A technical adviser with separate modes for examining a code repository or researching information outside it. It is intended for architecture choices, debugging, security analysis, and second opinions.

Use it to explore a repository, trace bugs, assess security, compare implementation choices with current practices, or research a technical question.

It gives structured investigation when the answer may depend on code, current external guidance, or both.

oracle — Skill for Claude Code by andreasasprou/agent-skills

Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code

/plugin marketplace add andreasasprou/agent-skills

Claude Code

/plugin install oracle

Made for: Claude Code.

Or install oracle, the plugin that ships this one along with the rest of its 1 skill.

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/andreasasprou/agent-skills/oracle/github.svg)](https://agentmods.dev/skills/andreasasprou/agent-skills/oracle)

Your own site

<a href="https://agentmods.dev/skills/andreasasprou/agent-skills/oracle"><img src="https://agentmods.dev/badge/skills/andreasasprou/agent-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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/andreasasprou/agent-skills/oracle"><img src="https://agentmods.dev/badge/skills/andreasasprou/agent-skills/oracle.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 81 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,400 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 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.

Model	Per session	Once invoked
Fable 5.1	$0.00081	$0.02400
Opus 5.5	$0.00032	$0.00960
Sonnet 5.5	$0.00016	$0.00480
Haiku 4.5	$0.00008	$0.00240

Measured 2mo ago against content hash dc124360e543, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 2mo ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/oracle.ts), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

plugins/oracle/skills/oracle/SKILL.md · 256 lines

How it starts

The opening of the file, as written. The whole thing — 256 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Oracle - Unified Technical Advisor

Two complementary modes for different types of questions.

Routing Decision

Ask: "Is the truth external, or is it in our code?"

Truth Location	Mode	Model
In our code	Repo	`gpt-5.2` xhigh via Codex SDK
External (docs, standards, comparisons)	Web	`5.2 Thinking` + Heavy (default)
Complex research needing web synthesis	Web	`gpt-5.2-pro` (escalation)
Both (compare impl vs standards)	Parallel	Run both modes

Commands

Script root: ${CLAUDE_PLUGIN_ROOT}/skills/oracle/scripts

Repo Oracle (codebase exploration)

bun ${CLAUDE_PLUGIN_ROOT}/skills/oracle/scripts/oracle.ts "question"

Capabilities: Explores files, runs commands, searches web (read-only sandbox).

Web Oracle (`@steipete/oracle` CLI)

The CLI 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 workflow: --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.

Quick reference

# Default: 5.2 Thinking with Heavy reasoning (fast questions)
npx -y @steipete/oracle --engine browser --model "5.2 Thinking" --browser-thinking-time heavy -p "question"

# Escalation: gpt-5.2-pro (Deep Research - complex multi-source research)
npx -y @steipete/oracle --engine browser --model gpt-5.2-pro -p "question"

# Include repo context (curated files)
npx -y @steipete/oracle --engine browser --model "5.2 Thinking" --browser-thinking-time heavy \
  --file "src/auth/**/*.ts" \
  --file "!**/*.test.ts" \
  -p "question with context"

Preview & dry-run (no tokens spent)

Always preview before large runs to check token budget and file selection.

# Summary preview
npx -y @steipete/oracle --dry-run summary -p "<task>" --file "src/**" --file "!**/*.test.*"

# Full preview
npx -y @steipete/oracle --dry-run full -p "<task>" --file "src/**"

# Token/cost sanity check
npx -y @steipete/oracle --dry-run summary --files-report -p "<task>" --file "src/**"

Read the full file on GitHub · 256 lines

Files

What ships with it

2 files 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.

2mo ago First seen · 256 lines · 81 tokens per session scan A dc124360e543

Subscribe to this mod's changes

oracle is a skill published in the GitHub repository andreasasprou/agent-skills (7 stars, last pushed 4mo ago), licensed MIT. It adds 81 tokens to every session and 2,400 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-08-31.

Debugging Research

oracle next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
oracleandreasasprou/agent-skills	Skill	7	4mo ago	MIT	A	81	Claude Code
systematic-debuggingopen-metadata/OpenMetadata	Skill	16k	yesterday	Apache-2.0	A	37	Claude Code
log-error-digestzebbern/claude-code-guide	Skill	4.7k	3d ago	MIT	A	71	Claude Code, Codex
cwv-optimizeradobe/skills	Skill	319	yesterday	Apache-2.0	A	112	Claude Code
ci-fixersipyourdrink-ltd/bernstein	Skill	1.2k	yesterday	Apache-2.0	A	15	Claude Code, Codex
incident-response-incident-responsermyndharis/antigravity-skills	Skill	1.9k	23d ago	MIT	A	36	Claude Code
triaging-web-analytics-supportPostHog/posthog	Skill	41k	yesterday	none	A	151	Claude Code, Codex