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 commands/huifer/claude-code-interview/feedbackgit clone --depth 1 https://github.com/huifer/claude-code-interviewWhat 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 | $0.00019 | $0.00549 |
| Opus 5 | $0.00010 | $0.00275 |
| Sonnet 5 | $0.00004 | $0.00110 |
| Haiku 4.5 | $0.00002 | $0.00055 |
Grade A, and why
feedback 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 2d 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
面试不足分析
您正在分析面试记录，系统将：
- 读取面试记录中的详细表现
- 使用 AI 深度分析各类不足
- 识别重复出现的问题
- 生成详细改进报告并保存
正在分析...
请提供面试记录的 ID（格式：YYYYMMDD_company_round，例如：20250109_google_2）
系统将执行以下步骤：
步骤 1: 读取面试记录
从 data/interviews/{{interview_id}}.json 读取面试数据
步骤 2: AI 深度分析
使用 interview-coach Skill 进行不足分析：
- 技术类不足（technical）：算法、数据结构、编码、系统设计、领域知识
- 沟通类不足（communication）：清晰度、结构、术语、简洁性、倾听
- 时间管理（time_management）：分析时间、编码速度、规划、优先级
- 思维模式（thinking_pattern）：分解、抽象、模式识别、优化、权衡
- 其他不足（other）：领域知识、工具、语言、自信、压力管理
步骤 3: 重复不足识别
与全局不足追踪系统对比：
- 计算语义相似度（文本相似度 70% + 关键词重叠 30%）
- 相似度阈值 ≥ 0.75 判定为重复
- 标注重复出现的不足
步骤 4: 更新全局追踪
更新 data/analytics/weaknesses.json：
- 增加出现历史
- 更新统计信息
- 计算优先级分数
- 记录改善状态
步骤 5: 生成详细报告
生成 Markdown 报告并保存到 exports/weakness-reports/{{interview_id}}_weakness_analysis.md，包含：
- 基本信息（面试 ID、公司、类型、日期）
- 总体评估（评分、问题数量、严重问题数、重复问题数）
- 🔴 紧急改进（重复出现的问题）
- 🟡 短期改进（高优先级问题）
- 🟢 长期提升（其他问题）
- 详细改进计划
- 推荐学习资源
请提供面试 ID，开始分析。
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.
- 2d ago First seen · 56 lines · 19 tokens per session scan A c995a6d3efb9
feedback is a command published in the GitHub repository huifer/claude-code-interview (23 stars, last pushed 7mo ago), licensed MIT. It adds 19 tokens to every session and 549 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 2026-08-30.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.