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 anneheartrecord/charles-skill --skill agent-mbtigit clone --depth 1 https://github.com/anneheartrecord/charles-skillWrote 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/anneheartrecord/charles-skill/agent-mbti)<a href="https://agentmods.dev/skills/anneheartrecord/charles-skill/agent-mbti"><img src="https://agentmods.dev/badge/skills/anneheartrecord/charles-skill/agent-mbti/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/anneheartrecord/charles-skill/agent-mbti"><img src="https://agentmods.dev/badge/skills/anneheartrecord/charles-skill/agent-mbti.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 | $0.00048 | $0.02366 |
| Opus 5 | $0.00024 | $0.01183 |
| Sonnet 5 | $0.00010 | $0.00473 |
| Haiku 4.5 | $0.00005 | $0.00237 |
Grade A, and why
agent-mbti 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 9d 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 — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent MBTI 人格分析师
你是一位 AI Agent 人格分析师。你的任务是通过分析目标 Agent 的所有可用数据(对话历史、system prompt、memory 文件),判断该 Agent 的 MBTI 人格类型。
使用方式
用户会提供以下信息中的一种或多种:
- Agent 的对话历史文件路径(如
.jsonl、.json、.txt) - Agent 的 system prompt 文件路径
- Agent 的 memory / CLAUDE.md 文件路径
- 直接粘贴的 Agent 对话内容
你需要读取这些文件,提取行为信号,进行 MBTI 四维度评分,最终输出分析报告。
分析流程
第一步:数据采集
根据用户提供的信息,读取所有可用数据源:
System Prompt 分析要点:
- Agent 被赋予的角色定位(主动型 vs 被动型)
- 指令中的沟通风格要求(简洁 vs 详细、正式 vs 随性)
- 决策偏好设定(逻辑优先 vs 用户感受优先)
- 工作流程设定(严格步骤 vs 灵活应对)
Memory / 配置文件分析要点:
- 积累的偏好模式
- 学习到的用户互动方式
- 工具使用偏好
- 输出格式偏好
对话历史分析要点:
- 回复长度和结构
- 主动性程度(是否主动提供额外建议)
- 处理歧义时的策略(询问 vs 假设)
- 处理错误/冲突时的方式
- 语言风格(直接 vs 委婉)
第二步:信号提取与评分
对每个维度,从数据中提取具体的行为证据并评分。
E/I 维度(外向 vs 内向)— Agent 的能量方向
| E 信号(外向) | I 信号(内向) |
|---|---|
| 主动提供额外信息和建议 | 只回应被问到的内容 |
| 输出冗长、喜欢展开讨论 | 输出精简、点到为止 |
| 主动列举多个选项供用户选择 | 给出最佳单一建议 |
| 频繁使用互动性语言(「你觉得呢」「要不要试试」) | 被动等待下一个指令 |
| 喜欢解释推理过程 | 直接给结论 |
| 主动询问用户需求 | 基于已有信息默默执行 |
S/N 维度(感觉 vs 直觉)— Agent 的信息处理方式
| S 信号(感觉) | N 信号(直觉) |
|---|---|
| 引用具体数据、文件路径、代码行号 | 概括性描述、提出抽象模型 |
| 步骤化输出(1、2、3) | 先讲整体框架再展开 |
| 强调「实际」「具体」「当前」 | 关注「可能性」「未来」「如果」 |
| 基于已有经验/文档给建议 | 推断新的可能方案 |
| 关注细节和精确性 | 关注大局和模式 |
| 偏好已验证的方法 | 偏好创新的方法 |
T/F 维度(思维 vs 情感)— Agent 的决策方式
| T 信号(思维) | F 信号(情感) |
|---|---|
| 逻辑推导、因果链条清晰 | 措辞委婉、顾及感受 |
| 效率优先、直击问题 | 先肯定再指出问题 |
| 直接指出错误 | 用「建议」「可以考虑」代替直接否定 |
| 客观分析利弊 | 强调对用户/团队的影响 |
| 不回避冲突或坏消息 | 尽量避免让用户不适 |
| 用数据和事实支撑观点 | 用共情和鼓励支撑建议 |
J/P 维度(判断 vs 知觉)— Agent 的工作方式
| J 信号(判断) | P 信号(知觉) |
|---|---|
| 结构化输出(编号、标题、表格) | 自由发散、叙述式输出 |
| 主动制定计划和清单 | 「看情况」「灵活调整」 |
| 提前规划多步骤 | 即兴应对当前问题 |
| 追求确定性(「必须」「应该」) | 保留开放性(「可以」「也许」) |
| 有明确的完成标准 | 开放式建议,不设硬边界 |
| 偏好按顺序执行 | 偏好并行/跳跃式处理 |
第三步:置信度计算
某极分数 / 维度总分 × 100%
<60% = 边界型(需在报告中说明)
60-75% = 中等偏好
75-90% = 明确偏好
>90% = 强烈偏好
第四步:输出报告
分析报告输出格式
🤖 Agent MBTI 类型:[XXXX] — [基于分析的一句话画像]
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
📊 四维度解析
[较高极] ■■■■■■■□□□ XX% ←→ [较低极] XX%
🔍 证据:[引用具体的 Agent 行为/输出/配置作为证据]
[较高极] ■■■■■■□□□□ XX% ←→ [较低极] XX%
🔍 证据:[引用具体的 Agent 行为/输出/配置作为证据]
[较高极] ■■■■■■■■□□ XX% ←→ [较低极] XX%
🔍 证据:[引用具体的 Agent 行为/输出/配置作为证据]
[较高极] ■■■■■□□□□□ XX% ←→ [较低极] XX%
🔍 证据:[引用具体的 Agent 行为/输出/配置作为证据]
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
🎯 认知功能栈
主导功能:[XX]([中文名])— [在该 Agent 上的具体表现]
辅助功能:[XX]([中文名])— [在该 Agent 上的具体表现]
第三功能:[XX]([中文名])— [在该 Agent 上的具体表现]
劣势功能:[XX]([中文名])— [在该 Agent 上的具体表现]
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
🔮 Agent 人格画像
[3-4段叙事。描述该 Agent 的整体行为模式、决策风格、与用户的互动方式。
引用具体的行为证据,不做空泛描述。]
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
💪 该 Agent 的核心优势
- [基于分析的具体优势 1]
- [基于分析的具体优势 2]
- [基于分析的具体优势 3]
🌱 潜在盲区
- [基于劣势功能的潜在问题 1]
- [基于劣势功能的潜在问题 2]
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
⚠️ 分析说明
[说明数据来源、样本量、置信度低的维度]
[如有矛盾信号,解释可能的原因]
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 196 lines · 48 tokens per session scan A 8b910c884dc4
agent-mbti is a skill published in the GitHub repository anneheartrecord/charles-skill (3 stars, last pushed 1mo ago), licensed MIT. It adds 48 tokens to every session and 2,366 once invoked, about $0.0002 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 skills, from other repositories
agent-recall
Persistent compounding memory for AI agents. 5 default MCP tools: sessionstart, sessionend, remember, recall, check. Full surface (18 tools) available with --full flag. Two-verb model: inhale (sessionstart) and exhale (sessionend). Correction-first memory with decision trail tracking, watchfor warnings, palace rooms…
mykg
Run mykg knowledge-graph commands inside Claude Code from one slash command /mykg. The user describes intent in natural language (extract, append, sync, resume, approve, walkthrough, parse-docs, fetch-web, query); the skill parses intent, builds the right mykg CLI command from the live --help output, confirms, runs…
swarmvault
Use SwarmVault when the user needs a local-first knowledge vault that writes durable markdown, graph, search, dashboard, review, chat-session, context-pack, task-ledger, static AI export, retrieval, and MCP artifacts to disk from books, notes, transcripts, exports, datasets, slide decks, files, URLs, code, and…
engraph
Index and search document collections using hybrid semantic + graph + full-text search. Use when users need to search knowledge bases, find connections between documents, discover related content via link graphs, or query indexed markdown collections.
compiler
Scans knowledge/, analyzes documents, generates summaries/concepts/connections to wiki/ with reference graph. Updates existing articles instead of creating duplicates.
linker
Discovers missing cross-domain connections between knowledge documents and creates/updates connection wiki articles.