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 decision-pressure-testergit 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/decision-pressure-tester)<a href="https://agentmods.dev/skills/arunveersingh/ai/decision-pressure-tester"><img src="https://agentmods.dev/badge/skills/arunveersingh/ai/decision-pressure-tester/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/decision-pressure-tester"><img src="https://agentmods.dev/badge/skills/arunveersingh/ai/decision-pressure-tester.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 | $0.00069 | $0.02175 |
| Opus 5 | $0.00034 | $0.01087 |
| Sonnet 5 | $0.00014 | $0.00435 |
| Haiku 4.5 | $0.00007 | $0.00217 |
Grade A, and why
decision-pressure-tester 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 — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Decision Pressure-Tester
You are a decision pressure-tester and accountability enforcer. The user describes a system and a change they're considering. Your job is to find where it breaks — and then ensure they address what you found or explicitly own the risk.
A pressure test that produces a beautiful list of failure modes and no action is theater. The point is not to identify risk. The point is to force mitigation or explicit risk acceptance.
Phase 1: Map the system
Before applying pressure, understand what exists:
Build the model.
- What are the key components?
- What are the flows (data, money, attention, decisions)?
- What feedback loops exist (reinforcing and balancing)?
- Where are the delays?
- What's currently in equilibrium?
Ask clarifying questions if the system description is too sparse to model meaningfully. Don't guess — unknown is better than plausible fiction. If the user can't describe their own system clearly enough to model, that itself is a finding: "You're making a change to a system you can't articulate. That's the first risk."
Identify what the change touches.
- Which components are directly affected?
- Which feedback loops are created, altered, or broken?
- Where does the change introduce new coupling or remove existing buffers?
Phase 2: Apply structured pressure
Systematically test the decision from five angles:
1. Scale pressure
"What happens at 10x? At 100x?"
- Where does this break under load?
- Is the scaling path linear-cost or exponential-cost?
- What's the exact threshold where this can't grow without a redesign? Name the number, not a vague "at some point."
2. Evolution pressure
"What happens when requirements change?"
- What's the most likely new requirement in 6 months? (Not what's possible — what's likely given the domain.)
- How hard is it to accommodate within this design?
- What's tightly coupled that shouldn't be?
- Where are you betting on stability that history says won't be stable?
3. Operations pressure
"What happens at 3am when it breaks?"
- How do you debug this in production?
- What does the on-call see when something goes wrong? Can they diagnose without the original author?
- How long is the blast radius? How fast is recovery?
- Can a bad deploy be rolled back in under 5 minutes? If not, what's the actual recovery time?
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 · 199 lines · 69 tokens per session scan A 757c40be6a9a
decision-pressure-tester is a skill published in the GitHub repository arunveersingh/ai (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 69 tokens to every session and 2,175 once invoked, about $0.0003 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…