Verification Loop

by affaan-mef648e01899bMIT275K starsListed Oct 8, 2026Updated Oct 8, 2026Repository updated 3 days ago

A comprehensive verification system for Claude Code sessions. Use when verifying a Claude Code session's work before claiming it is complete.

Instructions onlySoftware Development

AI-generated overview

Guides an agent through a six-phase verification pass over a code session before declaring work complete.

What it does: The skill defines a verification loop for coding sessions, covering build, type check, lint, test suite, security scan and diff review phases. It lists the commands to run for each phase and the conditions under which to stop and fix problems. It ends with a fixed verification report template showing pass or fail per phase, an overall readiness verdict and issues to fix.
When to use it: Use it after finishing a feature or significant code change, before opening a pull request, after refactoring, or whenever quality gates need to pass. It is also suggested for long sessions, run periodically or after major changes.
Requirements: Instructions only; no scripts are shipped. It assumes an agent able to run shell commands in a project, with tools such as npm, pnpm, tsc, pyright, ruff, git and grep available depending on the stack.

Verification Loop Skill

A comprehensive verification system for Claude Code sessions.

When to Use

Invoke this skill:

After completing a feature or significant code change
Before creating a PR
When you want to ensure quality gates pass
After refactoring

Verification Phases

Phase 1: Build Verification

If build fails, STOP and fix before continuing.

Phase 2: Type Check

Report all type errors. Fix critical ones before continuing.

Phase 3: Lint Check

Phase 4: Test Suite

bash

# Run tests with coveragenpm run test -- --coverage 2>&1 | tail -50
# Check coverage threshold# Target: 80% minimum

# Run tests with coveragenpm run test -- --coverage 2>&1 | tail -50
# Check coverage threshold# Target: 80% minimum

Report:

Total tests: X
Passed: X
Failed: X
Coverage: X%

Phase 5: Security Scan

bash

# Check for secretsgrep -rn "sk-" --include="*.ts" --include="*.js" . 2>/dev/null | head -10grep -rn "api_key" --include="*.ts" --include="*.js" . 2>/dev/null | head -10
# Check for console.loggrep -rn "console.log" --include="*.ts" --include="*.tsx" src/ 2>/dev/null | head -10

# Check for secretsgrep -rn "sk-" --include="*.ts" --include="*.js" . 2>/dev/null | head -10grep -rn "api_key" --include="*.ts" --include="*.js" . 2>/dev/null | head -10
# Check for console.loggrep -rn "console.log" --include="*.ts" --include="*.tsx" src/ 2>/dev/null | head -10

Phase 6: Diff Review

Review each changed file for:

Unintended changes
Missing error handling
Potential edge cases

Output Format

After running all phases, produce a verification report:

VERIFICATION REPORT==================
Build:     [PASS/FAIL]Types:     [PASS/FAIL] (X errors)Lint:      [PASS/FAIL] (X warnings)Tests:     [PASS/FAIL] (X/Y passed, Z% coverage)Security:  [PASS/FAIL] (X issues)Diff:      [X files changed]
Overall:   [READY/NOT READY] for PR
Issues to Fix:1. ...2. ...

VERIFICATION REPORT==================
Build:     [PASS/FAIL]Types:     [PASS/FAIL] (X errors)Lint:      [PASS/FAIL] (X warnings)Tests:     [PASS/FAIL] (X/Y passed, Z% coverage)Security:  [PASS/FAIL] (X issues)Diff:      [X files changed]
Overall:   [READY/NOT READY] for PR
Issues to Fix:1. ...2. ...

Continuous Mode

For long sessions, run verification every 15 minutes or after major changes:

markdown

Set a mental checkpoint:- After completing each function- After finishing a component- Before moving to next task
Run: /verify

Set a mental checkpoint:- After completing each function- After finishing a component- Before moving to next task
Run: /verify

Integration with Hooks

This skill complements PostToolUse hooks but provides deeper verification. Hooks catch issues immediately; this skill provides comprehensive review.

Source and attribution

Source:affaan-m/eccin.agents/skills/verification-loopat commitef648e0

License: MIT

Content belongs to its original authors. SourceWeft indexes it from a public repository.

Report or request removal

More from affaan-m/ecc

Vue Patterns

affaan-m

Reference guide for Vue 3 Composition API, component architecture, Pinia state, Vue Router, and Nuxt SSR patterns.

Software Development275Kupdated 3 days ago

Uncloud

affaan-m

Reference guide for managing Uncloud clusters with the uc CLI: deploying services, Caddy ingress, ports, scaling and logs.

DevOps & Cloud275Kupdated 3 days ago

Team Agent Orchestration

affaan-m

Coordinates multiple AI agents as a team using work items, Kanban states, branch isolation, and merge gates.

AI & Agents275Kupdated 3 days ago

Tasteforge Video

affaan-m

Use for file-driven multimodal image, video, and 3D-asset discovery; taste interviews; distill or apply workflows; style-pack validation; editable EDL/FCPXML export; provenance audits; and offline planning that must fail closed before provider generation.

Awaiting classification275Kupdated 3 days ago

Taste

affaan-m

Defines an angelcore / cloud-trance / hyperpop visual direction for music videos and short-form edits, with mood, editing grammar and a beat-mapped shot plan.

Design & Creative275Kupdated 3 days ago

Social Publisher

affaan-m

Schedules and publishes social media posts across 13 platforms through the SocialClaw workspace API.

Marketing & Sales275Kupdated 3 days ago

Verification Loop

Verification Loop Skill

When to Use

Verification Phases

Phase 1: Build Verification

Phase 2: Type Check

Phase 3: Lint Check

Phase 4: Test Suite

Phase 5: Security Scan

Phase 6: Diff Review

Output Format

Continuous Mode

Integration with Hooks

Source and attribution

More from affaan-m/ecc

Vue Patterns

Uncloud

Team Agent Orchestration

Tasteforge Video

Taste

Social Publisher

More in Software Development

Playground

M5 Onboard

Cardputer Buddy

Testing Strategy

Tech Debt

System Design