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/itxaiohanglover/mcp-codestyle-server/codestylenpx skills add itxaiohanglover/mcp-codestyle-server --skill codestylegit clone --depth 1 https://github.com/itxaiohanglover/mcp-codestyle-serverWrote 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/itxaiohanglover/mcp-codestyle-server/codestyle)<a href="https://agentmods.dev/skills/itxaiohanglover/mcp-codestyle-server/codestyle"><img src="https://agentmods.dev/badge/skills/itxaiohanglover/mcp-codestyle-server/codestyle.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 | $0.00088 | $0.01014 |
| Opus 5 | $0.00044 | $0.00507 |
| Sonnet 5 | $0.00018 | $0.00203 |
| Haiku 4.5 | $0.00009 | $0.00101 |
Grade A, and why
codestyle 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 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.
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 — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codestyle
Code template management: CLI tools for search/get/upload + AI-guided generation.
Decision Tree
User request
│
├─ "search" / "检索" ──→ Search Workflow (CLI, local+remote)
│
├─ "get" / "获取" ──→ Get Workflow (CLI, local+remote)
│
├─ "generate" / "生成" ──→ Generate Workflow (AI dialog, then upload)
│
└─ "upload" / "上传" ──→ Upload Workflow (CLI, remote)
Commands
| Command | Execution | Description |
|---|---|---|
search |
CLI (JAR) | Search templates (local Lucene + remote API) |
get |
CLI (JAR) | Get full template content |
generate |
AI Dialog | Multi-turn conversation, then call upload |
upload |
CLI (JAR) | Upload template to server |
Quick Start
Windows
"<SKILL_DIR>\scripts\codestyle.bat" search "keyword"
"<SKILL_DIR>\scripts\codestyle.bat" get "template-path"
"<SKILL_DIR>\scripts\codestyle.bat" upload --path ./my-template
Linux/macOS
bash <SKILL_DIR>/scripts/codestyle search "keyword"
bash <SKILL_DIR>/scripts/codestyle get "template-path"
bash <SKILL_DIR>/scripts/codestyle upload --path ./my-template
Generate (AI Dialog)
User: 把这段代码做成模板：[代码]
AI: [多轮对话引导生成模板]
AI: [调用 upload 存储]
Workflows
See references/ for detailed workflow instructions:
- Search Workflow - Find templates (local+remote)
- Get Workflow - Retrieve template content by full path
- Generate Workflow - AI-guided template creation
- Upload Workflow - Submit templates (remote)
Generate Workflow Overview
Generate workflow is pure AI dialog, no script calls until final upload.
| Input | Example | Pre-processing |
|---|---|---|
| Code snippet | @RestController ... |
None |
| Current file | "当前这个文件" | Read file |
| Local path | /path/to/file.java |
Read file |
| GitHub URL | https://github.com/xxx/repo |
Clone repo |
| Web URL | https://blog.xxx.com/... |
Crawl content |
What ships with it
36 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.
- examples/CRUD/1.0.0/bankend/sql/Menu.ftl 3.5 KB
- examples/CRUD/1.0.0/bankend/src/main/java/com/air/controller/Controller.ftl 1.1 KB
- examples/CRUD/1.0.0/bankend/src/main/java/com/air/mapper/Mapper.ftl 354 B
- examples/CRUD/1.0.0/bankend/src/main/java/com/air/model/entity/Entity.ftl 811 B
- examples/CRUD/1.0.0/bankend/src/main/java/com/air/model/query/Query.ftl 1.2 KB
- examples/CRUD/1.0.0/bankend/src/main/java/com/air/model/req/Req.ftl 1.5 KB
- examples/CRUD/1.0.0/bankend/src/main/java/com/air/model/resp/DetailResp.ftl 1.3 KB
- examples/CRUD/1.0.0/bankend/src/main/java/com/air/model/resp/Resp.ftl 923 B
- examples/CRUD/1.0.0/bankend/src/main/java/com/air/service/impl/ServiceImpl.ftl 956 B
- examples/CRUD/1.0.0/bankend/src/main/java/com/air/service/Service.ftl 716 B
- examples/CRUD/1.0.0/bankend/src/main/resources/mapper/MapperXml.ftl 226 B
- examples/CRUD/1.0.0/frontend/src/api/api.ftl 2.0 KB
- examples/CRUD/1.0.0/frontend/src/components/AddModal.ftl 3.6 KB
- examples/CRUD/1.0.0/frontend/src/components/DetailDrawer.ftl 1.9 KB
- examples/CRUD/1.0.0/frontend/src/views/index.ftl 6.8 KB
- examples/CRUD/1.0.0/meta.json 23 KB
- examples/CRUD/1.0.0/README.md 7.2 KB
- references/config.md 3.7 KB
- references/generate-workflow.md 14 KB
- references/get-workflow.md 5.6 KB
- references/search-workflow.md 2.7 KB
- references/template-format.md 7.1 KB
- references/template-syntax.md 2.7 KB
- references/upload-workflow.md 3.6 KB
- scripts/.gitignore 159 B
- scripts/cfg.json 228 B
- scripts/codestyle 1.6 KB
- scripts/codestyle-server.jar 68320 KB
- scripts/codestyle.bat 1.5 KB runs code
- scripts/init-repository.bat 4.3 KB runs code
- scripts/init-repository.sh 3.6 KB runs code
- scripts/install.bat 2.1 KB runs code
- scripts/install.sh 1.6 KB runs code
- scripts/update.bat 2.3 KB runs code
- scripts/update.sh 2.0 KB runs code
- scripts/validate_template.py 5.3 KB runs code
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 · 141 lines · 88 tokens per session scan A 6b8bd4f374d4
codestyle is a skill published in the GitHub repository itxaiohanglover/mcp-codestyle-server (55 stars, last pushed 5mo ago), licensed MIT. It adds 88 tokens to every session and 1,014 once invoked, about $0.0004 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.
Other skills, from other repositories
web-research
Use when a task needs current public-web facts, comparisons, fact-checking, sources, or a multi-source synthesis and both websearch and webfetch are available.
config-manager
Use when the Config Manager Agent reads or changes Denova presets, game modules, automations, Skills, or Agent profiles through configread and configapply.
novel-standard
Standard writing workflow in which the main Agent drafts and revises while the built-in general-purpose SubAgent reviews, balancing quality and speed.
novel-lite
Fast continuation, exploratory drafts, and low-latency prose generation performed directly by the main Agent without review or revision subprocesses.
chapter-illustration
Generate one spoiler-free illustration for the current or specified chapter and save it under workspace assets/illustrations.
interactive-image
Generate one image for an already established interactive-story turn.