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/extract-qagit 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/extract-qa)<a href="https://agentmods.dev/commands/trafficguard/typedai/extract-qa"><img src="https://agentmods.dev/badge/commands/trafficguard/typedai/extract-qa.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 | $0.00000 | $0.00135 |
| Opus 5 | $0.00000 | $0.00068 |
| Sonnet 5 | $0.00000 | $0.00027 |
| Haiku 4.5 | $0.00000 | $0.00014 |
Grade A, and why
extract-qa scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Extract all Q&A pairs (AskUserQuestion interactions) from the current session.
Find the current session file in ~/.claude/projects/ and extract all clarifying questions Claude asked along with the user's answers. Save the results as markdown to .claude/qa-extractions/.
Run the extraction script:
python3 .claude/hooks/extract-qa.py ~/.claude/projects/-Users-$USER-repo/*.jsonl --output-dir .claude/qa-extractions --format md
Then report:
- How many Q&A pairs were found
- A summary of the questions and answers
- The path to the saved file
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 · 14 lines · 0 tokens per session scan A 33995b38cff2
extract-qa is a command published in the GitHub repository TrafficGuard/typedai (1,192 stars, last pushed 8mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 135 tokens. 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
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.
pr
Handle the full workflow from current branch state to an open, CI-monitored pull request.
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.