oracle

oracle is a skill for Codex from aniketpanjwani/skills. It costs 72 tokens per session (2,364 once invoked), scanned A, original, MIT.

A guide for using the Oracle command-line tool to package a coding question with selected project files for review by ChatGPT. The guide also covers submitting the package through the user's browser when appropriate.

In plain words
What is it for?
Use it to bundle prompts and files, render or copy the bundle, submit it through a Chrome ChatGPT session, and bring the review back into the coding workflow.
Why use it?
It helps provide an external review with the relevant repository context while keeping the attached file set focused and checking the advice against the code and tests.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: mentions Codex.

Good fit Use it to bundle prompts and files, render or copy the bundle, submit it through a Chrome ChatGPT session, and bring the review back into the coding workflow.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/aniketpanjwani/skills/oracle
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add aniketpanjwani/skills --skill oracle
Clone the repo
git clone --depth 1 https://github.com/aniketpanjwani/skills

Made for: Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for oracle

README.md
[![agentmods](https://agentmods.dev/badge/skills/aniketpanjwani/skills/oracle/github.svg)](https://agentmods.dev/skills/aniketpanjwani/skills/oracle)
Your own site
<a href="https://agentmods.dev/skills/aniketpanjwani/skills/oracle"><img src="https://agentmods.dev/badge/skills/aniketpanjwani/skills/oracle/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for oracle

Your own site · 80×15
<a href="https://agentmods.dev/skills/aniketpanjwani/skills/oracle"><img src="https://agentmods.dev/badge/skills/aniketpanjwani/skills/oracle.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 72 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,364 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Privilege Escalation · line 132
    Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
    Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00072 $0.02364
Opus 5 $0.00036 $0.01182
Sonnet 5 $0.00014 $0.00473
Haiku 4.5 $0.00007 $0.00236

Measured 12d ago against content hash 833633eb54fb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

oracle scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/general/oracle/SKILL.md · 205 lines

How it starts

The opening of the file, as written. The whole thing — 205 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Oracle (CLI)

Oracle bundles your prompt plus selected files into one "one-shot" request so ChatGPT can answer with real repo context. Treat outputs as advisory and verify them against the codebase and tests.

Oracle is a bundler first. The default path is:

  1. use Oracle to bundle and render the exact prompt plus attachments
  2. copy that rendered bundle to the clipboard
  3. submit the bundle through the user's Chrome ChatGPT session when the safety preflight passes
  4. use the latest Pro model with extended thinking when available
  5. watch for the final answer and bring the result back into the agent workflow

Manual paste remains the fallback when browser automation is unavailable, logged out, interrupted, or unsafe for the current context.

Do not use Oracle API mode for routine work. Do not use Oracle's native browser automation by default. Do not use remote browser-host flows.

Default Workflow

Use this workflow for normal Oracle work:

oracle --render --copy -p "<task>" --file "<tight file set>"

Then:

  1. Pick the minimum files that still contain the truth.
  2. Run oracle --dry-run summary --files-report ... before rendering broad scopes.
  3. Render and copy the bundle with oracle --render --copy.
  4. Run the safety preflight below.
  5. Submit through the browser path ladder.
  6. Watch for the final answer, extract it, and verify it against local files and tests.

Browser Submit Ladder

Use the user's Chrome session by default when the safety preflight passes:

  1. Use the @Chrome plugin / Codex Chrome Extension if it is available.
  2. If @Chrome is unavailable, use Computer Use to operate Google Chrome.
  3. If Chrome cannot be operated, use the in-app @Browser plugin as a fallback.
  4. If browser automation is unavailable or unsafe, render/copy only and ask the human to paste manually.

When using any browser path:

  1. Open a new ChatGPT chat unless the user explicitly asked to use an existing thread.
  2. Do not read, summarize, or interact with unrelated existing chats.
  3. Verify ChatGPT is logged in by checking for the composer, not a login page.
  4. Verify the visible account/workspace is the intended one when possible.
  5. Do not switch accounts.
  6. Stop if the page shows sensitive unrelated content.
  7. Never handle passwords, OTPs, CAPTCHA, account recovery, or payment prompts.
  8. Use the latest Pro model with extended thinking when available. As of May 11, 2026, that is GPT-5.5 Pro; if the UI label has changed, pick the newest visible Pro/extended-thinking mode rather than a stale hardcoded model name.
  9. Paste the rendered Oracle bundle from the clipboard.
  10. Submit and watch until generation has stopped and the send/stop control indicates completion.
  11. Bring back the final answer plus any caveats, then verify locally before acting.

Read the full file on GitHub · 205 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 12d ago First seen · 205 lines · 72 tokens per session scan A 833633eb54fb

Subscribe to this mod's changes

oracle is a skill published in the GitHub repository aniketpanjwani/skills (52 stars, last pushed 25d ago), licensed MIT. It adds 72 tokens to every session and 2,364 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.