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 jonZlotnik/how-to-agent --skill prove-dont-assumegit clone --depth 1 https://github.com/jonZlotnik/how-to-agentWrote 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/jonzlotnik/how-to-agent/prove-dont-assume)<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.
<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>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 | $0.00056 | $0.00527 |
| Opus 5 | $0.00028 | $0.00264 |
| Sonnet 5 | $0.00011 | $0.00105 |
| Haiku 4.5 | $0.00006 | $0.00053 |
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.
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
- List the assumptions the current plan depends on. Write each as a falsifiable sentence: "X is non-null when reaching line Y."
- 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. - Run the checks. Don't predict the outcome before running; predictions bias what you see.
- 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.
- 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.
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.
- 12d ago First seen · 37 lines · 56 tokens per session scan A ca74854c2e87
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.
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…
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.
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.
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.
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…
byted-util-volcengine-detect-retry
An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.