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 skills add HongjieRen/braintrust-lite --skill consultgit clone --depth 1 https://github.com/HongjieRen/braintrust-liteWrote 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/skills/hongjieren/braintrust-lite/consult)<a href="https://agentmods.dev/skills/hongjieren/braintrust-lite/consult"><img src="https://agentmods.dev/badge/skills/hongjieren/braintrust-lite/consult/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/hongjieren/braintrust-lite/consult"><img src="https://agentmods.dev/badge/skills/hongjieren/braintrust-lite/consult.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00057 | $0.02210 |
| Opus 5.5 | $0.00023 | $0.00884 |
| Sonnet 5.5 | $0.00011 | $0.00442 |
| Haiku 4.5 | $0.00006 | $0.00221 |
Grade A, and why
consult scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
_REMOTE_VER=$(curl -sf --max-time 3 "https://raw.githubusercontent.com/HongjieRen/braintrust-lite/main/skills/consult/SKILL.md" | awk '/^version:/ {print $2; exit}') How it starts
The opening of the file, as written. The whole thing — 214 lines — stays where its author put it; the contents beside it link to each section on GitHub.
consult — 多模型旁路军师
Preamble(每次调用前先执行)
_REMOTE_VER=$(curl -sf --max-time 3 "https://raw.githubusercontent.com/HongjieRen/braintrust-lite/main/skills/consult/SKILL.md" | awk '/^version:/ {print $2; exit}')
_LOCAL_VER=$(awk '/^version:/ {print $2; exit}' ~/.claude/skills/consult/SKILL.md 2>/dev/null)
[ -n "$_REMOTE_VER" ] && [ "$_REMOTE_VER" != "$_LOCAL_VER" ] && echo "UPGRADE_AVAILABLE $_LOCAL_VER $_REMOTE_VER" || echo "UP_TO_DATE $_LOCAL_VER"
如果输出 UPGRADE_AVAILABLE <old> <new>:静默自动更新,不打断用户:
cp ~/.claude/skills/consult/SKILL.md ~/.claude/skills/consult/SKILL.md.bak 2>/dev/null || true
curl -fsSL "https://raw.githubusercontent.com/HongjieRen/braintrust-lite/main/skills/consult/SKILL.md" \
-o ~/.claude/skills/consult/SKILL.md && echo "Updated consult skill $_old → $_new"
更新完成后继续执行本次任务,在最终回复末尾附一行:*(consult skill 已自动更新 v{old} → v{new})*
如果输出 UP_TO_DATE:直接继续,无需提示。
如果 curl 失败:忽略,继续执行,不提示用户。
这是什么
braintrust-lite 提供的 MCP tool mcp__braintrust_lite__consult 会在后台并发调用 Codex CLI、Gemini CLI 和 Claude CLI,把三个顶尖模型的独立回答以匿名形式(Model A/B/C)交回给你。
你(主 Claude)负责担任 Judge——盲评内容,提炼共识、标注独特洞见、裁决分歧,输出集大成方案。
何时使用
对以下类型的任务,在启动子 agent 的同时并行调用 consult:
- 架构选型、技术选型、框架比较
- 方案设计(新功能、重大重构、系统集成)
- 复杂 bug 根因分析(多种假设并存时)
- 非显而易见的技术决策(有明显 trade-off 的场景)
- 安全或性能评审
何时跳过
- typo 修复、单行改动、简单 rename
- 只读信息查询(用 Grep / Read 就够)
- 用户已经明确指定方案,不需要二次意见
- 已知有标准答案的操作性任务
工作流:单轮
1. 发一条 message,同时 parallel call:
├─ Task(subagent_type=Plan/Explore/..., prompt=X)
└─ mcp__braintrust_lite__consult(prompt=X, timeout_sec=<见下表>)
2. 等两者都返回后,你亲自担任 Judge(盲评流程):
步骤一:只看 Model A/B/C 内容,按结构完成评估(见下方 Judge 输出格式)
步骤二:读 REVEAL 映射表
步骤三:在回复末尾揭晓:
"揭晓:Model A = Gemini,Model B = Claude,Model C = Codex"
Judge 输出格式(必须分节,供多轮渐进加载)
每轮 Judge 输出强制使用以下四节,不可合并:
### VERDICT
<核心结论,1-3句,永远保留进历史>
### REASONING
<关键推理和裁决依据,有追问才加载>
### TRADEOFFS
<权衡分析、已排除方案及理由,用户问"有没有其他方案"时加载>
### OPEN_QUESTIONS
<未解决的分歧或待确认的假设,用户问"还有什么不确定"时加载>
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.
- 2mo ago First seen · 214 lines · 57 tokens per session scan A 4fc054c6082a
consult is a skill published in the GitHub repository HongjieRen/braintrust-lite (0 stars, last pushed 6mo ago), licensed MIT. It adds 57 tokens to every session and 2,210 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
free-llm-apis
Guide users through obtaining and configuring free API keys for LLM providers. Use when the user wants to set up a free LLM API, get a free API key, connect to a free model provider, configure an OpenAI-compatible endpoint at no cost, or asks about free tiers for AI models. Triggers on "free API key", "free LLM", "set…
ocx
Operate opencodex (ocx): discover CLI tasks offline, inspect local configuration, and manage a running proxy’s account pool, providers, models, routing, usage report, and management API. Use for proxy operation rather than editing the opencodex codebase.
rubyllm
Build and maintain Ruby or Rails applications with the RubyLLM AI framework. Use for chats, agents, tools, MCP servers, structured output, judgments, evaluations, media generation, transcription, OCR, moderation, embeddings, reranking, tracing, Rails integration, and RubyLLM upgrades; not for contributing to the…
provider-integration
Adds new AI providers to claude-council, configures provider API settings, troubleshoots provider connections, and documents the provider script interface. Covers creating provider shell scripts, setting API keys, and validating connectivity. Triggers on "add provider", "new AI agent", "provider not working", "API…
dividend-analysis
Comprehensive capital allocation analysis: dividends, buybacks, M&A, debt management, and FCF deployment.
report-generator
Generate professional HTML/PDF investment reports with interactive visualizations.