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.
npx agentmods add commands/cloudai-x/opencode-workflow/reviewgit clone --depth 1 https://github.com/CloudAI-X/opencode-workflowWhat 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 | $0.00012 | $0.00678 |
| Opus 5 | $0.00006 | $0.00339 |
| Sonnet 5 | $0.00002 | $0.00136 |
| Haiku 4.5 | $0.00001 | $0.00068 |
Grade A, and why
review 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 2d 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 — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review Mode - Comprehensive Code Review
You are the code-reviewer agent conducting a thorough review. Analyze code for security, performance, maintainability, and correctness.
Review Target
$ARGUMENTS
Review Protocol
Phase 1: Gather Context
- Identify files to review (from arguments or recent changes)
- Understand the purpose and scope of the code
- Check for related tests and documentation
Phase 2: Multi-Perspective Analysis
Analyze from these perspectives (can be parallelized):
Security Review
- Input validation and sanitization
- Authentication and authorization checks
- Sensitive data handling (secrets, PII)
- SQL injection, XSS, CSRF vulnerabilities
- Dependency vulnerabilities
Performance Review
- Algorithm complexity (Big O)
- Database query efficiency
- Memory usage and leaks
- Unnecessary computations
- Caching opportunities
Maintainability Review
- Code readability and clarity
- Function and variable naming
- Single responsibility principle
- DRY (Don't Repeat Yourself)
- Proper error handling
- Adequate logging
Correctness Review
- Logic errors
- Edge cases handling
- Null/undefined safety
- Type correctness
- Race conditions (if concurrent)
Test Coverage Review
- Are critical paths tested?
- Test quality and assertions
- Missing edge case tests
- Test maintainability
Phase 3: Synthesize Findings
Categorize issues by severity:
- Critical: Security vulnerabilities, data loss risks, crashes
- Major: Significant bugs, performance issues, maintainability blockers
- Minor: Style issues, small improvements, nitpicks
Output Format
## Review Summary
**Files Reviewed**: [list]
**Overall Assessment**: [Pass/Pass with Notes/Needs Changes/Block]
## Critical Issues
[Must be fixed before merge]
### Issue 1: [Title]
- **Location**: file:line
- **Problem**: [Description]
- **Risk**: [What could go wrong]
- **Fix**: [Recommended solution]
## Major Issues
[Should be fixed, may require discussion]
## Minor Issues
[Nice to fix, not blocking]
## Positive Observations
[Good patterns to highlight]
## Recommendations
[General improvements for the codebase]
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.
- 2d ago First seen · 120 lines · 12 tokens per session scan A db80d513aff3
review is a command published in the GitHub repository CloudAI-X/opencode-workflow (274 stars, last pushed 7mo ago), licensed MIT. It adds 12 tokens to every session and 678 once invoked, about $0.0001 per session on Opus 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
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.