verify-result

verify-result is a skill for Claude Code, Codex from pandysp/claude-plugins. It costs 110 tokens per session (787 once invoked), scanned A, original, MIT.

A black-box check of an agent's output from the user's point of view. Instead of only rereading code or running tests, it uses the finished result and looks for concrete evidence that it works.

In plain words
What is it for?
Use it to verify APIs, websites, command-line tools, libraries, configurations, migrations, bug fixes, refactors, documents, slide decks, and reports.
Why use it?
It helps reveal problems that ordinary review or unit tests can miss, such as a broken user flow or a configuration that is never read.

Skill for Claude CodeCodex

Part of the verify-result plugin — 1 skill shipped together

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 skills/pandysp/claude-plugins/verify-result
Any agent
npx skills add pandysp/claude-plugins --skill verify-result
Clone the repo
git clone --depth 1 https://github.com/pandysp/claude-plugins

Made for: Claude Code, Codex.

Or install verify-result, the plugin that ships this one along with the rest of its 1 skill.

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 verify-result

README.md
[![agentmods](https://agentmods.dev/badge/skills/pandysp/claude-plugins/verify-result.svg)](https://agentmods.dev/skills/pandysp/claude-plugins/verify-result)
Your own site
<a href="https://agentmods.dev/skills/pandysp/claude-plugins/verify-result"><img src="https://agentmods.dev/badge/skills/pandysp/claude-plugins/verify-result.svg" alt="Measured on agentmods" height="20"></a>
Per session 110 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 787 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00110 $0.00787
Opus 5 $0.00055 $0.00394
Sonnet 5 $0.00022 $0.00157
Haiku 4.5 $0.00011 $0.00079

Measured 5d ago against content hash 9c4325f5cdec, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

verify-result scanned grade A with 1 finding 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 5d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

| Backend API | curl endpoints, check responses |
plugins/verify-result/skills/verify-result/SKILL.md · 51 lines

How it starts

The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Verify result: prove it works, show evidence

Prove the work actually works. Not by re-reading what you wrote. Not by running unit tests. By examining the output from the consumer's perspective and showing concrete evidence.

"I produced it correctly" is not verification. "The tests pass" is not verification. Verification is: here's what happens when I actually use this thing, look at this thing, run this thing.

How to verify, by output type

Output How to verify
Backend API curl endpoints, check responses
Frontend open browser, click through the flow, read browser/server logs, screenshot each step
CLI tool run with real inputs, show output
Library / utility write a small usage script, execute it
Config / infra verify the effect (does the config actually get read?)
Data migration check data state before and after
Bug fix reproduce the original bug scenario, show it's fixed
Refactor run the same operations, show identical behavior
Rendered document (Typst, LaTeX, markdown) render, open the file, read every page
Slide deck render, open, examine each slide
Generated report open, read, spot-check claims and data
Writing / copy read back, verify references, check claims

If the work spans multiple types, verify each.

Procedure

  1. Stand up the environment if needed. Reuse a running instance if one exists; otherwise start what you need in the background and wait for readiness.

  2. Verify each case: happy path, error cases, edge cases, and (for bug fixes) the original failure scenario. For each:

    • State what you're checking ("Verifying that POST /api/users returns 201").
    • Show the command, action, or rendered output.
    • Show the result. Paste output, attach screenshot, open the artifact.
    • Assess: does this match expectations? If not, why?
  3. Clean up. Write verification artifacts (screenshots, logs, test files) to /tmp/ by default. If any landed in the repo, remove them before reporting.

Read the full file on GitHub · 51 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. 5d ago First seen · 51 lines · 110 tokens per session scan A 9c4325f5cdec

Subscribe to this mod's changes

verify-result is a skill published in the GitHub repository pandysp/claude-plugins (5 stars, last pushed 14d ago), licensed MIT. It adds 110 tokens to every session and 787 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

microsoft/ai-agents-for-beginners · 200 tokens

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…

vercel/next.js · 95 tokens

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…

vercel/next.js · 170 tokens

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…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens