prove-dont-assume

prove-dont-assume is a skill for Claude Code from jonZlotnik/how-to-agent. It costs 56 tokens per session (527 once invoked), scanned A, original, MIT.

A set of debugging instructions that requires checking important assumptions with small, direct tests. It is meant for situations where an agent may be relying on what it thinks should be true.

In plain words
What is it for?
Use it when debugging stalls, before merging a non-trivial change, or when a library or system boundary needs verification.
Why use it?
It replaces guesses with evidence and helps locate the exact point where a debugging plan or risky change is wrong.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the how-to-agent plugin — 27 skills shipped together

Good fit Use it when debugging stalls, before merging a non-trivial change, or when a library or system boundary needs verification.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jonzlotnik/how-to-agent/prove-dont-assume
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 jonZlotnik/how-to-agent --skill prove-dont-assume
Clone the repo
git clone --depth 1 https://github.com/jonZlotnik/how-to-agent

Made for: Claude Code.

Or install how-to-agent, the plugin that ships this one along with the rest of its 27 skills.

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 prove-dont-assume

README.md
[![agentmods](https://agentmods.dev/badge/skills/jonzlotnik/how-to-agent/prove-dont-assume/github.svg)](https://agentmods.dev/skills/jonzlotnik/how-to-agent/prove-dont-assume)
Your own site
<a href="https://agentmods.dev/skills/jonzlotnik/how-to-agent/prove-dont-assume"><img src="https://agentmods.dev/badge/skills/jonzlotnik/how-to-agent/prove-dont-assume/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 prove-dont-assume

Your own site · 80×15
<a href="https://agentmods.dev/skills/jonzlotnik/how-to-agent/prove-dont-assume"><img src="https://agentmods.dev/badge/skills/jonzlotnik/how-to-agent/prove-dont-assume.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 56 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 527 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 $0.00056 $0.00527
Opus 5 $0.00028 $0.00264
Sonnet 5 $0.00011 $0.00105
Haiku 4.5 $0.00006 $0.00053

Measured 12d ago against content hash ca74854c2e87, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

prove-dont-assume 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 12d 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/prove-dont-assume/SKILL.md · 37 lines

How it starts

The opening of the file, as written. The whole thing — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Prove, Don't Assume

Most debugging dead-ends are paved with unverified assumptions. "It should be non-null here." "This function returns sorted output." "The cache is invalidated." Should is not evidence. Replace every load-bearing belief with a cheap check.

When to use

  • Investigation has stalled and you can't tell which step is wrong
  • About to make a non-trivial change to unfamiliar code
  • A library's behavior at a boundary matters to your fix
  • Someone (including yourself, including an AI) said something that sounds right

Protocol

  1. List the assumptions the current plan depends on. Write each as a falsifiable sentence: "X is non-null when reaching line Y."
  2. For each, write the one-line check. A print, assert, log line, REPL evaluation, or a one-line test. Cheapness matters — if it's hard to verify, refactor until it isn't.
  3. Run the checks. Don't predict the outcome before running; predictions bias what you see.
  4. Act only on what survived. Cross off the disproven assumptions. The bug usually lives in the gap between what you believed and what you measured.
  5. Leave the cheapest checks in as assertions or tests where they'd catch future regressions.

Red flags (rationalizations to reject)

  • "I just read the code, it's obvious." — Reading proves nothing. Run it.
  • "Adding a print is overkill." — Five seconds of printf > thirty minutes of theorizing.
  • "I'm sure the library does X." — Sure enough to run a one-line test? Then prove it.
  • "The types guarantee this." — Types catch a lot. They don't catch runtime data, third-party JSON, or stale caches.

Composes with

  • [[fix-the-problem-not-the-blame]] — proof-driven hypothesis testing is the workhorse step of root-cause analysis.
  • [[design-by-contract]] — assumptions you verify often deserve to become contracts so they can't silently break later.
  • [[listen-to-nagging-doubts]] — when a doubt resists naming, "what would I check?" turns it into a falsifiable assumption.

Read the full file on GitHub · 37 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. 12d ago First seen · 37 lines · 56 tokens per session scan A ca74854c2e87

Subscribe to this mod's changes

prove-dont-assume is a skill published in the GitHub repository jonZlotnik/how-to-agent (2 stars, last pushed 1mo ago), licensed MIT. It adds 56 tokens to every session and 527 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.

Related

Other skills, from other repositories

debug-optimize-lcp

Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…

ChromeDevTools/chrome-devtools-mcp · 99 tokens

systematic-debugging

Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.

open-metadata/OpenMetadata · 37 tokens

diagnose

Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.

emdash-cms/emdash · 43 tokens

repro-admin

Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.

emdash-cms/emdash · 48 tokens

log-error-digest

Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…

zebbern/claude-code-guide · 71 tokens

byted-util-volcengine-detect-retry

An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.

bytedance/agentkit-samples · 101 tokens