sanity-check

sanity-check is a skill for Claude Code, Codex from jenningsallen-art/second-brain-os. It costs 169 tokens per session (1,269 once invoked), scanned A, original, MIT.

A guide for testing assumptions and claims against notes in an Obsidian vault and outside evidence. It is designed to challenge agreement and expose overlooked information.

In plain words
What is it for?
Reviewing plans, challenging assumptions, checking claims, finding contradictions in past notes, and stress-testing decisions.
Why use it?
It reduces confirmation bias by checking whether a belief matches recorded decisions, current context, and available evidence.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Reviewing plans, challenging assumptions, checking claims, finding contradictions in past notes, and stress-testing decisions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jenningsallen-art/second-brain-os/sanity-check
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 jenningsallen-art/second-brain-os --skill sanity-check
Clone the repo
git clone --depth 1 https://github.com/jenningsallen-art/second-brain-os

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.

agentmods badge for sanity-check

README.md
[![agentmods](https://agentmods.dev/badge/skills/jenningsallen-art/second-brain-os/sanity-check/github.svg)](https://agentmods.dev/skills/jenningsallen-art/second-brain-os/sanity-check)
Your own site
<a href="https://agentmods.dev/skills/jenningsallen-art/second-brain-os/sanity-check"><img src="https://agentmods.dev/badge/skills/jenningsallen-art/second-brain-os/sanity-check/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 sanity-check

Your own site · 80×15
<a href="https://agentmods.dev/skills/jenningsallen-art/second-brain-os/sanity-check"><img src="https://agentmods.dev/badge/skills/jenningsallen-art/second-brain-os/sanity-check.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 169 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,269 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00169 $0.01269
Opus 5 $0.00084 $0.00634
Sonnet 5 $0.00034 $0.00254
Haiku 4.5 $0.00017 $0.00127

Measured 11d ago against content hash b3e157620f63, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

sanity-check 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 11d 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/sanity-check/SKILL.md · 109 lines

How it starts

The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Sanity Check

The anti-echo-chamber skill. While thinking-partner provides frameworks, this skill does something different: it checks claims against evidence. The vault is a living record of decisions, meeting notes, and context — use it to hold the user accountable to their own prior thinking and to external reality.

When to Activate

Explicit triggers:

  • "Sanity check this"
  • "Am I wrong about X?"
  • "Audit my assumptions"
  • "What does the vault say about this?"
  • "Stress test this against what we know"

Proactive triggers (use with a light touch):

  • The user makes a factual claim about a project, person, or decision that can be verified in the vault
  • The user's current plan contradicts something captured in a previous meeting note or decision log
  • An assumption in play hasn't been re-examined in 2+ weeks (check file dates in the vault's project notes and people directory)
  • The user and Claude have been in agreement for 4+ exchanges on a strategic topic without surfacing a counter-argument
  • The user uses "obviously" or "everyone knows" — these phrases often mark unexamined assumptions

The Sanity Check Process

1. Identify the Claims

Extract the specific claims, assumptions, or beliefs being tested. Be precise:

  • NOT: "The user thinks the strategy is good"
  • YES: "The user assumes (a) the data chain will be ready by Q3, (b) the executive sponsor supports the hire, (c) the team has capacity to absorb a new tool"

2. Evidence Audit (Vault-First)

For each claim, search the vault systematically:

Check project notes in 1 - Projects/ — Is there project context that confirms or contradicts? Check TASKS.md — Are there stale items that suggest a claim about progress is optimistic? Check recent meeting notes in 1 - Projects/ and 2 - Areas/ — Did someone say something in a meeting that cuts against the current assumption? Check people profiles in 3 - Resources/ — Is the user assuming someone's position without recent validation? Check Daily Notes/ — Has this topic come up before? What was the conclusion then?

Read the full file on GitHub · 109 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. 11d ago First seen · 109 lines · 169 tokens per session scan A b3e157620f63

Subscribe to this mod's changes

sanity-check is a skill published in the GitHub repository jenningsallen-art/second-brain-os (2 stars, last pushed 1mo ago), licensed MIT. It adds 169 tokens to every session and 1,269 once invoked, about $0.0008 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 2026-08-31.

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

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens