verify-before-done

verify-before-done is a skill for Claude Code, Codex from New1Direction/korgex. It costs 20 tokens per session (261 once invoked), scanned A, original, MIT.

A completion-checking practice for coding work: verify the edited files, run relevant checks, review the request, and report only what you confirmed.

In plain words
What is it for?
Use it before reporting work as done, especially after code changes, to reread edits, run tests or linters, check task items, and state any untested or unfinished parts.
Why use it?
It prevents claiming that a task is finished when tests, builds, files, or requested steps are still incomplete.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

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/new1direction/korgex/verify-before-done
Any agent
npx skills add New1Direction/korgex --skill verify-before-done
Clone the repo
git clone --depth 1 https://github.com/New1Direction/korgex

Made for: Claude Code, Codex.

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-before-done

README.md
[![agentmods](https://agentmods.dev/badge/skills/new1direction/korgex/verify-before-done.svg)](https://agentmods.dev/skills/new1direction/korgex/verify-before-done)
Your own site
<a href="https://agentmods.dev/skills/new1direction/korgex/verify-before-done"><img src="https://agentmods.dev/badge/skills/new1direction/korgex/verify-before-done.svg" alt="Measured on agentmods" height="20"></a>
Per session 20 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 261 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00020 $0.00261
Opus 5 $0.00010 $0.00130
Sonnet 5 $0.00004 $0.00052
Haiku 4.5 $0.00002 $0.00026

Measured 6d ago against content hash 42881743bef9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

verify-before-done 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 6d 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.

src/skills_builtin/verify-before-done/SKILL.md · 23 lines

What it actually says

The most common failure is claiming done while something is broken or unfinished. korgex records everything to a verifiable ledger — match that standard: report only what you've checked.

  1. Re-read your own change. Read the files you edited back; confirm the edit applied as intended and nothing adjacent broke.
  2. Run the checks. Run the relevant tests / build / linter. Quote the actual result. If tests fail, say so with the output — do not claim success.
  3. Check the checklist. If you used TaskCreate, confirm every item is completed. Open items mean you're not done.
  4. Match the request. Re-read the original ask. Did you do all of it, or only the easy part? Surface anything you skipped or couldn't do.
  5. Report honestly. State plainly what's done and verified, what's untested, and what's left. If a step was skipped, say so. No hedging on verified work; no confidence on unverified work.
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. 6d ago First seen · 23 lines · 20 tokens per session scan A 42881743bef9

Subscribe to this mod's changes

verify-before-done is a skill published in the GitHub repository New1Direction/korgex (5 stars, last pushed 2mo ago), licensed MIT. It adds 20 tokens to every session and 261 once invoked, about $0.0001 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

vibe-ui-design

Use when designing UI/UX, defining design systems, choosing color palettes, typography, spacing, or component primitives. Triggers on "design system", "design tokens", "color palette", "UI 设计", "深色工业风", "design language".

xushuodasd/VIBE-Claude-Plugin · 58 tokens

vibe-ui-beautify

Use when adding animations, micro-interactions, 3D effects, glassmorphism, or "juicy" tactile feedback to UI components. Triggers on "animation", "hover effect", "transition", "动效", "果汁感", "Framer Motion", "GSAP", "3D 视效".

xushuodasd/VIBE-Claude-Plugin · 74 tokens

vibe-security

Use when performing security audits, vulnerability scanning, dependency checks, or secure code reviews. Triggers on "security audit", "scan vulnerabilities", "安全审查", "漏洞扫描", "OWASP", "dependency check".

xushuodasd/VIBE-Claude-Plugin · 49 tokens

vibe-autopilot

Use this skill when the user requests fully autonomous, 24/7 hands-free development without human intervention.

xushuodasd/VIBE-Claude-Plugin · 27 tokens

vibe-test

Use when writing tests, performing unit testing, integration testing, or verifying system functionality. Triggers on "write tests", "run tests", "add unit test", "TDD", "测试", "跑测试".

xushuodasd/VIBE-Claude-Plugin · 48 tokens

vibe-assets

Use when the project needs real images, icons, fonts, illustrations, or logos. Automatically fetches and integrates assets from CDN libraries and AI generation APIs. Triggers on "images", "icons", "fonts", "assets", "素材", "图片资源", "图标库", "字体".

xushuodasd/VIBE-Claude-Plugin · 65 tokens