agentsclimarketplace

Verification gates

Skill josix/agent-flow/skills/verification-gates

This skill should be used when handling verification steps, quality gates, pre-commit checks, test failures, lint errors, build verification, or mandatory validation before task completion.From its SKILL.md

Install
npx -y skills add josix/agent-flow --skill verification-gates

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 7 stars7 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

6.6 KB, as published. Nobody here has run it

Verification Gates

Overview

Verification gates are mandatory quality checkpoints that must pass before any implementation work is considered complete. These gates prevent broken code from being committed, ensure type safety, maintain code style consistency, and validate that all tests pass.

Owner Agent: Alphonse (Verifier Agent)

Key Principles

  1. Non-Negotiable Quality: Every code change must pass all applicable gates
  2. Automated Enforcement: Gates are triggered automatically via hooks
  3. Clear Feedback: Failures provide actionable error messages
  4. Project-Aware: Commands adapt to detected project type and tooling
  5. Fail-Fast, Fix-First: When any gate fails, work stops until resolved

Verification Hierarchy

Loid (Executor)          Alphonse (Verifier)
     |                         |
Quick sanity tests       Full verification gate
during implementation    before completion
     |                         |
     +----------> Handoff >----+

Gate Types

Pre-Commit Gates

CheckExample CommandTimeout
Lintnpm run lint / ruff check30s
Formatnpm run format:check / black --check15s
Quick TestsChanged file tests only60s

Pre-Complete Gates

CheckExample CommandTimeout
Full Test Suitenpm test / pytest300s
Type Checkingnpx tsc --noEmit / mypy .120s
LintingFull codebase lint60s
Buildnpm run build / python -m build180s

Security Gates

Triggered by changes to sensitive files or security-critical code:

CheckTriggerAction
Credential Scan*.env, *secret*, *.keyBlock + Alert
Permission CheckAuth/ACL codeRequire review
Dependency AuditPackage filesnpm audit / pip-audit

Verification Commands

Quick Reference by Language

ActionNode.jsPythonGoRust
Testnpm testpytestgo test ./...cargo test
Typesnpx tsc --noEmitmypy .go buildcargo check
Lintnpm run lintruff check .golangci-lint runcargo clippy
Buildnpm run buildpython -m buildgo buildcargo build

For complete command reference, see references/verification-commands.md.


Verification Process

Alphonse Verification Steps

  1. Identify project type (Node.js, Python, Go, Rust, Java)
  2. Run test suite with appropriate framework
  3. Execute type checking if configured
  4. Run linters if present
  5. Attempt production build
  6. Report structured results

Standard Output Format

## Verification Results

### Tests
- Status: [PASS | FAIL]
- Output: [Summary of test execution]

### Type Check
- Status: [PASS | FAIL | SKIPPED]
- Errors: [List of type errors if any]

### Lint
- Status: [PASS | FAIL | SKIPPED]
- Warnings: [Count and summary]

### Build
- Status: [PASS | FAIL | SKIPPED]
- Issues: [Build errors if any]

### Overall: [VERIFIED | FAILED | ENVIRONMENT_BLOCKED]

Failure Handling

Failure Severity

TypeSeverityAction
Test FailureBLOCKINGFix and re-run
Type ErrorBLOCKINGResolve types
Lint ErrorBLOCKINGAuto-fix or manual
Build FailureBLOCKINGFix compilation
Security AlertCRITICALImmediate remediation
TimeoutWARNINGRetry once
Flaky TestWARNINGRetry 3x, then fix

Escalation Path

Alphonse Reports -> Loid Reviews
     |                   |
Simple Fix?         Complex Issue?
     |                   |
    YES                  NO
     |                   |
Loid Fixes      Escalate to Lawliet
     |                   |
Re-verify       Architecture Review

For detailed failure protocols, see references/failure-handling.md.


Best Practices

DO

  • Run verification after every significant change
  • Fix failures immediately
  • Trust Alphonse's verdict
  • Add tests for new features
  • Run full suite before PR

DON'T

  • Skip verification to save time
  • Suppress type errors with any
  • Disable lint rules without justification
  • Commit with failing tests
  • Use --no-verify flag
  • Mark tasks complete without verification

Gate Selection Guide

ScenarioGate TypeChecks Run
Small code fixPre-CommitLint, format, affected tests
New feature completePre-CompleteFull suite, types, lint, build
Security-related changeSecurityCredential scan, audit, permissions
Cross-service changeIntegrationE2E, contracts, compatibility

Override Rules

Verification gates can ONLY be skipped when:

  1. User explicitly requests skip - Must be documented
  2. No code changes were made - Documentation-only tasks
  3. Task is purely exploratory - No production impact

Override Documentation Required:

## Verification Override

Reason: [Explicit reason for skipping]
Requested by: [User or escalation source]
Risk Assessment: [Low/Medium/High]
Compensating Controls: [What will catch issues later]

Multi-reviewer disagreement (Codex co-review)

Disagreement rule: See the canonical truth table in commands/orchestrate.md Phase 4 (Codex co-review). The summary: Lawliet's NEEDS_CHANGES always wins; Codex's NEEDS_CHANGES/BLOCKED requires a file:line citation to flip the verdict.


Additional Resources

Reference Files

Examples

Related Files

FilePurpose
scripts/load-project-context.shProject type detection
hooks/scripts/verify-completion.shPre-complete gate implementation
hooks/scripts/validate-changes.shSecurity validation
agents/Alphonse.mdVerifier agent definition

Related Skills

  • task-classification: Determines when verification is required
  • agent-behavior-constraints: Model routing and tool access

Keep looking

Skills are one crate of 628,853. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.