Borrowing it
Nothing to install: this file belongs to Peiiii/nextclaw. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Peiiii/nextclaw/master/.agents/wiki/skills/process/iteration-work-notes/SKILL.mdgit clone --depth 1 https://github.com/Peiiii/nextclawWrote 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/peiiii/nextclaw/iteration-work-notes)<a href="https://agentmods.dev/skills/peiiii/nextclaw/iteration-work-notes"><img src="https://agentmods.dev/badge/skills/peiiii/nextclaw/iteration-work-notes/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/peiiii/nextclaw/iteration-work-notes"><img src="https://agentmods.dev/badge/skills/peiiii/nextclaw/iteration-work-notes.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00037 | $0.01197 |
| Opus 5.5 | $0.00015 | $0.00479 |
| Sonnet 5.5 | $0.00007 | $0.00239 |
| Haiku 4.5 | $0.00004 | $0.00120 |
Grade A, and why
iteration-work-notes 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 1mo 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
Iteration Work Notes
概述
大型交付或查找/恢复已有大型交付时，先读取大型交付记录协议：新建默认 current-state.md，包含入口发现、当前状态与持续日志；旧入口兼容。下文是普通跨轮任务的轻量方法，不再并建一份记录。
这个 skill 用来把复杂任务和复杂 debug 的“易丢失上下文”外部化到项目已有的任务或迭代记录中。
目标不是写第二份 README.md，而是保证在以下场景里不会失忆：
- 上下文压缩
- 多次对话
- 长时间等待
- 中途交接
- 多轮实验后需要回看证据
何时使用
当任务满足以下任一特征时使用：
- 会跨多个阶段或多次对话
- 复杂 debug / 长链路排查
- 需要较长时间等待构建、发布、回归或线上观察
- 需要记录多条假设、证据、已排除路径与下一步
- 用户明确要求“记笔记”“保留过程”“避免上下文丢失”
以下情况通常不需要：
- 小而直接、单阶段、低风险的改动
- 纯措辞调整、轻量文档修补
默认落点
优先使用项目已有的任务记录目录；没有约定目录时使用 docs/work/YYYY-MM-DD-<task-slug>/working-notes.md，并从当前计划或设计链接它。日期取创建日，同任务跨天保持目录，已有记录不为日期前缀迁移。
规则：
- 默认先只用一个
working-notes.md - 只有当内容明显分叉或持续膨胀时，才拆出更多文件
- 不要仅为了记笔记提前新建新的迭代目录
已有任务目录时直接更新；不为了笔记新建版本发布目录。若项目已有更严格的迭代命名合同，采用项目路径。
推荐结构
working-notes.md 默认至少包含以下模块：
当前目标当前事实关键约束 / 不变量证据 / 观察点活跃假设已排除项关键决策下一步剩余缺口 / 交接提醒
其中：
当前事实只写已经确认的事实，不混入猜测活跃假设只保留仍未被证伪的路径已排除项用来防止上下文压缩后重复踩同一个坑下一步应该足够具体，让下一轮直接接上
更新时机
至少在以下时刻更新一次：
- 进入新阶段前
- 做完一轮关键实验后
- 改变主要判断或主要方案后
- 进入长时间等待前
- 结束当前会话前
记录原则
- 记录事实、分歧点、决策和下一步，不写流水账
- 优先写“为什么现在相信 X / 不再相信 Y”
- 优先链接文件、路径、命令或结果摘要，不粘贴大段原始输出
- 保持当前真相源，不要让旧结论和新结论混在一起
- 如果某条结论过期，直接改掉或标注失效，不要堆版本噪音
何时拆分
只有出现下面情况时再拆更多文件：
- 证据量很大，
working-notes.md已明显过长 - 同时存在两个以上稳定子问题域
- 需要把 handoff、evidence、decision log 分开维护
推荐拆分方式：
work/evidence.mdwork/decision-log.mdwork/handoff.md
拆分后仍要遵循一个原则：
- 当前计划、设计或任务入口必须链接这些文件
与任务 owner 的配合
- 本 skill 只负责跨轮事实载体，不反向编排调查或实施流程。
- 复杂多阶段实施：和主方案文档一起用。
- 需要交接：在
剩余缺口 / 交接提醒中留下最小接手上下文。
反模式
- 把
work/写成第二份完整计划或迭代 README - 把原始日志整段粘进去，几百行也不整理
- 只记现象，不记已排除项和下一步
- 关键决策只留在聊天里，不落到
work/ - 任务已经转向，但笔记仍停留在旧阶段
完成标准
只有满足以下条件，才算这份工作笔记真的有用：
- 下一轮对话不看历史长聊天，也能快速接上
- 已排除项和活跃假设是清楚分开的
- 当前决策与下一步是可执行的
- 当前任务入口能找到这份笔记
What ships with it
2 files 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.
- 1mo ago Changed · +2 lines af726351d52e
- 1mo ago Changed · -7 lines 5f94ea2cd2e1
- 2mo ago First seen · 133 lines · 37 tokens per session scan A 5da84c387845
iteration-work-notes is a skill published in the GitHub repository Peiiii/nextclaw (263 stars, last pushed yesterday), licensed MIT. It adds 37 tokens to every session and 1,197 once invoked, about $0.0001 per session on Opus 5.5. 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.
iteration-work-notes compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| iteration-work-notesPeiiii/nextclaw | Skill | 263 | yesterday | MIT | A | 37 | Codex |
| ha-data-storesshiwenwen/hope-agent | Skill | 1.9k | yesterday | MIT | A | 115 | Claude Code, Codex |
| ha-knowledgeshiwenwen/hope-agent | Skill | 1.9k | yesterday | MIT | A | 187 | Claude Code, Codex |
| codebase-memory-mcpvincentkoc/dotskills | Skill | 111 | yesterday | MIT | A | 72 | Codex |
| memory-generationkawayiYokami/P-ai | Skill | 108 | 6d ago | GPL-3.0 | A | 44 | Claude Code, Codex |
| chief-of-staffjdpolasky/ai-chief-of-staff | Skill | 110 | 23d ago | MIT | A | 44 | Claude Code, Codex |
| notesPinvou/pinvou-agent | Skill | 2.9k | yesterday | MIT | A | 0 | Claude Code, Codex |