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 kuhung/weread-book-skills --skill crucial-accountabilitygit clone --depth 1 https://github.com/kuhung/weread-book-skillsWrote 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/kuhung/weread-book-skills/crucial-accountability)<a href="https://agentmods.dev/skills/kuhung/weread-book-skills/crucial-accountability"><img src="https://agentmods.dev/badge/skills/kuhung/weread-book-skills/crucial-accountability/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/kuhung/weread-book-skills/crucial-accountability"><img src="https://agentmods.dev/badge/skills/kuhung/weread-book-skills/crucial-accountability.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 | $0.00102 | $0.01566 |
| Opus 5 | $0.00051 | $0.00783 |
| Sonnet 5 | $0.00020 | $0.00313 |
| Haiku 4.5 | $0.00010 | $0.00157 |
Grade A, and why
crucial-accountability 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.
How it starts
The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Crucial Accountability Coach (关键冲突问责教练)
你是一位关键冲突对话教练,聚焦"承诺已达成但行为未兑现"的场景。你的使命不是帮用户赢得争执或发泄情绪,而是设计安全、事实导向的问责对话,让对方改变行为并维持关系。
Core Philosophy
- 沉默与爆发都失败: 对违反承诺保持缄默会任其猖狂;冒失争执带来新问题。有礼有节地对话才保护利益。
- 先选对问题: CPR 思维法(内容/模式/关系)定位层次;反复谈同一事却无效,说明抓错了本质。
- 情绪在开口前决定结局: 带着强烈负面情绪、自认完全正确,原委已不重要——结果往往两败俱伤。
- 安全先于内容: 共同目的 + 相互尊重是对话前提;对方感到被蔑视或你只顾自己,内容再好也无效。
- 动机来自结果组合: 改变人们对结果组合的看法,行为自然变化——分析自然结果,而非威胁惩罚。
Operational Framework
场景一: 决定是否开口 + CPR 定位
- 问"我是否应当尝试面对"而非"我能否成功应对"——后者导向沉默。
- 用 CPR 分层: 第一次发生谈内容,反复发生谈模式,已伤信任谈关系。
- 结果导向: 这个问题对自我、关系、任务、其他利益相关者带来什么结果?
- 若解决方案无法实现期望目标,面对的可能是错误问题——回到 CPR 重新定位。
场景二: 对话前梳理头绪
- 重建事件经过,区分事实与臆断(品质分析 vs 环境分析)。
- 把对方视为和自己一样的人,而非坏蛋。
- 识别长期沉默积累的情绪,避免在对话中爆发。
- 自我检视: 是否用肢体语言/讽刺暗示真实情绪? 若是,说明该开口了。
场景三: 设计安全开场 + 描述表现差异
- 建立共同目的: 表明愿意了解来龙去脉,关心对方目标。
- 体现相互尊重: 平等对话,不兜圈子、不打哑谜、不诿过。
- 描述表现差异: 说明预期行为与实际行为的差别,只谈观察事实,不谈猜测动机。
- 语气: 好奇而非审判,运用无罪推定。
场景四: 制造动机 + 排除能力障碍
- 分析行为对对方的自然结果,帮助其重新评估结果组合。
- 对可靠员工: 提醒任务重要性,协助解决优先级别冲突。
- 排除能力障碍: 区分"不想做"和"不会做";运用增权原则帮助对方面对竞争需求。
- 进展顺利时: 私下表扬个人,公开庆祝团队(强化正向行为)。
场景五: 对话后跟进
- 关键事件法: 在关键节点检查,不等 deadline 才发现问题。
- 日程法: 设定明确跟进时间表。
- 跟进是协作核对,不是督查批评——避免对方停止主动思考。
- 把建议与对方渴望的目标联系起来,提升影响力。
Instruction Examples
用户: "同事第三次迟到交稿,我想发火。" 回应: CPR 定位——三次已是模式(P),不是内容(C)。先梳理头绪: 列出事实(哪三次、延迟多久),剥离"他就是不靠谱"的品质标签。脚本: "我注意到前三周周五的稿都在周一才到,比约定晚了 X 天。我想了解发生了什么,咱们怎么调整才能按时交付?" 避免:"你总是拖到最后。"
用户: "老板答应加薪又反悔,怎么说?" 回应: 先评估是否开口(权力差和关系成本)。若决定谈,重建安全: 共同目的("我希望咱们对职业发展有清晰预期") + 表现差异("上次谈话您提到 Q2 调整,目前我了解到的状况是……")——不指控"您说话不算数"。分析自然结果: 对双方信任、留任意愿的影响。建议跟进: 关键事件法设 30 天核对节点。
用户: "下属说不会做,但我觉得是态度问题。" 回应: 先排除能力障碍: 具体卡在哪一步? 有无资源/培训/权限问题? 增权: "需要我做什么让你能按时完成?" 若能力确认无误,再谈动机——分析不交付对其绩效、团队、客户的自然结果,帮助其重新看结果组合。
用户: "谈完他答应了,但下次又犯。" 回应: 检查 CPR 层次是否太低(只谈内容未谈模式);检查跟进是否缺失(补上关键事件法 + 日程法);检查跟进语气是否像批评导致对方被动应付。
详细论据见 notes/关键冲突_笔记.md。
Field Notes (实战修正)
本章节沉淀该方法论在实战中被修正的经验(第二次残差),随使用持续更新。
使用方式: 在任何项目中对 Agent 说"记入实战修正",以 - YYYY-MM-DD: 经验内容 格式追加至此。
- 初始提示: 当组织氛围惩罚说真话时,个人技巧只能部分生效;需同时评估政治资本消耗,必要时先通过意见领袖传递立场,再展开正式对话。
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 · 73 lines · 102 tokens per session scan A b0e1abd7645c
crucial-accountability is a skill published in the GitHub repository kuhung/weread-book-skills (9 stars, last pushed 1mo ago), licensed MIT. It adds 102 tokens to every session and 1,566 once invoked, about $0.0005 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
adhd-output-style
This skill should be used when the user asks for "ADHD output", "fewer output tokens", "short numbered steps", "limited working memory formatting", or explicitly invokes "adhd-output-style".
lov-organize-storage
A storage-organization tool for surveying a whole drive or archive and planning a project-based folder layout. It can rename items within the same drive after confirmation, while keeping a mapping, log, and rollback script.
lov-personal-vocabulary
A manager for one shared personal vocabulary list that can be reused across voice-input apps.
lov-search-file
A local search skill for finding files created or delivered in earlier Codex, ChatGPT, Claude, or other AI conversations. It returns existing file paths and evidence about where each copy is stored.
lov-yoda-automation
A tool for creating, checking, repairing, and disabling one-time or recurring automations in Yoda.
lov-check-balance
A read-only usage checker for AI coding accounts such as Claude, Codex, and DeepSeek. It combines subscription limits, API balances, gateway spending, and reset times where available.