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 Songhonglei/better-agent-skills --skill multica-squad-onboardgit clone --depth 1 https://github.com/Songhonglei/better-agent-skillsWrote 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/songhonglei/better-agent-skills/multica-squad-onboard)<a href="https://agentmods.dev/skills/songhonglei/better-agent-skills/multica-squad-onboard"><img src="https://agentmods.dev/badge/skills/songhonglei/better-agent-skills/multica-squad-onboard/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/songhonglei/better-agent-skills/multica-squad-onboard"><img src="https://agentmods.dev/badge/skills/songhonglei/better-agent-skills/multica-squad-onboard.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00081 | $0.01512 |
| Opus 5.5 | $0.00032 | $0.00605 |
| Sonnet 5.5 | $0.00016 | $0.00302 |
| Haiku 4.5 | $0.00008 | $0.00151 |
Grade A, and why
multica-squad-onboard 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 6d 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 — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Multica 小队接入
- Version: 1.0.0
- License: MIT
- Author: Evan Song · github.com/Songhonglei
- Repository: https://github.com/Songhonglei/better-agent-skills
用户只需提供项目 ID 或 URL。队长、成员、业务 Skill 和分工从现有配置读取;不要求重复填表,不擅自选择负责人;用户明确目标和授权后可通过 CLI 设置项目负责人。不创建小队、不增删成员、不更换 Runtime、不修改容量或权限。用户另行提供的小队 ID/URL是校验约束,不能绕过“负责人领导唯一有效小队”的前提。
检查与前置设置
- 读取项目定位信息、当前登录环境及用户已明确的操作范围。“检查”只读;“接入/配置”允许完成该项目的安装和指令配置,不代表发布 Skill、业务派单或部署代码。URL 用同源服务器查证;仅 ID 使用当前 CLI 配置。服务器或工作区存在歧义时集中询问,不猜测域名映射。
- 执行 scripts/onboard.py 的
inspect,将快照保存到安装目录外。脚本核验项目负责人是 Agent、同工作区唯一未归档小队、队长在成员中、至少一名非队长 Agent,以及成员与 Runtime 配置。读 references/operations.md 的参数、安装和恢复流程。 - 有阻断条件时,返回具体对象、问题和 Multica 设置位置。目标未知时由用户确定负责人/队长/成员,登录和权限申请仍由用户完成。用户已明确目标并授权负责人变更时,直接调用
set-project-lead设置,不要求用户再手工操作或重复确认;只读检查不能执行该修复。修复后重新读取,不能仅凭“已完成”判定通过。离线、容量无效、缺少明确业务能力的成员单列;不自行提高容量或补装业务 Skill。 - 业务能力只按项目/任务明确声明核验,未声明时不编造必需 Skill 或角色,也不把未配置专业分工当阻断。异质成员不要求装相同业务 Skill。正式任务的能力筛选交给队长与公共 Skill。
安装与指令配置
- 从当前工作区查找唯一
multica-squad-load-balancer。核验完整包、版本及 用户认可的可信来源;不存在时走已授权的可信来源安装流程,详见 operations 的“公共 Skill 安装”。保留已有分配。已有同名包来源不明、版本冲突或不完整时先报告;覆盖会影响其他项目,未授权不覆盖。 - 阅读私有快照中的项目说明、Squad/Agent 指令,查找手工选人、重复 mention、队长代做、自动换人重派等冲突。不要机械追加相反规则。未托管的冲突先提出精确修改,只有已授权才修改;组织关系不擅改,已授权的负责人修复按前述流程执行。Agent 可能跨项目任不同角色,Squad 也可能被复用。
- 使用 references/roles.md 的项目作用域模板。
prepare生成私有变更计划,保留托管块外原文;apply只允许项目 description、Squad/Agent instructions 和公共 Skill 的追加分配。重复执行更新同项目块,不重复追加。不修改原业务 Skill、模型、Runtime、容量、审批或状态规则。 - 应用前展示具体变更摘要;已有“接入/配置”授权时直接继续,不为常规步骤重复确认。检查模式不能执行 apply 或 set-project-lead;组织角色选择、额外覆盖或外部操作仍需对应授权。写后读回;部分失败或结果不确定先对账,按 operations 恢复,不盲目重试或自动回滚他人修改。
验收与交付
- 再次 inspect,并核对计划内字段、Skill 分配、完整包和组织关系;运行同安装版本公共 Skill 的
preview --project-id <UUID>。只有原业务明确要求时才加--required-skill-id/--member-role。不调用plan、dispatch、verify-worker,不创建测试 Issue;用户另外授权真实业务测试时才按公共 Skill 处理。 - 在当前会话、工作目录及项目关联信息中发现代码和任务入口;先核对与目标项目的关联,不因当前目录有代码就默认属于该项目,再检查相关入口的重复调度规则;找不到标“未检查”,不要求必须提供仓库,不将局部检查描述为全覆盖。改代码/发布/部署不属于默认接入范围。
- 分别报告:配置完成、Runtime 实测情况、公共预览结果、业务端到端是否测试。平台已启用不等于远端已落盘可执行;本机 CLI/Python 成功不能证明成员 Runtime 就绪。
- 输出项目/小队/角色、公共 Skill 版本与来源、具体改动、可用成员与排除原因、缺失条件和证据位置。名单及容量为当次快照,不固化到调度配置。
What ships with it
8 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.
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.
- 6d ago First seen · 47 lines · 81 tokens per session scan A 3d6743ed5f3e
multica-squad-onboard is a skill published in the GitHub repository Songhonglei/better-agent-skills (3 stars, last pushed 6d ago), licensed MIT. It adds 81 tokens to every session and 1,512 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-10-20.
Other skills, from other repositories
test-result-feedback
Close the acceptance loop for a tested change — consume the apc test TierResult, map EACH acceptance criterion to a pass/fail outcome from structured fields (never chat text), attach an evidence ref, and write it back to the task. A SUT red is a finding, never softened to green.
spec-intake
Turn one atomic feature/gap request into a dispatchable task in a single pass — create the task, write SPEC.md (auto-folded into linkedAssetIds server-side), add acceptance criteria, record provenance. Two-part epics are refused, not silently split.
prismer-apple-reminders
Apple Reminders via remindctl: add, list, complete.
github-ops
GitHub CLI for issues, PRs, code search, CI logs, releases, and API queries. Requires gh CLI and auth.
ov-kanban
Work through tasks on a kanban board stored in OpenViking (viking://agent/kanban/ /, one markdown file per task). Use when the user says "ov kanban", "kanban", "看板", asks to put a task on the board, hand off the current work, continue a task another agent started, or run an unattended task loop. A board holds many…
task-forest
Maintains a repo-local task forest or task DAG for the current workspace. Use when the user asks to initialize or update a task forest, close a session, summarize evolving project work, align a request with a global goal, track progress/history/deviations/todos, save or apply a task proposal, or export the…