agent-oracle

A read-only expert consultation for one difficult, high-impact design or debugging question that remains unresolved after direct investigation.

In plain words
What is it for?
Use it for a specific unresolved tradeoff, suspected invariant violation, or failure sequence—not for routine review or broad searches.
Why use it?
It provides a second analysis for choices between plausible designs or for cross-file problems whose cause or rule is still unclear.

Skill for Claude CodeCodex

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.

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

Made for: Claude Code, Codex.

Per session 93 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 388 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00093 $0.00388
Opus 5 $0.00046 $0.00194
Sonnet 5 $0.00019 $0.00078
Haiku 4.5 $0.00009 $0.00039

Measured 2d ago against content hash 4d7d452f6aa9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-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 2d 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/agent-oracle/SKILL.md · 34 lines

What it actually says

Agent Oracle

Spawn a read-only advisor subagent for exactly one unresolved decision, invariant, or debugging question. This is the most expensive role: consult it only when the answer would materially change a high-impact decision, and never spawn it merely to verify finished work.

When not to use

  • Routine self-review, general reassurance, or a second pair of eyes.
  • Broad "find anything I missed" requests — identify a concrete concern first.
  • Work that is merely complex or high-impact without an unresolved question.
  • Searches (agent-finder / agent-librarian) or making code changes (do it yourself or delegate implementation).

How to write the task

  • State the unresolved question, what you already checked, and why the answer changes the decision.
  • Constrain it to one decision, invariant, or debugging question; tell the oracle what to ignore so scope creep doesn't dilute the answer.
  • Include the necessary context directly: relevant file paths inline, the intended behavior, and the constraints or product choices already settled.
  • If asking about current changes, say so explicitly so it inspects git diff.
  • State the output you need: the invariant and failing sequence if one exists, or a recommended alternative plus the evidence that would reverse the decision.
  • For a follow-up review, name the prior finding and the exact change that should resolve it.
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. 2d ago First seen · 34 lines · 93 tokens per session scan A 4d7d452f6aa9

Subscribe to this mod's changes

agent-oracle is a skill published in the GitHub repository vaayne/agent-kit (53 stars, last pushed 5d ago), licensed MIT. It adds 93 tokens to every session and 388 once invoked, about $0.0005 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens