A verification command that gathers concrete evidence that a coding task is complete and working.

Use it at the end of a task to run tests and type checks, compare behavior with the main branch, review the diff, audit changed files, and report whether the work is proven.

It prevents declaring success based only on an informal check by requiring test results, type-checking, diff inspection, security review, and edge-case demonstrations.

prove-it — Command for Claude Code by liortesta: A verification command that gathers concrete evidence that a…

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.

agentmods

npx agentmods add commands/liortesta/clawdagent/prove-it

Clone the repo

git clone --depth 1 https://github.com/liortesta/ClawdAgent

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/liortesta/clawdagent/prove-it.svg)](https://agentmods.dev/commands/liortesta/clawdagent/prove-it)

Your own site

<a href="https://agentmods.dev/commands/liortesta/clawdagent/prove-it"><img src="https://agentmods.dev/badge/commands/liortesta/clawdagent/prove-it.svg" alt="Measured on agentmods" height="20"></a>

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 331 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

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.

Model	Per session	Once invoked
Fable 5	$0.00000	$0.00331
Opus 5	$0.00000	$0.00166
Sonnet 5	$0.00000	$0.00066
Haiku 4.5	$0.00000	$0.00033

Measured 4d ago against content hash e05cf4062a73, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

prove-it 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 4d 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.

.claude/commands/prove-it.md · 50 lines

What it actually says

Prove It Works

Before considering this task done, provide concrete proof that everything works.

Verification Steps:

Tests: Show the test output — all tests passing with output visible
Type Safety: Run type checker — zero errors
Before/After: Compare behavior on main branch vs this branch
Diff Review: Show the diff is minimal and clean — no unnecessary changes
Security: Run security audit on changed files using the security-auditor agent
Edge Cases: Demonstrate at least 3 edge cases are handled correctly

Output Format:

## Proof of Correctness

### Tests
[paste test output]
Status: ALL PASSING / X FAILING

### Type Check
[paste type check output]
Status: CLEAN / X ERRORS

### Diff Summary
- Files changed: X
- Lines added: X
- Lines removed: X
- Unnecessary changes: NONE / [list]

### Security Audit
[security-auditor findings]
Status: CLEAN / X ISSUES

### Edge Cases Verified
1. [edge case]: [result]
2. [edge case]: [result]
3. [edge case]: [result]

### VERDICT: PROVEN / NOT PROVEN

Rules:

If ANY check fails — fix it immediately, don't ask permission
Do NOT mark task as done until ALL checks pass
The diff must be minimal — remove any unrelated changes
If you can't prove it, say so honestly

$ARGUMENTS

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.

4d ago First seen · 50 lines · 0 tokens per session scan A e05cf4062a73

Subscribe to this mod's changes

prove-it is a command published in the GitHub repository liortesta/ClawdAgent (11 stars, last pushed 8d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 331 tokens. 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 2026-08-30.

Testing

prove-it

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

Prove It Works

Verification Steps:

Output Format:

Rules:

What this file has done since we first saw it

Other commands, from other repositories

git

checklist

clarify

specify

converge

implement