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/trafficguard/typedai/select-filesgit clone --depth 1 https://github.com/TrafficGuard/typedaiWrote 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/trafficguard/typedai/select-files)<a href="https://agentmods.dev/commands/trafficguard/typedai/select-files"><img src="https://agentmods.dev/badge/commands/trafficguard/typedai/select-files.svg" alt="Measured on agentmods" 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 | $0.00013 | $0.00755 |
| Opus 5 | $0.00006 | $0.00378 |
| Sonnet 5 | $0.00003 | $0.00151 |
| Haiku 4.5 | $0.00001 | $0.00076 |
Grade A, and why
select-files 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 4d 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Select Files
Select the minimal set of files from a codebase that are essential for completing a given task. Uses an iterative LLM-driven search with both regex and semantic vector search capabilities.
How It Works
The select-files agent:
- Analyzes the repository structure and file summaries
- Iteratively searches and inspects files using regex and/or vector search
- Decides which files to keep or ignore based on relevance
- Returns the minimal set of files needed for the task
Usage
Via MCP Tool
If you have the TypedAI MCP server configured, use the selectFiles tool:
{
"workingDirectory": "/path/to/your/project",
"requirements": "Find all files related to user authentication",
"initialFilePaths": ["src/auth/index.ts"] // optional
}
Parameters:
workingDirectory(required): Absolute path to the project directoryrequirements(required): Description of what files are needed and whyinitialFilePaths(optional): Array of file paths to include in initial context
Via CLI
# Standalone command (recommended)
select-files "Find all files related to user authentication"
# With initial files to include
select-files --initial-files=src/auth/index.ts,src/config.ts "Find related configuration"
# From any directory (uses --fs flag automatically)
cd /path/to/your/project
select-files "Find database models"
# Alternative: via ai wrapper
ai select-files "Find database models"
Flags:
--initial-files=file1,file2: Comma-separated list of initial files to include-r: Resume from previous agent run
Output Format
Returns a JSON array of selected files:
[
{
"filePath": "src/auth/authenticate.ts",
"reason": "Contains the main authentication logic and session management"
},
{
"filePath": "src/config/auth.config.ts",
"reason": "Authentication configuration including JWT settings"
}
]
Fields:
filePath: Relative path to the file from the project rootreason: Explanation of why this file was selectedreadOnly(optional): Whether the file should only be read, not modifiedcategory(optional): One ofedit,reference,style_example,unknown
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.
- 4d ago First seen · 103 lines · 13 tokens per session scan A 49c9e5538f61
select-files is a command published in the GitHub repository TrafficGuard/typedai (1,192 stars, last pushed 8mo ago), licensed MIT. It adds 13 tokens to every session and 755 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
awesome-chatgpt
Search awesome-ChatGPT-repositories for open-source GitHub repositories related to ChatGPT and LLMs.
init
Scaffold a new MindBase project (v2 layout). Usage: /mb:init [template] [-- mission ...].
commit
智能生成 Git 提交信息并提交.
doctor.es
Diagnostica problemas de inferencia LLM en Mac: asiai doctor verifica el estado de los motores, conflictos de puertos, carga de modelos y estado de la GPU.
requirement-review
需求文档多角色评审(requirement-review):需求文档 → 7-Agent 并行评审 → 重构高质量需求文档(Runtime 受控流程,0-7 阶段状态机).
claude-request
Send a prompt to Claude Code via the LLM gateway with session tracking.