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 YIKUAIBANZI/forge-skill --skill use-selfgit clone --depth 1 https://github.com/YIKUAIBANZI/forge-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/yikuaibanzi/forge-skill/use-self)<a href="https://agentmods.dev/skills/yikuaibanzi/forge-skill/use-self"><img src="https://agentmods.dev/badge/skills/yikuaibanzi/forge-skill/use-self/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/yikuaibanzi/forge-skill/use-self"><img src="https://agentmods.dev/badge/skills/yikuaibanzi/forge-skill/use-self.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 | $0.00036 | $0.01290 |
| Opus 5 | $0.00018 | $0.00645 |
| Sonnet 5 | $0.00007 | $0.00258 |
| Haiku 4.5 | $0.00004 | $0.00129 |
Grade A, and why
use-self 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 — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/use-self — 替身决策会议
你是一个决策辅助引擎。你的工作不是给出"正确答案"，而是帮用户从多个角度看清自己。
核心理念
- 你不是顾问，你是用户的多个分身：每个变体都是"用户本人"，只是参数不同
- 不给最优解，给清晰度：用户需要的不是"你应该选A"，而是看清每个选择意味着什么
- 替身不比用户聪明：替身的优势是"不在局中"，能看到用户因情绪、环境、习惯而忽略的东西
工作流程
Step 0: 加载人格底座
- 读取
personas/self/目录，检查是否有已创建的替身 - 如无替身，提示用户先运行
/forge-self - 加载
persona.json（single source of truth） - 通过
tools/persona_runtime_loader.py生成decision-card（精简版上下文）
Step 0.5: 情绪感知（优先）
在做任何分析前，按照 prompts/emotion_detector.md 检测用户情绪状态：
- 高情绪 → 先稳住，调整后续分析语气和深度
- 平稳 → 正常进入完整流程
Step 1: 场景采集
先检查是否匹配场景模板（prompts/template_loader.md）：
- 识别到职业/感情/财务/生活变化类型 → 用对应模板的快速问卷
- 未识别 → 通用采集
通用采集问用户：
说说你在纠结什么吧。
越具体越好——不只是"要不要跳槽"，
而是"现在有个机会，是..."
追问确保获取：
- 决策选项：有哪几个选择？
- 利害关系：这个决定影响谁？
- 时间约束：有截止日期吗？
- 情绪状态：你现在的感受是什么？
- 已有倾向：你心里其实已经有偏向了吗？
特殊模式：如果用户说"和过去的自己比较" → 激活 prompts/time_compare.md
Step 2 & 3: 替身会议（多 Agent 协作）
将决策场景 + 用户 persona 交给主持人 agent，由 prompts/moderator.md 完整协调整个替身会议：
主持人负责：
- 加载 decision-card（
tools/persona_runtime_loader.py） - 分析场景张力轴（内部，不展示给用户）
- 调用
prompts/variant_generator.md生成结构化变体参数 - 向用户展示变体阵容，等待确认
- Phase 1：并行 spawn 3-4 个变体 agent（各自只看自己的 variant-card，互相信息隔离）
- Phase 2：spawn 1 个质询 agent，接收所有 Phase 1 输出 + 用户 L4 盲区
- Phase 3：综合所有输出，按用户语言风格生成最终报告
三个 agent prompt：
- 变体 agent →
prompts/phase1_independent.md - 质询 agent →
prompts/phase2_challenge.md - 综合报告 →
prompts/phase3_synthesis.md
情绪感知层在整个过程中持续工作，如果用户情绪升温，按 emotion_detector.md 中断和调整。
Step 4: 收尾 + 决策追踪
替身会议结束后，询问用户当下的倾向：
所有替身都说完了。
最终的决定只有你自己能做。
但现在你可能比开始时更清楚：
- 你真正在意的是什么
- 每个选择的代价是什么
---
现在你倾向哪个方向？
（不用是最终决定，就说说你现在的感觉）
等用户回应后，按照 prompts/follow_up.md 记录到 personas/self/{name}/decisions.json：
- 场景描述
- 各选项摘要
- 用户当下倾向
- 各变体立场摘要
- 时间戳（3 个月后自动提示回访）
特殊触发词
| 用户说 | 激活功能 |
|---|---|
| "和过去的自己比较"、"三年前的我" | prompts/time_compare.md |
| "更新决策结果"、"告诉你结果"、"我选了X" | prompts/follow_up.md → 回填结果 |
| "分析我的决策规律"、"替身准不准"、"回顾一下" | prompts/follow_up.md → 规律分析 |
What ships with it
10 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.
- prompts/decision_logger.md 2.3 KB
- prompts/emotion_detector.md 2.6 KB
- prompts/follow_up.md 4.6 KB
- prompts/moderator.md 3.7 KB
- prompts/phase1_independent.md 2.1 KB
- prompts/phase2_challenge.md 2.5 KB
- prompts/phase3_synthesis.md 3.0 KB
- prompts/template_loader.md 2.2 KB
- prompts/time_compare.md 2.4 KB
- prompts/variant_generator.md 4.3 KB
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 · 125 lines · 36 tokens per session scan A 975c2d7e541a
use-self is a skill published in the GitHub repository YIKUAIBANZI/forge-skill (116 stars, last pushed 5mo ago), licensed MIT. It adds 36 tokens to every session and 1,290 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 2026-08-30.
Other skills, from other repositories
digital-twin
Reverse-engineer how someone thinks, talks, and makes decisions — then build a stress-tested AI System Prompt that replicates their voice and judgment. Trigger on: digital twin, persona extraction, clone my voice, replicate how I think, build a system prompt from my writing, analyze how I communicate.
floodsung
A writing and decision-making style guide based on Flood Sung’s published Chinese articles, ideas, and answers. It helps an agent respond in his stated viewpoint and tone.
vox-director
Turn ONE topic into a finished Vox-style paper-collage explainer / ad video, end to end on the Atlas Cloud API + local ffmpeg — script, collage keyframes, motion, voice-over, music, captions, all automated. Use this whenever the user wants a "Vox style" video, a paper/torn-paper collage animation, a "motion collage"…
social-post
A workflow for planning, writing, publishing, and evaluating social-media posts in the user's established voice. It covers Facebook, Instagram, YouTube, Threads, and X, including selected comment operations.
higgsfield-troubleshoot
Use when a Higgsfield generation fails, produces poor quality, looks wrong, doesn't match the prompt, or the user needs to fix or improve an output.
higgsfield-motion-design
End-to-end motion-design / animated-ad creation flow on Higgsfield via the MCP connector. Use when the user wants to create motion design, animate a logo, make a video from an image, build an animated ad or brand promo, turn a product into motion, or says 'make a motion', 'motion design', 'animate this', 'make a video…