How do I install the Oracle skill?

Run npx skillmds@latest add phrazzld/oracle in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Oracle safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Oracle?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Oracle free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Oracle?

phrazzld (@phrazzld) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Oracle by phrazzld — Agent Skill

Name: Oracle
Author: phrazzld

Oracle

Browser-mode-only Oracle consults: bundle a prompt plus selected files and ask a signed-in ChatGPT GPT-5.5 Pro browser session for a second opinion. Use when stuck, debugging hard bugs, reviewing an architecture plan, or cross-checking a substantive diff with large file context. Never use Oracle API mode from Harness Kit. Trigger: /oracle, /consult.

phrazzld f04b48f 2 files · 3.4 KB Updated Sep 17, 2026

File contents

/oracle

Use Oracle only as a browser-backed consult surface. It bundles the prompt and selected files, opens a signed-in ChatGPT browser session, and stores the answer under ~/.oracle/sessions. The lead agent still owns synthesis, verification, and final judgment.

Hard Boundary

Always pass --engine browser.
Prefer --model gpt-5.5-pro unless the operator names another browser model.
Never run --engine api, --provider openai, --no-azure, --models, or API preflight from this skill.
If an Oracle command would need an API key or per-token billing, do not use Oracle for that work from Harness Kit; use the normal roster/research paths instead.

Workflow

Pick the tightest file set that contains the truth. Exclude tests, snapshots, generated output, and fixtures unless they are the oracle.

Preview first:

npx -y @steipete/oracle --engine browser --model gpt-5.5-pro \
  --dry-run summary --files-report \
  -p "<task>" --file "src/**" --file "!**/*.test.*"

Run only after the preview is sensible:

npx -y @steipete/oracle --engine browser --model gpt-5.5-pro \
  --slug "<3-5-words>" \
  -p "<task>" --file "src/**" --file "!**/*.test.*"

If the run detaches or times out, do not re-run. Inspect the stored session:

npx -y @steipete/oracle status --hours 72
npx -y @steipete/oracle session <id> --render

Good Prompts

Oracle starts cold. Include the repo goal, relevant commands, exact failure, constraints, and desired output shape. For review, give the artifact and oracle, not the author's reasoning trail.

Good output requests:

Return blockers only, with file/line evidence.
Challenge this plan; list missing proof, wrong assumptions, and safer alternatives.
Find the likely root cause and the smallest verification loop.

Safety

Do not attach secrets, .env, key files, tokens, browser profiles, or private customer data.
Use --dry-run summary --files-report before every real run.
Treat Oracle output as advisory evidence. Verify with the repo's live oracle, tests, gate, browser route, or command before claiming done.
Browser mode is cheaper than API billing but can be slow and subject to ChatGPT subscription limits.

---name: oracledescription: Browser-mode-only Oracle consults: bundle a prompt plus selected files and ask a signed-in ChatGPT GPT-5.5 Pro browser session for a second opinion. Use when stuck, debugging hard bugs, reviewing an architecture plan, or cross-checking a substantive diff with large file context. Never use Oracle API mode from Harness Kit. Trigger: /oracle, /consult.---# /oracleUse Oracle only as a browser-backed consult surface. It bundles the prompt andselected files, opens a signed-in ChatGPT browser session, and stores theanswer under `~/.oracle/sessions`. The lead agent still owns synthesis,verification, and final judgment.## Hard Boundary- Always pass `--engine browser`.- Prefer `--model gpt-5.5-pro` unless the operator names another browser model.- Never run `--engine api`, `--provider openai`, `--no-azure`, `--models`, or API preflight from this skill.- If an Oracle command would need an API key or per-token billing, do not use Oracle for that work from Harness Kit; use the normal roster/research paths instead.## Workflow1. Pick the tightest file set that contains the truth. Exclude tests, snapshots, generated output, and fixtures unless they are the oracle.2. Preview first: ```sh npx -y @steipete/oracle --engine browser --model gpt-5.5-pro \ --dry-run summary --files-report \ -p "<task>" --file "src/**" --file "!**/*.test.*" ```3. Run only after the preview is sensible: ```sh npx -y @steipete/oracle --engine browser --model gpt-5.5-pro \ --slug "<3-5-words>" \ -p "<task>" --file "src/**" --file "!**/*.test.*" ```4. If the run detaches or times out, do not re-run. Inspect the stored session: ```sh npx -y @steipete/oracle status --hours 72 npx -y @steipete/oracle session <id> --render ```## Good PromptsOracle starts cold. Include the repo goal, relevant commands, exact failure,constraints, and desired output shape. For review, give the artifact and oracle,not the author's reasoning trail.Good output requests:- `Return blockers only, with file/line evidence.`- `Challenge this plan; list missing proof, wrong assumptions, and safer alternatives.`- `Find the likely root cause and the smallest verification loop.`## Safety- Do not attach secrets, `.env`, key files, tokens, browser profiles, or private customer data.- Use `--dry-run summary --files-report` before every real run.- Treat Oracle output as advisory evidence. Verify with the repo's live oracle, tests, gate, browser route, or command before claiming done.- Browser mode is cheaper than API billing but can be slow and subject to ChatGPT subscription limits.

Frequently asked questions