agentmods.dev

mistakebook

mistakebook is a command for coding agents from Septemc/MistakebookSkill. It costs 85 tokens per session (994 once invoked), scanned A, original, MIT.

A command-based notebook and correction tracker for organizing mistakes, lessons, and long-term notes in project or global records.

In plain words
What is it for?
It can enable or disable automatic detection, show status, consolidate records, enter note mode, and switch to a more extensive review mode when ordinary fixes are not enough.
Why use it?
It creates a repeatable way to recognize corrections, decide what is worth retaining, and keep stored guidance up to date.

Command

Part of the mistakebook plugin — 4 skills, 4 commands, 2 hooks shipped together

not rated 23 4mo ago A scan 85 tokens original MIT
View the source file Septemc/MistakebookSkill
Install

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.

agentmods
npx agentmods add commands/septemc/mistakebookskill/mistakebook
Clone the repo
git clone --depth 1 https://github.com/Septemc/MistakebookSkill

Or install mistakebook, the plugin that ships this one along with the rest of its 4 skills, 4 commands, 2 hooks.

Wrote 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.

agentmods badge for mistakebook

README.md
[![agentmods](https://agentmods.dev/badge/commands/septemc/mistakebookskill/mistakebook.svg)](https://agentmods.dev/commands/septemc/mistakebookskill/mistakebook)
Your own site
<a href="https://agentmods.dev/commands/septemc/mistakebookskill/mistakebook"><img src="https://agentmods.dev/badge/commands/septemc/mistakebookskill/mistakebook.svg" alt="Measured on agentmods" height="20"></a>
Per session 85 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 994 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00085 $0.00994
Opus 5 $0.00043 $0.00497
Sonnet 5 $0.00017 $0.00199
Haiku 4.5 $0.00009 $0.00099

Measured 5d ago against content hash 7ce0afa52f00, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mistakebook 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 5d 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.

commands/mistakebook.md · 56 lines

What it actually says

根据参数执行以下路由：

参数路由

  • 无参数 或任意任务描述
    • 加载 mistakebook 核心 skill，进入统一闭环
  • note
    • 加载 mistakebook 核心 skill，按 note 条目模式处理当前事项
    • 先整理当前长期注意事项，再在结尾询问是否写入记事本
  • on
    • 如果存在 scripts/mistakebook_cli.py，执行：
      • python scripts/mistakebook_cli.py config --auto-detect on
    • 输出确认：> [Mistakebook ON] 已开启自动识别纠错 / 记事项景。
  • off
    • 如果存在 scripts/mistakebook_cli.py，执行：
      • python scripts/mistakebook_cli.py config --auto-detect off
    • 输出确认：> [Mistakebook OFF] 已关闭自动识别纠错 / 记事项景。
  • status
    • 如果存在 scripts/mistakebook_cli.py，执行：
      • python scripts/mistakebook_cli.py status --host codex --project-root . --scope both
  • scholar-on
    • 如果存在 scripts/mistakebook_cli.py，执行：
      • python scripts/mistakebook_cli.py config --scholar on
    • 输出确认：> [Scholar ON] 已开启学霸模式预检。
  • scholar-off
    • 如果存在 scripts/mistakebook_cli.py，执行：
      • python scripts/mistakebook_cli.py config --scholar off
    • 输出确认：> [Scholar OFF] 已关闭学霸模式预检。
  • scholar-status
    • 如果存在 scripts/mistakebook_cli.py，执行：
      • python scripts/mistakebook_cli.py status --host codex --project-root . --scope both
  • consolidate
    • 如果存在 scripts/mistakebook_cli.py，执行：
      • python scripts/mistakebook_cli.py consolidate --host codex --project-root . --scope both
    • 重读当前项目和全局的错题、记事本、命中数据，重写项目记忆和全局记忆
  • ascended
    • 立刻进入飞升模式（Ascended Mode）
    • 先输出固定飞升模式回复语
    • 全面检索项目级 / 全局级错题、记事本、记忆缓存和当前知识库后，再处理当前问题

执行规则

  1. 当路由到核心 skill 时，严格遵循 mistakebook 的激活句、固定纠错追问句、记事本追问句、归档流程和记忆刷新规则
  2. 用户没有明确确认前，禁止提前把当前案例归档为 mistake 或 note
  3. consolidate 不是简单追加条目，而是重读相关条目后做去重、合并、压缩和暂时遗忘
  4. ascended 不是普通继续修补，而是显式要求你调用当前已知最有效的方法，全面检索项目级 / 全局级知识来源后再给出方案
  5. 对于新的普通任务，如果当前不在纠错闭环、note 流程或 ascended 流程里，且学霸模式未被关闭，先执行： python scripts/mistakebook_cli.py scholar --host codex --project-root . --scope both --text "<当前任务>"
  6. 只有当 scholar 返回 shouldInject = true 时，才允许在正式回答前输出一行历史提醒；否则保持静默
  7. 一旦进入纠错闭环或 Ascended Mode，就停止运行 scholar，不要让学霸模式和飞升模式争抢同一个时机
Changes

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.

  1. 5d ago First seen · 56 lines · 85 tokens per session scan A 7ce0afa52f00

Subscribe to this mod's changes

mistakebook is a command published in the GitHub repository Septemc/MistakebookSkill (23 stars, last pushed 4mo ago), licensed MIT. It adds 85 tokens to every session and 994 once invoked, about $0.0004 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.

Learning and teachingProductivity
Related

Other commands, from other repositories

lrn

Execute the /vibeguard:learn command. $ARGUMENTS.

majiayu000/vibeguard · 0 tokens

review

Cold re-quiz on code that already shipped — your own session commits, not the change in front of you.

emanzurv/quiz-me-skill · 23 tokens

annex-a-deep-dive

Deep dive analysis of ISO 27001 Annex A control domains with implementation guidance.

GRCEngClub/claude-grc-engineering · 15 tokens

start-10-1

Command "start-10-1" from minicoohei/ai-agent-camp, covering 🎓 lesson 10-1: clasp基本・gasプロジェクト管理, 📍 このセッションでやること, 🎯 準備チェック, 🚀 step 1: claspのインストールと apps script api の確認 and 🚀 step 2: google認証.

minicoohei/ai-agent-camp · 2 tokens

start-13-4.en

Welcome to Lesson 13-4: Landing Page Implementation!

minicoohei/ai-agent-camp · 2 tokens

learn-story-flow

Learn story-flow concepts with interactive guidance for junior developers.

Intai/story-flow · 10 tokens