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 skills add wsshow/feikong-teams --skill fkteamsgit clone --depth 1 https://github.com/wsshow/feikong-teamsWrote 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/wsshow/feikong-teams/fkteams)<a href="https://agentmods.dev/skills/wsshow/feikong-teams/fkteams"><img src="https://agentmods.dev/badge/skills/wsshow/feikong-teams/fkteams/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.
<a href="https://agentmods.dev/skills/wsshow/feikong-teams/fkteams"><img src="https://agentmods.dev/badge/skills/wsshow/feikong-teams/fkteams.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 4 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Excessive Agency · line 232 Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
- high Excessive Agency · line 255 Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
- high Privilege Escalation · line 330 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- medium Data Exfiltration · line 313 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
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 5.1 | $0.00147 | $0.03668 |
| Opus 5 | $0.00073 | $0.01834 |
| Sonnet 5 | $0.00029 | $0.00734 |
| Haiku 4.5 | $0.00015 | $0.00367 |
Grade A, and why
fkteams scanned grade A with 1 finding 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 10d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s https://example.com/api | fkteams -q "解析这个 API 响应" How it starts
The opening of the file, as written. The whole thing — 382 lines — stays where its author put it; the contents beside it link to each section on GitHub.
fkteams 命令行完整指南
一、快速入门
# 第一步：生成配置文件
fkteams generate config
# 第二步：编辑配置，添加模型（必填）
# 编辑 ~/.fkteams/config/config.toml，填写 api_key 和 model
# 第三步（可选）：安装运行时依赖
fkteams init --all # 安装 uv（Python）和 bun（JavaScript）
# 第四步：启动
fkteams web # Web 界面（推荐）
fkteams # CLI 交互模式
二、启动与运行模式
模式对照表
| 模式 | 命令 | 适用场景 |
|---|---|---|
| Web 界面 | fkteams web |
日常使用，需要历史记录和可视化界面 |
| CLI 交互 | fkteams |
服务器/终端环境 |
| 直接查询 | fkteams -q "..." |
脚本集成、自动化 |
| 纯 API 服务 | fkteams serve |
作为后端独立部署 |
Web 界面模式
fkteams web
# 启动后访问 http://localhost:23456
CLI 交互模式
fkteams # 默认：团队模式（coordinator 协调多智能体）
fkteams -m deep # 深度分析模式
fkteams -m group # 多智能体讨论模式（圆桌）
fkteams --temporary # 临时会话，不保存历史
直接查询模式（非交互，执行后退出）
fkteams -q "帮我审查 main.go"
fkteams -m deep -q "深度分析这个架构"
fkteams -q "生成一份报告" # 默认保存历史
fkteams -q "临时问答" --temporary # 不保存历史
管道输入模式
管道有内容时自动进入非交互模式。
echo "解释一下 Go 的 context 包" | fkteams
cat main.go | fkteams -q "审查以下代码:"
git diff HEAD~1 | fkteams -q "审查这次提交"
curl -s https://example.com/api | fkteams -q "解析这个 API 响应"
规则：同时提供 -q 时，查询内容为 -q 文本 + 换行 + 管道内容；管道为空且无 -q 时报错。
纯 API 服务模式
fkteams serve
fkteams serve --host 0.0.0.0 --port 8080
与 web 提供相同的 API，但无前端页面。支持端点：GET /v1/models、POST /v1/chat/completions。
恢复历史会话
fkteams -r "20260302_091249" # 交互模式恢复
fkteams -r "20260302_091249" -q "继续上次的分析" # 恢复后直接查询
全局参数
| 参数 | 简写 | 说明 |
|---|---|---|
--mode |
-m |
工作模式：team（默认）/ deep / group |
--query |
-q |
直接查询模式，执行后退出 |
--resume |
-r |
恢复指定会话 ID |
--temporary |
--temp |
临时会话，不保存历史 |
--approve |
自动批准工具调用：all / command / file / git / dispatch（逗号分隔） |
三、交互模式内置命令
| 命令 | 说明 |
|---|---|
quit / q |
退出程序 |
help |
显示帮助 |
list_agents |
列出所有可用智能体 |
@智能体名 [查询] |
切换到指定智能体并可选执行查询 |
switch_work_mode |
切换工作模式 |
save_chat_history |
保存当前会话 |
list_chat_history |
列出所有历史会话 |
load_chat_history |
选择并加载历史会话 |
clear_chat_history |
清空当前会话（不删除文件） |
save_chat_history_to_markdown |
导出为 Markdown |
save_chat_history_to_html |
导出为 HTML |
list_schedule |
列出所有定时任务 |
cancel_schedule |
取消定时任务 |
delete_schedule |
删除定时任务 |
list_memory |
列出长期记忆条目 |
delete_memory |
删除记忆条目 |
clear_memory |
清空所有长期记忆 |
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.
- 10d ago First seen · 382 lines · 147 tokens per session scan A 0fed1a57148d
fkteams is a skill published in the GitHub repository wsshow/feikong-teams (147 stars, last pushed 4d ago), licensed MIT. It adds 147 tokens to every session and 3,668 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
code-review-practices
Provides practical guidance for conducting thorough code reviews that identify issues early, promote knowledge sharing, and deliver constructive feedback. This skill should be used when reviewing pull requests, establishing team review standards, or mentoring developers on effective review practices.
refactoring-advisor
Provides refactoring recommendations and step-by-step improvement plans. Use when planning refactoring, improving code structure, or reducing technical debt.
migration-review
Review database migration files when a change adds or modifies paths under migrations/. Use it before merge to collect forward, rollback, locking, and data-safety evidence.
learn-from-sage
Detection-gap (miss) analysis for Code Review Sage. Learn from shipped fixes, acted-on human comments, and design outcomes to close reviewer blind spots. Inline during review stages a candidate; a human triggers a one-shot AI consolidation into the live ruleset.
github-review-pr
Review GitHub pull requests with detailed, multi-perspective code analysis using parallel subagents. Use this skill whenever the user wants to review a PR, asks for code review on a pull request, mentions "review PR", "check this PR", "look at pull request", or references a PR number or GitHub PR URL. Do NOT use for…
no-mistakes
Validate committed feature-branch changes through the no-mistakes pipeline: intent, rebase, review, test, docs, lint, push, PR, and CI. Use when the user asks to run no-mistakes, ship safely, validate before pushing, or gate a change before it reaches upstream.