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/flashus/detrix/review-plangit clone --depth 1 https://github.com/flashus/detrixWhat 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 | $0.00010 | $0.00302 |
| Opus 5 | $0.00005 | $0.00151 |
| Sonnet 5 | $0.00002 | $0.00060 |
| Haiku 4.5 | $0.00001 | $0.00030 |
Grade A, and why
review-plan scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Input
The argument provided is: "$ARGUMENTS"
If the argument is empty or blank, you MUST use AskUserQuestion to ask the user BEFORE doing anything else:
Question: "What would you like me to review?"
Options:
- "Paste text" — "I'll paste the plan text directly in the chat"
- "Read a file" — "I'll provide a file path to read"
- "Read from clipboard" — "Use the most recent clipboard content"
If the user picks "Paste text", say: "Please paste your plan text and I'll review it." If the user picks "Read a file", say: "Please provide the file path." Then wait for their response before proceeding.
If the argument IS provided, proceed directly with the review below.
Review Instructions
Please review the following plan as a project architect and as a staff developer.
I need you to find any possible architectural flaws, inconsistencies, poor design decisions, missing considerations, and potential risks.
Specifically evaluate:
- Architectural soundness and alignment with existing patterns
- Separation of concerns and dependency direction
- Error handling strategy
- Edge cases and failure modes
- Performance implications
- Security considerations
- Testability of the proposed design
- Whether the plan follows SOLID principles
- Any missing steps or overlooked dependencies
Plan to review:
$ARGUMENTS
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 · 47 lines · 10 tokens per session scan A 786bcc0b265f
review-plan is a command published in the GitHub repository flashus/detrix (23 stars, last pushed 9d ago), licensed MIT. It adds 10 tokens to every session and 302 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
freview
Prepare PR with CI checks and Devin AI review loop.
debug-task
Debug Frontman task interactions from the database.
work
Set up a containerized worktree for a GitHub issue or PR.
auto-work
给一个需求，AI自动完成调研→方案→方案Review→开发→开发Review全流程.
develop-review
Review feature-developing 生成的代码，检查遗漏和宪法违规.
developing
Command "developing" from chaohong-ai/ai-auto-work, covering 参数解析, 你的角色, 工作流程, 第一步：建立完整上下文 and 第二步：确认实现范围.