oracle-review

oracle-review is a skill for Claude Code from pedrohcgs/claude-code-my-workflow. It costs 0 tokens per session (911 once invoked), scanned A, original, MIT.

A workflow for sending a paper, proof, estimator, or replication package to an external AI referee and evaluating the returned review. A replication package is the code and data needed to reproduce research results.

In plain words
What is it for?
Use it for external checks of research correctness, proofs, statistical methods, replication materials, or named fixes from an earlier review.
Why use it?
It adds an independent review round and separates useful evidence from unsupported criticism before changes are made.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions Claude Code.

Good fit Use it for external checks of research correctness, proofs, statistical methods, replication materials, or named fixes from an earlier review.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/pedrohcgs/claude-code-my-workflow/oracle-review
About the project

claude-code-my-workflow is a forkable setup for using Claude Code to produce and review academic papers, slides, data analyses, and replication packages. Researchers use its agents, skills, rules, hooks, and quality checks to coordinate these tasks and verify their results. The catalogue entries define the reusable workflow components for Claude Code.

pedrohcgs/claude-code-my-workflow · 1,569 stars · on GitHub · psantanna.com

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 pedrohcgs/claude-code-my-workflow --skill oracle-review
Clone the repo
git clone --depth 1 https://github.com/pedrohcgs/claude-code-my-workflow

Made for: Claude Code.

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-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/pedrohcgs/claude-code-my-workflow/oracle-review/github.svg)](https://agentmods.dev/skills/pedrohcgs/claude-code-my-workflow/oracle-review)
Your own site
<a href="https://agentmods.dev/skills/pedrohcgs/claude-code-my-workflow/oracle-review"><img src="https://agentmods.dev/badge/skills/pedrohcgs/claude-code-my-workflow/oracle-review/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-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/pedrohcgs/claude-code-my-workflow/oracle-review"><img src="https://agentmods.dev/badge/skills/pedrohcgs/claude-code-my-workflow/oracle-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 911 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 pass 7 Sept 2026
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 $0.00000 $0.00911
Opus 5 $0.00000 $0.00456
Sonnet 5 $0.00000 $0.00182
Haiku 4.5 $0.00000 $0.00091

Measured 10d ago against content hash 5200f8d0f719, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

oracle-review 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 10d 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.

.claude/skills/oracle-review/SKILL.md · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Oracle review — an independent referee, then an honest triage

Never launch a bare Oracle run. This skill is the driver; the mechanics and the full contract live in external-oracle-process.md. Read it before the first run in a project — it carries setup, flags, artifact layout, the payload cliff, and the failure modes that have actually cost runs.

Compose with /credible-claims (the brief before, the claim record after) and /deep-audit (exhaustive in-house coverage first, so the oracle is confirmation, not discovery).

1. Brief before launch (5 lines)

  • Question — what must this review answer? (correctness audit? venue-referee simulation? confirm N named fixes cleared?)
  • Scope — what is IN, and what is HELD (standing rulings; list them so triage can filter).
  • Completion — what verdict or evidence ends this run.
  • Required evidence — findings carry location + failing case, or they do not count.
  • Escalation — which finding types come back to the user before any fix: estimand changes, assumption concessions, reporting-language downgrades.

2. Assign coverage — never let the referee sample

Maintain a statement inventory and a cross-round coverage ledger. Each round assigns what to audit and requires the referee to report what it actually verified, so union coverage reaches 100% instead of drifting toward whatever is easiest to read.

3. Launch

Mechanics, flags, and gotchas: the reference, §2–§3. Smoke-test first; check --files-report against the payload cliff; a run with no conversation URL never happened.

4. Triage — adjudicate, never ingest

Every finding is a CANDIDATE. Hand the batch to /adjudicate-review: judge each against the actual text, compute the computable first, filter the HELD list, and assign CONFIRMED / REFUTED / DOWNGRADED.

Oracle agreeing with your own reading is not independent confirmation — different models correlate on the same wrong answer.

Read the full file on GitHub · 66 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.

  1. 10d ago First seen · 66 lines · 0 tokens per session scan A 5200f8d0f719

Subscribe to this mod's changes

oracle-review is a skill published in the GitHub repository pedrohcgs/claude-code-my-workflow (1,569 stars, last pushed 16d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 911 tokens. 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.

Related

Other skills, from other repositories