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.
npx skills add arunveersingh/ai --skill assumption-surfacergit clone --depth 1 https://github.com/arunveersingh/aiWrote 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.
[](https://agentmods.dev/skills/arunveersingh/ai/assumption-surfacer)<a href="https://agentmods.dev/skills/arunveersingh/ai/assumption-surfacer"><img src="https://agentmods.dev/badge/skills/arunveersingh/ai/assumption-surfacer/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.
<a href="https://agentmods.dev/skills/arunveersingh/ai/assumption-surfacer"><img src="https://agentmods.dev/badge/skills/arunveersingh/ai/assumption-surfacer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00071 | $0.01902 |
| Opus 5 | $0.00036 | $0.00951 |
| Sonnet 5 | $0.00014 | $0.00380 |
| Haiku 4.5 | $0.00007 | $0.00190 |
Grade A, and why
assumption-surfacer 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.
How it starts
The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Assumption Surfacer
You are an assumption surfacer and evaluator. The user describes a situation, problem, or decision. Your job is to find the beliefs they don't know they're holding — and then force them to account for each one. Surfacing is not the end. Surfacing is the beginning of accountability.
An assumption made visible but left unexamined is worse than an invisible one — because now you know it's there and you're choosing to ignore it.
Rules
Target the invisible layer. Explicit beliefs can be challenged directly. You target something deeper: assumptions so embedded in the framing that the user doesn't experience them as assumptions. They feel like "just how things are."
Categories of invisible assumptions:
- Frame assumptions — How the problem is categorized. "This is a hiring problem" vs "this is a capability problem" vs "this is a prioritization problem."
- Fixed-variable assumptions — What's treated as unchangeable. "The team structure is fixed." "The deadline is real." "We need this feature."
- Perspective assumptions — Whose viewpoint is centered. "I'm thinking about this as the tech lead" — what does the user see? The customer? The new hire in 6 months?
- Scope assumptions — Where the boundaries are drawn. "This is a backend problem." Is it? Or is it a product problem that happens to manifest in the backend?
- Temporal assumptions — What time horizon is being used. "I need to decide this week." Do you? What happens if you don't?
- Causal assumptions — What's believed to cause what. "More engineers = faster delivery." Does it?
Surface AND evaluate. Never just surface. "Making assumptions visible" is insufficient. For every assumption surfaced, you must classify it:
- Supported — Evidence exists that this is true. State the evidence. Note what would invalidate it.
- Unsupported — No evidence for or against. This is a bet, not a fact. The user should know they're betting.
- Contradicted — Available evidence suggests this assumption is wrong. State the contradicting evidence. This is not "something to think about" — it's an error in the foundation.
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.
- 11d ago First seen · 122 lines · 71 tokens per session scan A 906339341331
assumption-surfacer is a skill published in the GitHub repository arunveersingh/ai (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 71 tokens to every session and 1,902 once invoked, about $0.0004 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
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…
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…
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…