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-fixnpx skills add dinhanhthi/coding-friend --skill cf-fixgit 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-fix)<a href="https://agentmods.dev/skills/dinhanhthi/coding-friend/cf-fix"><img src="https://agentmods.dev/badge/skills/dinhanhthi/coding-friend/cf-fix.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 | $0.00075 | $0.02596 |
| Opus 5 | $0.00037 | $0.01298 |
| Sonnet 5 | $0.00015 | $0.00519 |
| Haiku 4.5 | $0.00007 | $0.00260 |
Grade A, and why
cf-fix 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 — 296 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/cf-fix
CLI Requirement: OPTIONAL — Uses the memory MCP from
coding-friend-clifor fast indexed search and storage. Without the CLI: falls back to grep overdocs/memory/and direct file writes. Full functionality preserved, slower memory recall. See CLI requirements.
Fix the bug: $ARGUMENTS
Workflow
Step 0: Custom Guide
bash "<plugin-root>/lib/load-custom-guide.sh" cf-fix
If output is not empty: ## Before → before first step, ## Rules → throughout, ## After → after final step.
Step 1: Understand the Bug
- Read the error or description from
$ARGUMENTS - If unclear, ask expected vs actual, and when it happens
Step 2: Verify the Problem Exists
- Run the failing test or command; capture exact output
- If you cannot reproduce, tell the user and ask for context — do NOT guess
- No test AND
--add-tests(alias--tdd) → write one that fails. Else reproduce via existing tests or by running the code.
Step 3: Recall Past Bugs + Explore Relevant Code
3a. Check existing bug docs (memory recall):
Extract 2–3 keywords from the bug.
Primary — Memory MCP (if memory_search is available):
{ "query": "<bug keywords>", "type": "episode", "limit": 3 }
Fallback — grep ({docsDir} from .coding-friend/config.json, default docs):
- Grep
^description:in{docsDir}/memory/bugs/**/*.md - Else grep
^tags:
Read the top 1–2 matches; pass relevant findings to the explorer.
3b. Generate task-id and explore (cf-explorer):
- task-id:
YYYY-MM-DD-<short-descriptor> - docsDir:
.coding-friend/config.jsonordocs - Context file:
{docsDir}/context/{task-id}.json
Call invoke_subagent with agent cf-explorer. Pass:
Diagnose this bug: [from $ARGUMENTS] Error output: [Step 2] Context file: write structured findings to [docsDir/context/.json] [If 3a hits]: Related past bugs: [summary] Answer: (1) error path backward to origin (2) files/functions/deps (3) existing tests (4) relevant patterns
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 · 296 lines · 75 tokens per session scan A dcdd95cb00d5
cf-fix is a skill published in the GitHub repository dinhanhthi/coding-friend (3 stars, last pushed today), licensed MIT. It adds 75 tokens to every session and 2,596 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 2026-08-31.
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.
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。.
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.
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.