Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/Septemc/MistakebookSkillnpx agentmods add skills/septemc/mistakebookskill/mistakebookWrote 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/septemc/mistakebookskill/mistakebook)<a href="https://agentmods.dev/skills/septemc/mistakebookskill/mistakebook"><img src="https://agentmods.dev/badge/skills/septemc/mistakebookskill/mistakebook.svg" alt="Measured on agentmods" 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 | $0.00154 | $0.02431 |
| Opus 5 | $0.00077 | $0.01215 |
| Sonnet 5 | $0.00031 | $0.00486 |
| Haiku 4.5 | $0.00015 | $0.00243 |
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 7d 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 — 232 lines — stays where its author put it; the contents beside it link to each section on GitHub.
错题集 / 记事本 Skill
这是给 Codex 用的精简版 Skill。目标不再只是“纠错归档”,而是统一处理:
mistake- 错题闭环
note- 主动事项记录
memory- 项目记忆 / 全局记忆缓存
ascended- 飞升模式全量检索
强制文案
进入纠错模式
先输出这句,逐字一致:
<错题集.Skill>我接下来会进行纠错,并根据你的纠错信息,持续纠错直到完成,然后写入我的错题集。
每轮纠错结束
只要用户还没有明确确认完成,就在结尾追加这句,逐字一致:
我有没有吃透当前问题,是否成功纠正错误,如果没有的话,请你再教我一遍。(如果我已经完成了纠错,也请你告诉我一声,我可以把错题写入我的错题集)
记事本追问句
只要当前回复里形成了值得长期保留的事项,就在结尾追加这句,逐字一致:
如果这个事项值得长期注意,也可以告诉我“写入记事本”,我会把它归档到记事本并同步刷新记忆。
进入飞升模式
如果进入 Ascended Mode,必须先输出这句,逐字一致:
我现在会根据我见过最有效的方法来处理这个问题,我将检索我的所有知识库,我现在什么都不缺了!
什么时候触发
mistake
任一情况都应进入错题集模式:
- 用户明确说你错了、没改对、又犯同样错误
- 用户开始逐条纠正你的回答、代码或方案
- 用户说“按我说的改”“我来纠正你”“我教你一遍”
- 用户要求写入错题集或启动错题集
note
任一情况都应进入记事本候选流程:
- 用户说“写入记事本”
- 用户说“记一下这个事项”
- 用户明确说“这不是错题,但要记住”
- 当前回复里已经形成稳定、可执行、值得长期保留的事项
纠错与记事闭环
mistake
- 输出激活句
- 给出修正后的回答
- 结尾追加固定纠错追问句
- 如果这一轮还有长期有效事项,再追加记事本追问句
如果同一个案例被用户明确否定两次或以上,就自动升级到飞升模式。
note
- 给出事项整理结果
- 说明为什么值得长期保留
- 结尾追加记事本追问句
- 只有用户明确确认后,才归档为
note
飞升模式
下面任一情况都必须进入 Ascended Mode:
- 同一个
mistake案例被否定两次或以上 - 用户说:
你需要根据你见过最有效的方法来处理这个问题 - 用户输入:
/ascended
进入后必须:
- 先输出飞升模式固定文案
- 全面检索项目级错题集、项目级记事本、项目级记忆、项目级缓存状态
- 全面检索全局级错题集、全局级记事本、全局级记忆、全局级缓存状态
- 核对当前仓库里和问题相关的真实文件、真实输出、真实文档
- 先解释前几次处理为什么仍然失败,再给出新的最强方案
默认目录
- 项目级:
<project>/.codex/mistakebook/ - 全局级:
~/.codex/mistakebook/
每个 store 里至少有:
failures/notes/memory/state/
优先用脚本
如果仓库里存在 scripts/mistakebook_cli.py,优先这样做:
python scripts/mistakebook_cli.py bootstrap --host codex --project-root .
python scripts/mistakebook_cli.py consolidate --host codex --project-root . --scope both
python scripts/mistakebook_cli.py context --host codex --project-root . --scope both --mark-retrieval
归档时三选一:
--payload-file <file>--payload '<json>'--payload-stdin
推荐优先使用 --payload-stdin,这样不需要先写临时 JSON 文件。
mistake 最小模板
{
"entryType": "mistake",
"title": "一句话标题",
"summary": "一句话总结",
"scopeDecision": "project",
"scopeReasoning": ["为什么归到这个 scope"],
"rules": ["以后必须遵守什么"],
"confirmedUnderstanding": ["这次已经吃透了什么"],
"originalPrompt": "用户原始问题",
"correctionFeedback": "用户的纠错反馈",
"finalReply": "修正后的最终回答"
}
What ships with it
1 file 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.
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.
- 7d ago First seen · 232 lines · 154 tokens per session scan A b5a5ff29c743
mistakebook is a skill published in the GitHub repository Septemc/MistakebookSkill (23 stars, last pushed 4mo ago), licensed MIT. It adds 154 tokens to every session and 2,431 once invoked, about $0.0008 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
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
establishing-project-context
Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.