From agent-flow
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.
npx claudepluginhub josix/agent-flow --plugin agent-flowThis skill uses the workspace's default tool permissions.
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.
Enforces five-step verification (identify/run/read/verify/claim) of commands like npm test/build/lint before claiming code complete, fixed, or passing. Builds trust via evidence.
Runs lint, type-check, tests, and build for Node.js, Python, Rust, Go, Java projects after code changes to verify nothing is broken.
Runs code verification phases including build, type check, lint, tests, security scans, and diff review for Python and Node.js projects before PRs.
Share bugs, ideas, or general feedback.
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)
Loid (Executor) Alphonse (Verifier)
| |
Quick sanity tests Full verification gate
during implementation before completion
| |
+----------> Handoff >----+
| Check | Example Command | Timeout |
|---|---|---|
| Lint | npm run lint / ruff check | 30s |
| Format | npm run format:check / black --check | 15s |
| Quick Tests | Changed file tests only | 60s |
| Check | Example Command | Timeout |
|---|---|---|
| Full Test Suite | npm test / pytest | 300s |
| Type Checking | npx tsc --noEmit / mypy . | 120s |
| Linting | Full codebase lint | 60s |
| Build | npm run build / python -m build | 180s |
Triggered by changes to sensitive files or security-critical code:
| Check | Trigger | Action |
|---|---|---|
| Credential Scan | *.env, *secret*, *.key | Block + Alert |
| Permission Check | Auth/ACL code | Require review |
| Dependency Audit | Package files | npm audit / pip-audit |
| Action | Node.js | Python | Go | Rust |
|---|---|---|---|---|
| Test | npm test | pytest | go test ./... | cargo test |
| Types | npx tsc --noEmit | mypy . | go build | cargo check |
| Lint | npm run lint | ruff check . | golangci-lint run | cargo clippy |
| Build | npm run build | python -m build | go build | cargo build |
For complete command reference, see references/verification-commands.md.
## 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]
| Type | Severity | Action |
|---|---|---|
| Test Failure | BLOCKING | Fix and re-run |
| Type Error | BLOCKING | Resolve types |
| Lint Error | BLOCKING | Auto-fix or manual |
| Build Failure | BLOCKING | Fix compilation |
| Security Alert | CRITICAL | Immediate remediation |
| Timeout | WARNING | Retry once |
| Flaky Test | WARNING | Retry 3x, then fix |
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.
any--no-verify flag| Scenario | Gate Type | Checks Run |
|---|---|---|
| Small code fix | Pre-Commit | Lint, format, affected tests |
| New feature complete | Pre-Complete | Full suite, types, lint, build |
| Security-related change | Security | Credential scan, audit, permissions |
| Cross-service change | Integration | E2E, contracts, compatibility |
Verification gates can ONLY be skipped when:
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]
| File | Purpose |
|---|---|
scripts/load-project-context.sh | Project type detection |
hooks/scripts/verify-completion.sh | Pre-complete gate implementation |
hooks/scripts/validate-changes.sh | Security validation |
agents/Alphonse.md | Verifier agent definition |