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/dinhanhthi/coding-friend/cf-plan-customnpx skills add dinhanhthi/coding-friend --skill cf-plan-customgit clone --depth 1 https://github.com/dinhanhthi/coding-friendWrote 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/dinhanhthi/coding-friend/cf-plan-custom)<a href="https://agentmods.dev/skills/dinhanhthi/coding-friend/cf-plan-custom"><img src="https://agentmods.dev/badge/skills/dinhanhthi/coding-friend/cf-plan-custom.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 | $0.00000 | $0.02460 |
| Opus 5 | $0.00000 | $0.01230 |
| Sonnet 5 | $0.00000 | $0.00492 |
| Haiku 4.5 | $0.00000 | $0.00246 |
Grade A, and why
cf-plan-custom 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 5d 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 — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Before
New Skill/Agent Detection
Force trigger: If the task description contains --skill or --agent flag → strip the flag from the description, pre-select the type (skill or agent) for the Skill Type Decision later, and skip detection + confirmation — go directly to the challenge below.
Auto-detect: Scan the task description for these keyword patterns (case-insensitive):
- "new skill", "create skill", "add skill", "build skill"
- "new command", "create command", "add command"
- "new agent", "create agent", "add agent"
If none of these patterns match → skip this entire Before section and proceed with standard cf-plan.
If a pattern matches → ask the user to confirm: "It looks like you want to create a new Coding Friend skill/agent — is that correct?" If they say no, skip this Before section.
If confirmed → proceed with the challenge below.
Challenge: Is a New Skill Really Needed?
Before planning anything, challenge the idea rigorously. Ask the user these questions using AskUserQuestion (one round, all 5 questions — batched intentionally to minimize back-and-forth since these are validation questions, not discovery):
-
What specific gap does this fill? What can't you do today with existing skills? Be concrete — "it would be nice" is not a gap.
-
Can an existing skill be extended instead? Read
plugin/context/bootstrap.mdat runtime to get the current inventory of skills and agents (do not rely on a hardcoded list — skills change over time). Could any of them be extended with new steps, modes, or flags to cover this use case? -
Can existing skills be combined/chained? Could a workflow combining 2-3 existing skills achieve the same result? For example,
/cf-scan+/cf-rememberor/cf-fix+/cf-review. If yes, a small doc describing the combo may be all that's needed. -
Who is the audience? All Coding Friend users (→ plugin skill), only this project (→ custom guide), or only you the creator (→
.claude/skills/)?
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.
- 5d ago First seen · 182 lines · 0 tokens per session scan A d34471038a77
cf-plan-custom is a skill published in the GitHub repository dinhanhthi/coding-friend (3 stars, last pushed 5d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,460 tokens. 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
dingtalk_channel_connect
Use a headed browser to automatically complete DingTalk channel integration for QwenPaw. Applicable when the user mentions DingTalk, developer console, Client ID, Client Secret, bot, Stream mode, binding or configuring a channel. Supports pausing when a login page is detected and resuming after the user logs in.
make_plan
For external plan request scenarios, guides the Agent to request a clear, actionable, step-by-step plan from a stronger Agent via listagents and chatwithagent, emphasizing that the plan is executed by the requester, not by the consulted Agent.
当用户需要对PDF文件进行任何操作时,请使用此技能。包括从 PDF 中读取或提取文本/表格、合并多个 PDF、拆分 PDF、旋转页面、添加水印、创建新PDF、填写PDF表单、加密/解密 PDF、提取图片,以及对扫描版 PDF 进行 OCR 使其可搜索。如果用户提到 .pdf 文件或要求生成 PDF,请使用此技能。.
gpt-image-2
面向 GPT Image 2 的图像生成 / 编辑技能。可在 3 种环境下使用:(A) Garden 本地模式,通过 OpenAI 兼容接口直接出图并落盘;(B) Host-Native 模式,把本 Skill 当作提示词工程指引,把渲染好的 prompt 交给宿主 Agent 自带的图像工具出图;(C) Advisor 模式,宿主无任何图像工具时退化为高质量 prompt 顾问。涵盖 18 大类、80+ 个结构化模板,覆盖海报 / UI / 产品 / 信息图 / 学术图 / 技术架构图 / 漫画 / 头像 / 流程板 / 电影分镜 / IP 周边 / 编辑工作流等场景。.
new
Create a new project to start development quickly.
oss-upload
Upload local files to Tencent COS (oss.1024code.com CDN) using coscli. Use when user wants to upload a file to CDN/OSS, or deploy static assets.