agentmods.dev

javis-os: Skill for Claude Code

.claude/skills/javis-builder/SKILL.md

Javis Builder is a skill for Claude Code from blogminhquy/javis-os. It costs 35 tokens per session (3,611 once invoked), scanned A, original, MIT.

A builder for creating or editing Javis capabilities, such as agents, Skills, workflows, loops, and plugins. Javis is an agent system that can be extended with these components.

In plain words
What is it for?
Use it to add reusable knowledge, specialist roles, multi-step processes, scheduled tasks, or new tools to Javis.
Why use it?
It helps choose the right kind of capability and create it in the expected format instead of building overlapping or unsuitable components.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths; mentions Claude Code; mentions Codex.

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 changed today A scan SkillSpector: pass 35 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/javis-builder/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 Javis Builder

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/blogminhquy/javis-os/javis-builder"><img src="https://agentmods.dev/badge/skills/blogminhquy/javis-os/javis-builder.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,611 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 $0.00035 $0.03611
Opus 5 $0.00017 $0.01806
Sonnet 5 $0.00007 $0.00722
Haiku 4.5 $0.00003 $0.00361

Measured today against content hash d19a07703a02, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

Javis Builder 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 today.

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/javis-builder/SKILL.md · 200 lines

How it starts

The opening of the file, as written. The whole thing — 200 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Javis Builder - tạo agent / skill / workflow / loop

Khi nào dùng

Kích hoạt khi người dùng nói những câu như: "tạo agent chuyên X", "thêm kỹ năng Y", "dựng workflow nghiên cứu rồi viết", "tạo loop mỗi 2 tiếng làm Z", "viết tool/plugin tính ...", "làm cho Javis biết làm ...".

Khi người dùng muốn Javis có thêm một năng lực, bạn TỰ GHI FILE .md đúng chuẩn dưới đây vào vault (brain đang chọn). Studio / trang tương ứng tự nhận file mới. Luôn báo cáo ngắn sau khi tạo.

Quy trình (làm đúng thứ tự)

  1. Hiểu nhu cầu. Nếu mô tả đủ rõ thì làm luôn; thiếu điểm cốt lõi (mục tiêu, đầu ra mong muốn) thì hỏi 1 câu ngắn rồi làm. Đừng hỏi lan man.
  2. Chọn đúng LOẠI năng lực:
    • Việc trả lời/kiến thức cách-làm tái dùng nhiều lần -> skill.
    • Một "vai" chuyên môn có system prompt riêng -> agent.
    • Chuỗi nhiều bước, nhiều vai nối nhau -> workflow (tạo trước các agent còn thiếu).
    • Việc LẶP theo chu kỳ, tự chạy nền -> loop.
    • Cần một TOOL native mới (làm được bằng Python, tái dùng, mọi engine gọi được) mà chưa có MCP -> plugin. Chỉ là hướng dẫn cách làm bằng tool sẵn -> skill. Nguồn dữ liệu ngoài có sẵn MCP -> đấu MCP.
    • Việc làm 1 lần -> KHÔNG tạo gì, cứ làm luôn hoặc đề xuất task Kanban.
  3. Chống trùng. TRƯỚC khi tạo, đọc folder tương ứng (agents/ workflows/ skills/ loops/). Nếu đã có cái gần giống -> cập nhật cái cũ, đừng đẻ bản sao.
  4. Ghi file đúng frontmatter (mẫu bên dưới). slug = ASCII không dấu, gạch nối. Tên hiển thị tiếng Việt. TUYỆT ĐỐI không dùng ký tự em dash, dùng "-". group là BẮT BUỘC với cả ba loại agent / skill / workflow. Trước khi chọn, đọc nhóm đang dùng trong agents/*.md, workflows/*.md, skills/*/SKILL.md rồi lấy nhóm sát nhất; không nhóm nào hợp thì đặt nhóm mới, tên ngắn theo lĩnh vực. Bỏ trống thì nó rơi vào "Chung" và trang Studio dồn hết vào một đống - đúng chỗ mà cột nhóm sinh ra để tránh.
  5. Báo cáo ngắn bằng văn nói: đã tạo loại gì, tên/đường dẫn file, dùng ở đâu.

Read the full file on GitHub · 200 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. today Changed · +1 lines d19a07703a02
  2. 6d ago Changed · +6 lines 6a8a60cdbca6
  3. 11d ago First seen · 193 lines · 35 tokens per session scan A 53b048d51a22

Subscribe to this mod's changes

Javis Builder is a skill published in the GitHub repository blogminhquy/javis-os (194 stars, last pushed yesterday), licensed MIT. It adds 35 tokens to every session and 3,611 once invoked, about $0.0002 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.

Building agentsagent-operationsagent-optimizationagent-orchestrationagent-orchestratoragent-osai-agent
Related

Other skills, from other repositories

beevibe-team-mesh-negotiation

Multi-round negotiation protocol — covers both initiator and peer roles. Use when about to call negotiate(), when receiving a intent block as a peer, or when receiving an 'escalated' sentinel from a blocked respondnegotiate. Covers proposal crafting, counter-strategy, deadlock detection, when to accept early…

beevibe-ai/beevibe · 112 tokens

beevibe-verify-pr

CI verification before marking a PR-bearing task done. Use BEFORE calling mcpbeevibeupdateprogress(done) on any session whose deliverable is a pull request — including the first dispatch (you opened the PR with gh pr create) and any revision dispatch (you pushed new commits to an existing PR). Watches the PR's…

beevibe-ai/beevibe · 172 tokens

beevibe-pre-task-setup

Cold-start git workspace setup for a fresh beevibe task. Use at the start of a session whose intent has a block but NO or block — i.e. the first dispatch of this task. Checks for an existing repo clone, pulls the base branch if present (clone if missing), prunes any per-task worktrees from earlier tasks whose work has…

beevibe-ai/beevibe · 198 tokens

beevibe-use-repo

You are the child agent inside a fresh Docker sandbox. Borrow the given GitHub repo, produce a real artifact for the goal, and export it. Do not review the repo. The proof is that it works.

beevibe-ai/beevibe · 50 tokens

beevibe-discover-repo

Find the best GitHub repo for a goal, then call userepo to run it in a sandbox. Use whenever the user's goal requires a capability you don't have natively and you haven't been given a specific repo.

beevibe-ai/beevibe · 51 tokens

gitnexus-refactoring

Use when the user wants to rename, extract, split, move, or restructure code safely. Examples: "Rename this function", "Extract this into a module", "Refactor this class", "Move this to a separate file".

qualixar/qualixar-os · 53 tokens