verification-before-completion

verification-before-completion is a skill for Claude Code, Codex from myths-labs/muse. It costs 71 tokens per session (2,664 once invoked), scanned A, original, MIT.

A checklist for verifying coding work before declaring it complete. It requires defining observable acceptance criteria and running fresh checks.

In plain words
What is it for?
Use it before reporting that a feature is finished, a bug is fixed, tests pass, or a change is ready to commit or release.
Why use it?
It reduces the risk of claiming a fix works without evidence, including in error cases and integrations.

Skill for Claude CodeCodex

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

Good fit Use it before reporting that a feature is finished, a bug is fixed, tests pass, or a change is ready to commit or release.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/myths-labs/muse/verification-before-completion
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 myths-labs/muse --skill verification-before-completion
Clone the repo
git clone --depth 1 https://github.com/myths-labs/muse

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 verification-before-completion

README.md
[![agentmods](https://agentmods.dev/badge/skills/myths-labs/muse/verification-before-completion.svg)](https://agentmods.dev/skills/myths-labs/muse/verification-before-completion)
Your own site
<a href="https://agentmods.dev/skills/myths-labs/muse/verification-before-completion"><img src="https://agentmods.dev/badge/skills/myths-labs/muse/verification-before-completion.svg" alt="Measured on agentmods" height="20"></a>
Per session 71 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,664 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 2 findings, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Excessive Agency · line 10
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
  • medium MCP Rug Pull · line 210
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
How audits are shown
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 $0.00071 $0.02664
Opus 5 $0.00036 $0.01332
Sonnet 5 $0.00014 $0.00533
Haiku 4.5 $0.00007 $0.00266

Measured 8d ago against content hash c317b91b9a0f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

verification-before-completion 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 8d 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.

| "Code looks right" | "Ran curl/browser, saw expected response body" |
skills/core/verification-before-completion/SKILL.md · 275 lines

How it starts

The opening of the file, as written. The whole thing — 275 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Verification Before Completion

Overview

Claiming work is complete without verification is dishonesty, not efficiency.

Core principle: Evidence before claims, always.

Violating the letter of this rule is violating the spirit of this rule.

The Iron Law

NO COMPLETION CLAIMS WITHOUT FRESH VERIFICATION EVIDENCE

If you haven't run the verification command in this message, you cannot claim it passes.


Phase 0: AC-First Workflow (写代码前)

💡 Inspired by opslane/verify: "You can't trust what an agent produces unless you told it what 'done' looks like before it started."

Before writing any code, define Acceptance Criteria:

## Acceptance Criteria

### AC-1: [Feature/behavior name]
- [Observable outcome 1]
- [Observable outcome 2]

### AC-2: [Edge case / error handling]
- [What user sees]
- [What system does]

### AC-3: [Integration / compatibility]
- [Works with X]
- [Doesn't break Y]

AC Writing Rules:

  • Each AC must be independently verifiable (pass or fail, no "partially")
  • Use observable behavior not implementation details ("User sees X" not "Code calls Y")
  • Include negative cases (what happens when things go wrong)
  • For frontend: specify exact text, navigation, visual state
  • For backend: specify status codes, response shape, error messages
  • For mobile: specify platform behavior, i18n, haptics

When to write ACs:

  • ✅ Before ANY new feature (even "simple" ones)
  • ✅ Before bug fixes (AC = "original symptom no longer occurs" + "no regression")
  • ✅ Before refactors (AC = "all existing behavior preserved")
  • ❌ NOT needed for: config changes, docs-only, status file updates

Phase 1: Pre-Flight Check (零成本快速失败)

💡 Pure checks, no LLM tokens. Fail fast before spending effort.

Before starting work, verify preconditions:

PRE-FLIGHT CHECKLIST (30 seconds, zero tokens):
□ Dev server running? (or can it start?)
□ Target files exist and are accessible?
□ Dependencies installed? (node_modules, Pods, etc.)
□ Auth/session valid? (Supabase, App Store Connect, etc.)
□ Branch correct? (not accidentally on main when should be feature)
□ Previous build clean? (no leftover errors)

Read the full file on GitHub · 275 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. 8d ago First seen · 275 lines · 71 tokens per session scan A c317b91b9a0f

Subscribe to this mod's changes

verification-before-completion is a skill published in the GitHub repository myths-labs/muse (32 stars, last pushed yesterday), licensed MIT. It adds 71 tokens to every session and 2,664 once invoked, about $0.0004 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 2026-08-30.