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 konglong87/methodology-skills --skill experience-managergit clone --depth 1 https://github.com/konglong87/methodology-skillsWrote 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/konglong87/methodology-skills/experience-manager)<a href="https://agentmods.dev/skills/konglong87/methodology-skills/experience-manager"><img src="https://agentmods.dev/badge/skills/konglong87/methodology-skills/experience-manager/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/konglong87/methodology-skills/experience-manager"><img src="https://agentmods.dev/badge/skills/konglong87/methodology-skills/experience-manager.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 | $0.00017 | $0.02863 |
| Opus 5 | $0.00009 | $0.01432 |
| Sonnet 5 | $0.00003 | $0.00573 |
| Haiku 4.5 | $0.00002 | $0.00286 |
Grade A, and why
experience-manager scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 389 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Experience Manager - 经验管理技能
前置协议
环境检测
PROJECT_ROOT=$(git rev-parse --show-toplevel 2>/dev/null || echo "unknown")
mkdir -p memory/artifacts/experience-manager memory/retrospectives
调用方式
方式1：工件传递（推荐）
- 检测工件：
memory/artifacts/*/experience-*.json
方式2：用户直接调用
- 使用
/experience-manager命令
详细说明：参考 detailed-guide.md
Overview
experience-manager 是独立的知识管理技能，负责项目经验知识的沉淀、读取、复盘、反思，实现知识闭环，帮助AI避免重复错误，持续改进。
核心能力：
- 经验沉淀：任务完成后，四层级同步沉淀
- 经验读取：任务开始前，智能检索历史经验
- 经验复盘：里程碑完成时，保留好的，改掉坏的
- 经验反思：验证有效性，提炼智慧
- 错误预防：检测风险，提供预防建议
- 效果追踪：记录应用效果，持续优化
关键价值：
- 避免重复错误，快速复用成功模式
- 持续积累知识资产，形成自我进化闭环
核心原则
四层级沉淀机制
| 层级 | 文件 | 维度 | 优先级 | 用途 |
|---|---|---|---|---|
| 规则层 | CLAUDE.md | 做什么 | 最高 | 项目约定，强约束 |
| 策略层 | AGENT.md | 怎么做 | 高 | AI执行策略，决策规则 |
| 知识层 | MEMORY.md | 学到了什么 | 中 | 技术知识，经验总结 |
| 历史层 | MCP Memory | 过去发生了什么 | 低 | 完整历史，智能检索 |
读取优先级：规则层 > 策略层 > 知识层 > 历史层
冲突处理：以高优先级为准。
持续改进原则
- 好则加冕：成功经验升级为规则/策略
- 错则改之：失败教训更新知识库
- 动态更新：过时经验及时标记和更新
核心能力
能力1：经验沉淀（Save）
触发时机：任务完成后，由 goal-oriented 调用
执行步骤：
- 接收请求工件（
experience-save-request.json） - 生成回顾报告（
memory/retrospectives/{task-id}.md） - 四层级同步沉淀（CLAUDE.md、AGENT.md、MEMORY.md、MCP Memory）
- 创建结果工件（
save-result-{timestamp}.json）
示例：
// 输入
{
"action": "save",
"task_id": "2026-03-24_task-keywords",
"lessons_learned": ["经验1", "经验2"],
"errors_fixed": [{"error": "...", "fix": "..."}]
}
// 输出：四层级同步更新 + 结果工件
能力2：经验读取（Retrieve）
触发时机：任务开始前，由 goal-oriented、pilot 调用
执行步骤：
- 接收请求工件（
experience-request.json） - 四层级并行检索（关键词匹配 + 语义检索）
- 按优先级排序和去重
- 生成预防清单和推荐模式
- 创建结果工件（
experience-result-{timestamp}.json）
示例：
## 📚 历史经验参考
### ⚠️ 错误预防（来自 CLAUDE.md）
- 预防措施1
- 预防措施2
### 🎯 可复用模式（来自 AGENT.md）
- 代码模式/流程模式
### 📖 技术知识（来自 MEMORY.md）
- 知识点1、知识点2
能力3：经验复盘（Review）
触发时机：里程碑完成时，由 goal-oriented 调用
目的：保留好的，改掉坏的，持续优化
What ships with it
6 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.
- 9d ago First seen · 389 lines · 17 tokens per session scan A 111ce7f7652b
experience-manager is a skill published in the GitHub repository konglong87/methodology-skills (5 stars, last pushed 1mo ago), licensed MIT. It adds 17 tokens to every session and 2,863 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 2026-08-31.
Other skills, from other repositories
omh-memory-sync
This is a Hermes-native memory-sync workflow skill.
omh-memory-new
This is a Hermes-native memory-new workflow skill.
omh-context-budget-review
This is a Hermes-native context-budget-review workflow skill.
omh-instinct-ledger
This is a Hermes-native instinct-ledger workflow skill.
omh-decision-recall
This is a Hermes-native decision-recall workflow skill.
importing-a-codebase
Use when the repo holds real source code but no specs: the existing-codebase branch of setting-up-a-project, normally reached via that dispatcher, directly only when the situation is unmistakable. Not for empty workspaces (starting-a-new-project) or feature work in a specced project (brainstorming).