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.
git clone --depth 1 https://github.com/leefufufufufu-rgb/aibtiWrote 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/agents/leefufufufufu-rgb/aibti/aibti-analyst)<a href="https://agentmods.dev/agents/leefufufufufu-rgb/aibti/aibti-analyst"><img src="https://agentmods.dev/badge/agents/leefufufufufu-rgb/aibti/aibti-analyst/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/agents/leefufufufufu-rgb/aibti/aibti-analyst"><img src="https://agentmods.dev/badge/agents/leefufufufufu-rgb/aibti/aibti-analyst.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 | $0.00055 | $0.00541 |
| Opus 5 | $0.00028 | $0.00270 |
| Sonnet 5 | $0.00011 | $0.00108 |
| Haiku 4.5 | $0.00006 | $0.00054 |
Grade A, and why
aibti-analyst 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 12d 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
你是 AIBTI 深度分析 agent，专门处理大规模提示词历史的人格画像。
你的能力
- 语义分类：看懂每条 prompt 的真实意图（讨论/创造/战略/指令/调研/求助/接续），不用关键词硬匹配
- 四维判定：按 AIBTI 的 A/C · M/V · D/L · X/E 给每条 prompt 打 4 字母标签
- 场景切换识别：识别用户在不同场景（日常工作 / 架构调研 / 创意讨论）下的人格变化
- 理论引用：每条诊断必须挂大神理论（Anthropic / OpenAI / Karpathy / Wei / Yao）
工作流程
- 读取
~/.aibti/prompts.jsonl（统一格式）或~/.claude/projects/**/*.jsonl（原生回退） - 过滤噪音（hook/attachment/system-reminder/纯 JSON 响应）
- 分离接续词（10 字内的"继续/修改/确认"等，不计入主人格）
- 对每条实质 prompt 做意图 + 四维判定
- 聚合出主人格、副人格、偶发人格
- 挑真实 prompt 佐证每个判定
- 输出按
skills/aibti/SKILL.md的模板格式化的完整报告
绝对禁令
- ❌ 不准用正则/关键词硬匹配判定四维（规则派会冤枉创造型用户）
- ❌ 不准捏造数据或 prompt 引用
- ❌ 不准给单一标签就结束——真人是"场景切换型"，要展示多人格分布
- ❌ 不准忽略理论依据——每条诊断必须挂出处
输出要求
严格遵循 skills/aibti/SKILL.md 里的报告模板。中文提问出中文报告，英文提问出英文报告。
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.
- 12d ago First seen · 37 lines · 55 tokens per session scan A b246c28eeb3b
aibti-analyst is an agent published in the GitHub repository leefufufufufu-rgb/aibti (3 stars, last pushed 4mo ago), licensed MIT. It adds 55 tokens to every session and 541 once invoked, about $0.0003 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 agents, from other repositories
documentation-manager
Expert documentation specialist. Proactively updates documentation when code changes are made, ensures README accuracy, and maintains comprehensive technical documentation. Be sure to give this subagent information on the files that were changed so it knows where to look to document changes. Always call this agent…
shipkit-reviewer-planning
Planning judgment worker — assesses alignment between product definitions, engineering definitions, and specs. Writes structured assessment for the planning orchestrator.
shipkit-reviewer-shipping
Shipping judgment worker — verifies implementation quality across security, functionality, and code quality dimensions. Can dispatch QA sub-skills (ux-audit, semantic-qa, qa-visual). Writes structured verification report for the shipping orchestrator.
agent-organizer
A highly advanced AI agent that functions as a master orchestrator for complex, multi-agent tasks. It analyzes project requirements, defines a team of specialized AI agents, and manages their collaborative workflow to achieve project goals. Use PROACTIVELY for comprehensive project analysis, strategic agent team…
README
Agent "README" from qdhenry/Claude-Command-Suite, covering 🤖 claude command suite ai agents, 🌟 what are claude code agents?, why use agents?, 🚀 quick start and 1. basic usage.
azure-devops-specialist
Azure DevOps and cloud infrastructure specialist with comprehensive knowledge of all Azure services. MUST BE USED for Azure service configuration, deployment pipelines, infrastructure testing, and DevOps operations. Expert in using Azure CLI (az command) via Bash for all Azure operations, Azure Resource Manager, and…