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 MuduiClaw/ClawKing --skill self-improvinggit clone --depth 1 https://github.com/MuduiClaw/ClawKingWrote 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/muduiclaw/clawking/self-improving)<a href="https://agentmods.dev/skills/muduiclaw/clawking/self-improving"><img src="https://agentmods.dev/badge/skills/muduiclaw/clawking/self-improving/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/muduiclaw/clawking/self-improving"><img src="https://agentmods.dev/badge/skills/muduiclaw/clawking/self-improving.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 | $0.00000 | $0.00771 |
| Opus 5.5 | $0.00000 | $0.00308 |
| Sonnet 5.5 | $0.00000 | $0.00154 |
| Haiku 4.5 | $0.00000 | $0.00077 |
Grade A, and why
self-improving 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
Self-Improving — 教训管理体系
基于 ClawHub
self-improving（ivangdavila）+self-improving-agent（pskoett）改写
触发条件
- 被用户纠正
- 操作/工具执行失败
- 完成重要任务后复盘
- 发现更好的做法
- 启动新任务时主动检索相关教训
快速参考
| 场景 | 动作 |
|---|---|
| 被纠正 | 记录到 memory/archive/lessons.md，格式见 references/format.md |
| 操作失败 | 同上。先归因再记录，修根因不打补丁 |
| 新增教训 | 先 grep "pattern_key:.*关键词" memory/archive/lessons.md 去重。命中 → 更新复现计数；未命中 → 新建 |
| 任务启动 | memory_search("lessons + 关键词") 检索相关教训 |
| 发现复现 ≥3 | 检查是否需要晋升（见 references/promotion.md） |
| 完成重要任务 | 主动自评：哪里做得好、哪里可以改进、有无新教训 |
教训格式（速查）
## [LSN-YYYYMMDD-XXX] pattern_key: 关键词
- **优先级**: critical | high | medium | low
- **状态**: pending | resolved | promoted → <目标文件>
- **复现**: N 次（日期列表）
- **领域**: infra | content | product | trading | ops
### 摘要
一句话描述
### 触发场景 + 错误模式
什么情况下犯的、错在哪
### 正确做法
应该怎么做
### if-then
IF <触发条件> THEN <正确行为>
ID 格式：LSN-YYYYMMDD-<3位随机字符>（如 LSN-20260308-A7B），避免序号冲突。
完整格式定义和示例 → references/format.md
晋升规则（速查）
| 优先级 | 晋升条件 | 目标 |
|---|---|---|
| 🔴 Critical | 首次发生即晋升 | AGENTS.md 铁律 / IDENTITY.md 已知缺陷 |
| 🟡 High | 复现 ≥3 次 | AGENTS.md 铁律 / IDENTITY.md 已知缺陷 |
| 🟢 Medium/Low | 不晋升 | 留在 lessons.md 供检索 |
晋升后原条目状态改为 promoted → <目标文件>#<编号>
完整晋升规则 → references/promotion.md
分层存储
| 层级 | 对应文件 | 加载时机 |
|---|---|---|
| HOT | AGENTS.md 铁律 + IDENTITY.md 已知缺陷 | 每个 session 自动注入 |
| WARM | memory/archive/lessons.md |
memory_search 按需检索 |
| COLD | memory/archive/lessons-cold.md |
极少访问，90天+ 未引用的非 critical 条目 |
衰减规则
- 90 天未被引用 + 非 critical → 移入
lessons-cold.md（手动，不自动） - 移入 COLD 前在原位留一行引用：
→ moved to lessons-cold.md [LSN-ID]
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 First seen · 75 lines · 0 tokens per session scan A 476a27b9c599
self-improving is a skill published in the GitHub repository MuduiClaw/ClawKing (11 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 771 tokens. 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
knowledge-ingest
Ingest documents, articles, conversations, or supplied text into Knowledge with retained originals, sourced claims, entity updates, timelines, and cross-links; also learn durable lessons from a set of conversations, transcripts, or past sessions (/learn), including the Learn from conversations and Learn from Memory…
forget
Remove a personal fact, preference, relationship detail, topic, or prior event from Muse's active memory and stop existing copies or automations from bringing it back. Use for explicit requests such as 'forget that', 'don't remember this about me', or 'remove that from your memory'. Do not use when 'forget it' merely…
mem0-oss-to-platform
Plan, then execute, a migration of a project from the mem0 open-source / self-hosted SDK (local Memory class) to the mem0 Platform / hosted SDK (MemoryClient). TRIGGER when: the developer wants to move, switch, or migrate mem0 off OSS/self-hosted to the hosted API, e.g. "migrate my mem0 setup to the platform", "switch…
Cortex
LifeOS memory, prior-session recall, and learning capture. USE WHEN capture this learning, document this learning, what did we learn recently, recent learnings, cortex, knowledge, knowledge base, search knowledge, what do we know about, archive, harvest, knowledge status, develop note, add to knowledge, add a people…
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…