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.
git clone --depth 1 https://github.com/CloudAI-X/opencode-workflowWrote 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.
[](https://agentmods.dev/commands/cloudai-x/opencode-workflow/verify-changes)<a href="https://agentmods.dev/commands/cloudai-x/opencode-workflow/verify-changes"><img src="https://agentmods.dev/badge/commands/cloudai-x/opencode-workflow/verify-changes/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/cloudai-x/opencode-workflow/verify-changes"><img src="https://agentmods.dev/badge/commands/cloudai-x/opencode-workflow/verify-changes.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00009 | $0.00707 |
| Opus 5.5 | $0.00004 | $0.00283 |
| Sonnet 5.5 | $0.00002 | $0.00141 |
| Haiku 4.5 | $0.00001 | $0.00071 |
Grade A, and why
verify-changes 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verify Changes Command
Comprehensive verification of recent changes using the adversarial verification approach from claude-workflow-v2.
Philosophy
Use progressive quality gates - run cheap checks first, expensive checks later. If early checks fail, stop immediately to save time.
Phase 1: Gather Context
Run in parallel:
git diff HEAD~1orgit diff- Understand what changedgit status- See current state- Identify affected files and their types (source, test, config)
Phase 2: Fast Checks (Fail-Fast Gate)
Run these quick checks first (~5-30 seconds each). Stop on first failure:
Lint Check
- Detect project linter (eslint, prettier, ruff, golint, etc.)
- Run:
npm run lintor equivalent - Exit immediately if lint fails
Type Check
- Detect type system (TypeScript, mypy, etc.)
- Run:
npx tsc --noEmitor equivalent - Exit immediately if type errors exist
Build Check
- Run:
npm run buildor equivalent - Verify compilation succeeds
Phase 3: Deep Checks (Quality Gate)
Only proceed if Phase 2 passes:
Test Execution
- Run:
npm testor equivalent - Capture test results and coverage if available
- Report any failing tests with details
Security Scan (if security-auditor agent available)
- Invoke @security-auditor for OWASP top 10 review
- Check for obvious vulnerabilities in changed code
Phase 4: Adversarial Review
Spawn parallel verification subagents (if Task tool available):
- Logic Reviewer: "Review the changed code for logical errors, edge cases, and potential bugs"
- Consistency Checker: "Verify the changes are consistent with existing codebase patterns"
- Test Coverage Analyzer: "Check if new code has adequate test coverage"
Phase 5: Synthesize Results
Compile findings from all phases:
Verification Report
===================
Fast Checks (Phase 2):
[ ] Lint Check: [PASS/FAIL]
[ ] Type Check: [PASS/FAIL]
[ ] Build Check: [PASS/FAIL]
Deep Checks (Phase 3):
[ ] Tests: [X passed, Y failed]
[ ] Security: [issues found / clean]
Adversarial Review (Phase 4):
- Logic Issues: [list]
- Consistency Issues: [list]
- Coverage Gaps: [list]
Overall Status: [READY TO MERGE / NEEDS WORK]
Recommended Actions:
1. [action item]
2. [action item]
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.
- 1mo ago First seen · 108 lines · 9 tokens per session scan A f01278d6cd06
verify-changes is a command published in the GitHub repository CloudAI-X/opencode-workflow (276 stars, last pushed 9mo ago), licensed MIT. It adds 9 tokens to every session and 707 once invoked, about $0.0000 per session on Opus 5.5. 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 2026-08-30.
Other commands, from other repositories
playwright-test-heal
Run all my tests and fix the failing ones.
verify-bug
Post-merge UAT verification workflow. Walks JIRA reproduce steps, performs comparative audits (Before/After), attaches evidence to JIRA, and transitions status on PASS.
bugfix
Bug fix workflow: root cause analysis → user review → regression test + fix via TDD.
api-aqa-flow-execution-and-report-analysis
Phase 6 Execution & Report Analysis of api-aqa-flow (USER INTERACTION REQUIRED).
timeout-fix
A procedure for diagnosing and fixing tests that exceed their time limit by finding causes such as slow processing, hanging network calls, deadlocks, heavy setup, or leaked resources.
AGENTS
Run the current binary in a temporary test repository with a real PTY. Use tmux-cli when available, capture terminal output, and inspect -vv logs when behavior depends on timing or shell state. Avoid treating a piped command as proof of interactive behavior.