agentmods.dev

javis-os: Skill for Claude Code

.claude/skills/ingest-source/SKILL.md

Ingest Source is a skill for Claude Code from blogminhquy/javis-os. It costs 28 tokens per session (862 once invoked), scanned A, original, MIT.

A workflow for turning a raw source, such as an article, book, or transcript, into connected pages in a personal knowledge wiki.

In plain words
What is it for?
Use it to process source files, extract key ideas and frameworks, create or update wiki pages, link related concepts, and check whether the resulting pages answer important questions.
Why use it?
It prevents useful details from being lost when long material is summarized and checks existing pages first to avoid creating duplicate knowledge.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions CLAUDE.md; mentions AGENTS.md.

This is blogminhquy/javis-os's own configuration. It tells Claude Code how to work on javis-os itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything javis-os configures →

not rated 194repo +6 today A scan SkillSpector: pass 28 tokens original MIT
View source ↗ blogminhquy/javis-os javisos.com
Reuse

Borrowing it

Nothing to install: this file belongs to blogminhquy/javis-os. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/blogminhquy/javis-os/main/.claude/skills/ingest-source/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/blogminhquy/javis-os

Made for: Claude Code.

Wrote 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.

agentmods badge for Ingest Source

README.md
[![agentmods](https://agentmods.dev/badge/skills/blogminhquy/javis-os/ingest-source/github.svg)](https://agentmods.dev/skills/blogminhquy/javis-os/ingest-source)
Your own site
<a href="https://agentmods.dev/skills/blogminhquy/javis-os/ingest-source"><img src="https://agentmods.dev/badge/skills/blogminhquy/javis-os/ingest-source/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.

agentmods 80×15 button for Ingest Source

Your own site · 80×15
<a href="https://agentmods.dev/skills/blogminhquy/javis-os/ingest-source"><img src="https://agentmods.dev/badge/skills/blogminhquy/javis-os/ingest-source.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 28 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 862 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00028 $0.00862
Opus 5 $0.00014 $0.00431
Sonnet 5 $0.00006 $0.00172
Haiku 4.5 $0.00003 $0.00086

Measured 11d ago against content hash a5ff4dfc1ea5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

Ingest Source 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 11d 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.

.claude/skills/ingest-source/SKILL.md · 41 lines

How it starts

The opening of the file, as written. The whole thing — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.

INGEST - tiêu hoá 1 source thành wiki (compounding)

Khi nào dùng

Kích hoạt khi người dùng nói những câu như: "tiêu hoá source này", "xử lý bài này vào wiki", "đọc file này rồi ghi lại kiến thức", hoặc khi có file mới thả vào sources/.

Skill làm theo đúng 3 kỷ luật của vault.

Đọc schema vault (CLAUDE.md/AGENTS.md ở gốc brain) trước; đây là bản thao tác của phép INGEST.

Trước khi làm

  • Kiểm frontmatter source: status: processed -> DỪNG, báo đã xử lý, hỏi có re-ingest không. unprocessed/chưa có -> làm.
  • Phân loại độ dài. Source dài (>= ~10.000 dòng / sách / transcript) -> BẮT BUỘC 3-pass:
    1. Đọc lướt, lập mục lục theo số dòng (vd "1-1300: giới thiệu"). Báo người dùng xác nhận trọng tâm.
    2. Đọc sâu từng đoạn ~1.000-1.500 dòng, viết wiki NGAY từng đoạn (đừng nén cả file 1 lần - mất 25-40% chi tiết).
    3. Tự hỏi 5 câu về các vùng khác nhau; wiki không trả lời được câu nào -> quét bổ sung vùng đó.

Các bước

  1. Đọc source (kèm ảnh nếu có).
  2. Tóm tắt 3-5 ý chính; rút insight/framework; liên hệ khái niệm đã có.
  3. Xác định trang wiki: mới cần tạo / cần cập nhật / cần merge (đọc wiki/index.md để dedup).
  4. Viết/cập nhật wiki (1 trang = 1 ý, có [[...]] ngược lại trang liên quan) - TUÂN THỦ 3 KỶ LUẬT:
    • Citation cứng: mỗi câu cụ thể kết bằng [[Nguồn]].
    • Mục tiêu vs thực tế: gắn nhãn "(mục tiêu)" / "(thực tế tính đến ...)" / "(cần xác minh)".
    • Mâu thuẫn với trang cũ: thêm ## Mâu thuẫn (giữ cả 2 quan điểm + nguồn) + append wiki/_open-questions.md, KHÔNG ghi đè. Ngoài 3 kỷ luật, mỗi trang phải TỰ ĐỦ NGỮ CẢNH (contextual retrieval - trang tách khỏi source vẫn hiểu và tìm thấy được):
    • Mở đầu trang bằng 1-2 câu định vị: khái niệm này là gì, thuộc chủ đề/nguồn nào, dùng khi nào. Nhất là khi ingest source dài theo từng đoạn - đoạn giữa sách mà thiếu câu định vị là sau này đọc lẻ không hiểu.
    • Frontmatter thêm aliases: [tên gọi khác, viết tắt, thuật ngữ tiếng Anh] - để sau này hỏi bằng từ khác thì grep/search vẫn bắt trúng trang.
  5. Cập nhật wiki/index.md (thêm dòng link + mô tả 1 dòng).
  6. Set source status: processed, processed_at, wiki_links: [...]. Không đáng vào wiki -> status: skipped + note.
  7. Append wiki/log.md: ## [YYYY-MM-DD] ingest | <tên source> + nguồn/đã tạo/đã cập nhật/insight.
  8. Đề xuất task nếu source mở ra hành động (chỉ đề xuất). Báo cáo ngắn: tóm tắt + trang đã chạm + insight + task.

Read the full file on GitHub · 41 lines

Changes

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.

  1. 11d ago First seen · 41 lines · 28 tokens per session scan A a5ff4dfc1ea5

Subscribe to this mod's changes

Ingest Source is a skill published in the GitHub repository blogminhquy/javis-os (194 stars, last pushed today), licensed MIT. It adds 28 tokens to every session and 862 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 2026-08-30.

Memory and contextagent-operationsagent-optimizationagent-orchestrationagent-orchestratoragent-osai-agent
Related

Other skills, from other repositories

handoff

Write a compact, decision-ready handoff so the next session (or the user) can continue without reconstructing the current one. Use when the session is ending, context is running low, the user asks for a handoff / "pass the baton" / "hand off", or a long-running operation needs a durable state checkpoint.

Hmbown/CodeWhale · 70 tokens

cao-learning

Report task outcomes and distill lessons so the team improves across runs — reportoutcome after each unit of work, retrospector handoffs at natural boundaries, and applying injected lessons. Use in workflows that run repeatedly over similar work items. Requires memory.learningenabled; degrade silently when the tools…

awslabs/cli-agent-orchestrator · 63 tokens

cao-memory

Store, recall, and forget durable facts with CAO memory — user preferences, project conventions, decisions, and corrections that should persist across sessions and agents. Use proactively to check memory before asking the user, and to save anything worth remembering. Distinct from any provider-native memory.

awslabs/cli-agent-orchestrator · 59 tokens

state-management

STATE.md reading, writing, and field-level updates. Provides cross-session state persistence via .planning/STATE.md with structured fields for current task, completed phases, blockers, decisions, and quick tasks.

a5c-ai/babysitter · 43 tokens

mem0-integration

Mem0 memory layer integration for AI agents. Implement persistent, semantic memory for long-term context retention and personalization.

a5c-ai/babysitter · 27 tokens

context-preservation

State capture and restore across context window compactions. Monitors usage thresholds and serializes quality, task, and spec state for seamless continuation.

a5c-ai/babysitter · 32 tokens