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 skills/corallips/thinking-tree/prefnpx skills add CoralLips/thinking-tree --skill prefgit clone --depth 1 https://github.com/CoralLips/thinking-treeWhat 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 | $0.00029 | $0.00882 |
| Opus 5 | $0.00015 | $0.00441 |
| Sonnet 5 | $0.00006 | $0.00176 |
| Haiku 4.5 | $0.00003 | $0.00088 |
Grade A, and why
pref 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 yesterday.
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
调整记录偏好
用户通过自然语言描述偏好,系统更新 ~/.thinking-tree/.preferences.md。
用法
/pref 不要记录 debug 过程
/pref 碎片标题用问句形式
/pref 更关注产品认知,技术细节不用记
/pref 显示当前偏好
$ARGUMENTS 是自然语言描述的偏好调整。
工具准备
本 skill 依赖 AskUserQuestion 提供选项式确认。进入交互前:
- 若工具列表已含
AskUserQuestion→ 直接使用 - 未加载 → 先执行
ToolSearch("select:AskUserQuestion")加载 schema - 加载失败(session 不支持该工具)→ 降级为纯文本确认:
- 清晰列出编号选项(例如
1) 确认 2) 不改 3) 调整) - 明确告知回复格式(例如「回复编号」)
- 不要跳过确认步骤
- 清晰列出编号选项(例如
降级只影响呈现方式,不影响功能。
执行步骤
1. 读取当前偏好
读取 ~/.thinking-tree/.preferences.md(如果存在)。
2. 理解意图
判断用户想要:
- 新增偏好 — 之前没有类似规则
- 修改偏好 — 调整已有规则的方向或程度
- 删除偏好 — 用户说"取消"、"恢复默认"等
- 查看偏好 — 用户说"显示"、"当前"、"有哪些"
3. 展示方案并确认
不要直接修改文件,先展示你打算怎么改,让用户确认:
我理解你想:不记录纯 debug 讨论
打算这样调整 .preferences.md:
+ 新增「记录范围」:不记录纯 debug 过程中的排查细节
确认?(y/n)
如果涉及修改或删除已有偏好,要明确展示前后对比:
打算这样调整:
~ 修改「记录范围」:
原:只关注产品认知
改:只关注产品认知和架构决策
确认?(y/n)
用 AskUserQuestion 工具获取确认,提供选项按钮(用户点击即可,不用打字):
- 选项 1:「确认,就这样改」
- 选项 2:「不改了」
- 选项 3:「调整一下」(用户补充说明后重新展示方案)
4. 用户确认后写入
确认后修改 ~/.thinking-tree/.preferences.md,保持格式:
# 记录偏好
> 通过 /pref 命令管理。clarifier 每轮读取此文件作为额外判断依据。
## 记录范围
- {什么要记、什么不记}
## 记录风格
- {标题风格、内容详略、结构偏好}
## 整理偏好
- {/reduce 时的分组偏好、保留倾向}
只写用户明确表达的偏好,不要自作主张填充默认值。空分区不写。
5. 反馈
偏好已更新:
+ 新增:不记录纯 debug 讨论
当前偏好共 N 条。
注意事项
- .preferences.md 是纯人类可读的 markdown,不是 JSON
- 每条偏好一行,用
-开头 - 偏好之间不能矛盾——如果新偏好和旧偏好冲突,替换旧的
- 用户说"重置"或"清空"时,删除所有条目但保留文件框架
- 这个文件只影响 clarifier 的判断,不改变 clarifier 的核心规则
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.
- yesterday First seen · 114 lines · 29 tokens per session scan A 983ec33c25a5
pref is a skill published in the GitHub repository CoralLips/thinking-tree (1 stars, last pushed 4mo ago), licensed MIT. It adds 29 tokens to every session and 882 once invoked, about $0.0001 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-memory
../../../engineering/agent-memory/skills/agent-memory/SKILL.md.
amazon-reviews-api-skill
This skill helps users automatically extract Amazon product reviews via the Amazon Reviews API. Agent should proactively apply this skill when users express needs like getting reviews for Amazon product with ASIN B07TS6R1SF, analyzing customer feedback for a specific Amazon item, getting ratings and comments for a…
ai-security
../../../engineering-team/skills/ai-security/SKILL.md.
amazon-competitor-analyzer
Scrapes Amazon product data from ASINs using browseract.com automation API and performs surgical competitive analysis. Compares specifications, pricing, review quality, and visual strategies to identify competitor moats and vulnerabilities.
ctf-malware
Provides malware analysis and network traffic techniques for CTF challenges. Use when analyzing obfuscated scripts, malicious packages, custom crypto protocols, C2 traffic, PE/.NET binaries, RC4/AES encrypted communications, YARA rules, shellcode analysis, memory forensics for malware (Volatility malfind, process…
research
Conduct preliminary research on a topic and generate research outline. For academic research, benchmark research, technology selection, etc.