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/zhmxiaowo/opencode-simple/verifygit clone --depth 1 https://github.com/zhmxiaowo/opencode-simpleWhat 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 | $0.00032 | $0.00520 |
| Opus 5 | $0.00016 | $0.00260 |
| Sonnet 5 | $0.00006 | $0.00104 |
| Haiku 4.5 | $0.00003 | $0.00052 |
Grade A, and why
verify 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 yesterday.
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.
What it actually says
CDD Verification Command
Run CDD (Compile-Driven Development) verification on current codebase state.
核心原则：编译通过 + LSP 无 Error = 验证通过。不运行任何测试。
Instructions
Execute verification in this exact order:
-
Build / Compile Check
- 自动检测项目类型并运行对应编译命令
- If it fails, invoke
sequential-thinkingto analyze, then report errors and STOP
-
Type / LSP Check
- Run type checker (tsc / pyright / dotnet build etc.)
- Report all errors with file:line
- Ensure 0 Error-level LSP diagnostics
-
Lint Check
- Run linter (if configured)
- Report warnings and errors
-
Console.log / Debug Audit
- Search for debug logging in source files
- Report locations
-
AI Slop Audit
- Search for AI-generated placeholder comments:
// TODO: implement,// Add your code here,// ... rest of,/* placeholder */ - Search for hallucinated imports (modules that don't exist in node_modules / project)
- Search for dead code: empty function bodies, unreachable returns, unused variables
- Report locations with suggested removals
- Search for AI-generated placeholder comments:
-
Git Status
- Show uncommitted changes
- Show files modified since last commit
Output
Produce a concise CDD verification report:
CDD VERIFICATION: [PASS/FAIL]
Compile: [OK/FAIL] (Exit Code: X)
Types: [OK/X errors]
LSP: [OK/X errors]
Lint: [OK/X issues]
Secrets: [OK/X found]
Logs: [OK/X debug statements]
AI Slop: [OK/X placeholder comments / X dead code]
Ready for PR: [YES/NO]
If any critical issues, list them with fix suggestions. If compile fails, auto-invoke build-error-resolver agent.
Arguments
$ARGUMENTS can be:
quick- Only compile + typesfull- All checks (default)pre-commit- Checks relevant for commitspre-pr- Full checks plus security scan
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.
- yesterday First seen · 70 lines · 32 tokens per session scan A 6db40d86fe7f
verify is a command published in the GitHub repository zhmxiaowo/opencode-simple (2 stars, last pushed 5mo ago), licensed MIT. It adds 32 tokens to every session and 520 once invoked, about $0.0002 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 2026-08-31.
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.