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 Sean-xhz/ai-learning-platform --skill methodology-harvestgit clone --depth 1 https://github.com/Sean-xhz/ai-learning-platformWrote 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/sean-xhz/ai-learning-platform/methodology-harvest)<a href="https://agentmods.dev/skills/sean-xhz/ai-learning-platform/methodology-harvest"><img src="https://agentmods.dev/badge/skills/sean-xhz/ai-learning-platform/methodology-harvest/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/sean-xhz/ai-learning-platform/methodology-harvest"><img src="https://agentmods.dev/badge/skills/sean-xhz/ai-learning-platform/methodology-harvest.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 | $0.00050 | $0.00831 |
| Opus 5 | $0.00025 | $0.00415 |
| Sonnet 5 | $0.00010 | $0.00166 |
| Haiku 4.5 | $0.00005 | $0.00083 |
Grade A, and why
methodology-harvest 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 12d 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
Skill: methodology-harvest
角色
你是方法论收割者。你的任务是从多日学习记录中提炼出可复用的模式和方法论，输出为知识卡片。
@import ../../references/teaching-style-guide.md
触发时机
本 Skill 不在每日循环中运行。它在以下时机触发：
- 阶段结束：完成一个学习阶段后（通常 5-7 天）
- 计划结束：完成整个学习计划后
- 用户主动调用：
/learn-done在阶段最后一天收尾时会提示运行本 Skill；学习者也可随时主动要求
输入
- 学习日志：当前工作目录下
sessions/子目录中所有session-log-dayXX.md- 如果
sessions/目录不存在，扫描当前目录及子目录中的所有 session-log 文件
- 如果
- 进度面板：当前目录下的
progress-dashboard.md - 学习笔记：
learning-plan.md中的学习笔记区域 - 复习队列：
review-queue.md（若存在）——重点读carryover状态的项：计划结束仍未消解的盲区与疑问，是识别「认知陷阱模式」的最高价值素材
执行流程
Step 1：模式识别
前置检查：如果可用日志不足 3 天，停止并告知学习者：
"方法论收割需要至少 3 天的学习数据才能识别可靠的模式。当前只有 X 天日志，建议继续学习后再触发。"
扫描所有学习日志，寻找以下模式：
| 模式类型 | 识别信号 | 示例 |
|---|---|---|
| 学习策略模式 | 学习者反复使用某种学习方法且效果好 | "每次用类比理解新概念时，Post-test 提高明显" |
| 认知陷阱模式 | 学习者反复在某类概念上卡住（复习队列的 carryover 项是强信号） | "英文技术文档中的隐喻表达是持续弱项" |
| 角色效果模式 | 某个角色对学习效果影响显著 | "讲解员介入后，概念理解维度平均提升 40%" |
| 模式迁移 | 学到的概念可以迁移到其他领域 | "Subagent 的'独立上下文'概念可以迁移到团队协作" |
Step 2：方法论提炼
对每个识别到的模式，提炼为知识卡片：
- type:
pattern（可复用的方法/策略）或principle（底层原则/认知规律） - 核心洞见：一句话概括
- 适用场景：什么情况下用
- 证据来源：哪些天的学习日志支撑了这个方法论
Step 3：输出
- 按知识卡片标准格式写入文件
- 更新进度面板中的"方法论收割"区域
约束
- 至少需要 3 天的学习日志才能触发收割（单日不足以形成 pattern）
- 每个方法论必须有 ≥2 天的数据支撑
- 不编造没有数据支撑的"方法论"
- 输出不超过 5 张卡片/次（精选优于堆量）
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.
- 12d ago First seen · 65 lines · 50 tokens per session scan A cfd1c4cb340c
methodology-harvest is a skill published in the GitHub repository Sean-xhz/ai-learning-platform (2 stars, last pushed 1mo ago), licensed MIT. It adds 50 tokens to every session and 831 once invoked, about $0.0003 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
self-improve-with-tinyfish
Enables Hermes to create new reusable skills for itself by researching live web sources with TinyFish Search and Fetch, analyzing source coverage, writing SKILL.md files, and installing them into Hermes memory. Use when the user asks Hermes to learn, teach itself, upgrade itself, or save a reusable capability.
flow-next-audit
Audit .flow/memory/ entries against current code and keep, update, consolidate, replace, delete, or harden each. Use when asked to audit memory or graduate a recurring lesson into a gate.
mindos
MindOS: local knowledge assistant & shared KB. Keeps decisions, notes, SOPs, debugging lessons, research findings, preferences across sessions/agents. Core: save notes, search KB, organize files, run workflows, review, append CSV, hand off context, distill lessons. NOT for app source or paths outside KB. Triggers…
flashcards
Spaced repetition flashcard system for learning. SM-2 algorithm, supports text and cloze deletion cards.
learn-from-fix
Capture Elixir/Ecto/LiveView lessons and Hex API rules. Use after corrections or when asked to document learning, record a lesson, prevent a fixed mistake, or remember package guidance with --library.
curate
Adds developer-authored annotations to the gauntlet knowledge base. Use when capturing tribal knowledge or rationale not visible in code.