A command-line tool that sends a selected prompt and project files to another AI model for a second review.

It helps review code, investigate bugs, assess refactors and designs, and cross-check decisions using a focused set of files.

It provides an additional opinion grounded in the relevant repository files when debugging, refactoring, or checking a design.

oracle — Skill for Claude Code and Codex by marchatton

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 marchatton/agent-skills --skill oracle

Clone the repo

git clone --depth 1 https://github.com/marchatton/agent-skills

Made for: Claude Code, 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/marchatton/agent-skills/oracle.svg)](https://agentmods.dev/skills/marchatton/agent-skills/oracle)

Your own site

<a href="https://agentmods.dev/skills/marchatton/agent-skills/oracle"><img src="https://agentmods.dev/badge/skills/marchatton/agent-skills/oracle.svg" alt="Measured on agentmods" height="20"></a>

Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,708 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.

Origin 92% copy Near-identical to another mod 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.

Model	Per session	Once invoked
Fable 5.1	$0.00043	$0.01708
Opus 5	$0.00022	$0.00854
Sonnet 5	$0.00009	$0.00342
Haiku 4.5	$0.00004	$0.00171

Measured 8d ago against content hash ae1795f06e18, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, 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 8d 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.

Origin

This is a copy

92% identical to oracle — 15 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.agents/skills/00-utilities/oracle/SKILL.md · 120 lines

How it starts

The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.

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)

Pick a tight file set (fewest files that still contain the truth).
Preview what you’re about to send (--dry-run + --files-report when needed).
Run in browser mode for the usual GPT‑5.2 Pro ChatGPT workflow; use API only when you explicitly want it.
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):
- Store bundles in git-tracked tmp/ locations so they can be reused by automations later:
  - If the work is tied to a dossier under docs/04-projects/.../<dossier>/: write to <dossier>/tmp-oracle/.
  - Otherwise: write to docs/98-tmp/oracle/.
- npx -y @steipete/oracle --render --copy -p "<task>" --file "src/**"
- Note: --copy is a hidden alias for --copy-markdown.
- Save-to-file (recommended so it can be committed):
  - Dossier work:
    - mkdir -p "<dossier>/tmp-oracle" && npx -y @steipete/oracle --render -p "<task>" --file "src/**" > "<dossier>/tmp-oracle/oracle-bundle_<slug>.md"
  - Non-dossier work:
    - mkdir -p docs/98-tmp/oracle && npx -y @steipete/oracle --render -p "<task>" --file "src/**" > "docs/98-tmp/oracle/oracle-bundle_<slug>.md"

Read the full file on GitHub · 120 lines

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.

8d ago First seen · 120 lines · 43 tokens per session scan A ae1795f06e18

Subscribe to this mod's changes

oracle is a skill published in the GitHub repository marchatton/agent-skills (5 stars, last pushed 6mo ago), licensed MIT. It adds 43 tokens to every session and 1,708 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 92% identical to oracle, differing in 15 lines, and is treated as a copy.

Code review Debugging

adversarial-reviewer

Adversarial code review that assumes bugs exist and hunts for them. Use when asked to review code, find bugs, audit for correctness, stress-test a PR, or when someone says "tear this apart" or "what's wrong with this". Give no benefit of the doubt — every line is guilty until proven innocent.

emdash-cms/emdash · 71 tokens

gsd-ns-review

Route to the appropriate quality / review skill based on the user's intent. gsd-code-review-fix was absorbed by gsd-code-review --fix in #2790.

open-gsd/gsd-core · 16 tokens

issue

Use when starting a chain from a GitHub issue — turning an issue URL or number into a triaged, planned, dispatched, and reviewed pull request. Classifies the thread (bug → root-cause discipline, feature → plan chain, question → drafted reply), synthesizes a spec from the issue's own acceptance criteria, then runs the…

jeremylongshore/tons-of-skills-marketplace · 115 tokens

oracle