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.
npx skills add aniketpanjwani/skills --skill oraclegit clone --depth 1 https://github.com/aniketpanjwani/skillsWrote 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.
[](https://agentmods.dev/skills/aniketpanjwani/skills/oracle)<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.
<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>- NVIDIA SkillSpector warn
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.
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.
| Model | Per session | Once 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 |
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.
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:
- use Oracle to bundle and render the exact prompt plus attachments
- copy that rendered bundle to the clipboard
- submit the bundle through the user's Chrome ChatGPT session when the safety preflight passes
- use the latest Pro model with extended thinking when available
- 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:
- Pick the minimum files that still contain the truth.
- Run
oracle --dry-run summary --files-report ...before rendering broad scopes. - Render and copy the bundle with
oracle --render --copy. - Run the safety preflight below.
- Submit through the browser path ladder.
- 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:
- Use the
@Chromeplugin / Codex Chrome Extension if it is available. - If
@Chromeis unavailable, use Computer Use to operate Google Chrome. - If Chrome cannot be operated, use the in-app
@Browserplugin as a fallback. - If browser automation is unavailable or unsafe, render/copy only and ask the human to paste manually.
When using any browser path:
- Open a new ChatGPT chat unless the user explicitly asked to use an existing thread.
- Do not read, summarize, or interact with unrelated existing chats.
- Verify ChatGPT is logged in by checking for the composer, not a login page.
- Verify the visible account/workspace is the intended one when possible.
- Do not switch accounts.
- Stop if the page shows sensitive unrelated content.
- Never handle passwords, OTPs, CAPTCHA, account recovery, or payment prompts.
- 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.
- Paste the rendered Oracle bundle from the clipboard.
- Submit and watch until generation has stopped and the send/stop control indicates completion.
- Bring back the final answer plus any caveats, then verify locally before acting.
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.
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.
- 12d ago First seen · 205 lines · 72 tokens per session scan A 833633eb54fb
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.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…