --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.

• 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.
• API runs require explicit user consent before starting because they incur usage costs.

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 --render
• If ChatGPT finishes but the session still shows running, the CLI likely never captured the final response. Reattach to mark completion and write output.
• oracle session --render
• ~/.oracle/sessions//meta.json should flip to status: completed.
• If models/.log is empty and output.log only shows “Launching browser mode…”, it likely never attached.
• Use --slug "" 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”).

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.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

• Author: minghinmatthewlam
• Source: minghinmatthewlam/agent-guards
• License: MIT

Install and usage instructions live in the source repository linked above.