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 agentmods add skills/yyz666ai/learning-agent/knowledge-curatornpx skills add yyz666ai/Learning-Agent --skill knowledge-curatorgit clone --depth 1 https://github.com/yyz666ai/Learning-AgentWrote 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/yyz666ai/learning-agent/knowledge-curator)<a href="https://agentmods.dev/skills/yyz666ai/learning-agent/knowledge-curator"><img src="https://agentmods.dev/badge/skills/yyz666ai/learning-agent/knowledge-curator.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 | $0.00055 | $0.00853 |
| Opus 5 | $0.00028 | $0.00426 |
| Sonnet 5 | $0.00011 | $0.00171 |
| Haiku 4.5 | $0.00006 | $0.00085 |
Grade A, and why
knowledge-curator scanned grade A with 1 finding 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 4d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
1. **先搜**：先搜权威技术文档 / 官方教程。**用 `python tools/web_search.py "查询词"` 联网搜索**（DeepSeek 原生 web_search，返回带来源的结果）；要抓某个官方文档的具体内容时，用 `curl -s <官方URL>`。把关键来源、版本记下来，作为后续原子的参考依据。 What it actually says
知识库自生长
教 curriculum 里没有的主题时，按 「搜 → 规划（先做）→ 懒沉淀（后台做）」 三步走。不要一上来把整个知识库预生成——只沉淀「真教过、验证过」的知识。
执行流程（定稿）
- 先搜：先搜权威技术文档 / 官方教程。用
python tools/web_search.py "查询词"联网搜索（DeepSeek 原生 web_search，返回带来源的结果）；要抓某个官方文档的具体内容时，用curl -s <官方URL>。把关键来源、版本记下来，作为后续原子的参考依据。 - 出 Plan（先做）：用 plan 模式生成分阶段学习大纲，立即存成
learning-paths/下的路线——这是知识库的骨架，先落盘。 - 建层级：没有就在
$DEV_CURRICULUM/下建libraries/<主题>/README.md（是什么/前置/路线）+atoms/。 - 懒沉淀（后台做，别急）：不预生成全部原子；而是每实际教完课堂并完成必答选择题后，才把该章写成可复用资产（Markdown 原子 + 配套
.deck.html+ 结构化讲义缓存）。课后打印输出不再是写入门禁。后台由服务完成原子写入，不能让模型在生成阶段自行宣称已保存。写到$DEV_CURRICULUM/（dev 母本的绝对路径），不要写到 cwd 里的只读快照。- 同时保存研究来源、版本、题目答案、常见误区、讲义修订版本和适用画像。
- 写入失败必须记录
pending_sync，不能静默声称已经反哺知识库。
- 复用边界：后续同主题、同路线、同能力层级、且覆盖范围相同的章节优先复用已验收资产，减少模型调用；画像、路线或章节范围不同则重新生成，不能硬套旧课。
- 反向修订：教学后发现讲得不好、有误区、练习太难 → 回改
$DEV_CURRICULUM/下的原子（追加误区、调练习），并同步改对应 deck。 - 重点问题：学习者提出涉及原理、边界、错误、性能、安全或架构的重点问题时，先把问题与 Agent 总结写入
curation/pending/待整理队列并加入个人复习卡；复核正确性与可复用性后，才合并进公共知识原子。 - 留痕：git commit，注明触发原因 + 参考来源。
边界
- 只能写
$DEV_CURRICULUM/（atoms、learning-paths、README）；改.codex/skills/、AGENTS.md、references/仍需用户显式确认。 - 原子要小而可复用，一个原子 = 一个知识点，不复制大段代码。
- 没教过、没复核的候选内容不直接写进公共原子；先标记为待整理，避免把一次个人对话当成普遍结论。
- Markdown 原子与 HTML deck 必须同步：改一个，同步改另一个。
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.
- 4d ago First seen · 29 lines · 55 tokens per session scan A 0b036f96827c
knowledge-curator is a skill published in the GitHub repository yyz666ai/Learning-Agent (1 stars, last pushed 4d ago), licensed MIT. It adds 55 tokens to every session and 853 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
sentiment-surprise
Computes a sentiment surprise by comparing the current quarter's tone against the trailing eight-quarter mean stored in long-term memory. Use whenever the analysis needs tone change relative to history, not just an absolute tone score.
bootstrap
Generate a personalized SOUL.md through a warm, adaptive onboarding conversation. Trigger when the user wants to create, set up, or initialize their AI partner's identity — e.g., "create my SOUL.md", "bootstrap my agent", "set up my AI partner", "define who you are", "let's do onboarding", "personalize this AI", "make…
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.
skillpack-creator
Create a reusable SkillPack from a successful completed task. Use when the user wants to convert a one-off research, coding, analysis, or content workflow into a distributable local SkillPack with skillpack.json, local skills under skills/, starter prompts, start scripts, and an optional zip package.
skill-creator
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
distill-session-knowledge
Offline-mine this project's pi session JSONL logs into reusable, verified knowledge: extracts faults, decisions, corrections, procedures and docs, promotes only recurring patterns, and routes artifacts into skillmanage, memory and docs. Use on "mine my sessions", "distill session knowledge", "extract lessons from…