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/lxyer/multi-agent-collaboration-system/before-devnpx skills add lxyer/multi-agent-collaboration-system --skill before-devgit clone --depth 1 https://github.com/lxyer/multi-agent-collaboration-systemWrote 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/lxyer/multi-agent-collaboration-system/before-dev)<a href="https://agentmods.dev/skills/lxyer/multi-agent-collaboration-system/before-dev"><img src="https://agentmods.dev/badge/skills/lxyer/multi-agent-collaboration-system/before-dev.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 | $0.00068 | $0.00352 |
| Opus 5 | $0.00034 | $0.00176 |
| Sonnet 5 | $0.00014 | $0.00070 |
| Haiku 4.5 | $0.00007 | $0.00035 |
Grade A, and why
before-dev 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.
This is a copy
89% identical to trellis-before-dev — 20 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
Read the relevant development guidelines before starting your task.
Execute these steps:
-
Discover packages and their spec layers:
python3 ./.trellis/scripts/get_context.py --mode packages -
Identify which specs apply to your task based on:
- Which package you're modifying (e.g.,
cli/,docs-site/) - What type of work (backend, frontend, unit-test, docs, etc.)
- Which package you're modifying (e.g.,
-
Read the spec index for each relevant module:
cat .trellis/spec/<package>/<layer>/index.mdFollow the "Pre-Development Checklist" section in the index.
-
Read the specific guideline files listed in the Pre-Development Checklist that are relevant to your task. The index is NOT the goal — it points you to the actual guideline files (e.g.,
error-handling.md,conventions.md,mock-strategies.md). Read those files to understand the coding standards and patterns. -
Always read shared guides:
cat .trellis/spec/guides/index.md -
Understand the coding standards and patterns you need to follow, then proceed with your development plan.
This step is mandatory before writing any 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 · 35 lines · 68 tokens per session scan A 8ba9c9703b6f
before-dev is a skill published in the GitHub repository lxyer/multi-agent-collaboration-system (1 stars, last pushed 4mo ago), licensed MIT. It adds 68 tokens to every session and 352 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 89% identical to trellis-before-dev, differing in 20 lines, and is treated as a copy.
Other skills, from other repositories
workflow-guide
创建、编辑、校验、运行或排查 DeterminFlow 工作流时必须先加载此技能；也适用于任务填参、节点审批、变量传递、网关、执行方案、子流程与工作区覆盖。涉及 Agent 定义、Prompt 模板或 Script Library 的专项设计时，继续加载对应 Core Skill。.
agent-definition-guide
创建、修改、删除或排查 DeterminFlow Agent Definition 时必须加载此技能；也适用于选择 agenttype、最小工具权限、Prompt 模板绑定、模型覆盖、Skill/Rule 可见分组、子会话可用性与 Workflow Agent 节点配置。.
automation-guide
创建、查看、更新、暂停、恢复、立即运行、删除或排查 DeterminFlow Cron 自动化任务时必须加载此技能；也适用于 once/interval/cron 调度、时区、Agent 类型与权限、重复次数、静默输出、失败重试和历史输出核验。.
prompt-template-guide
查看、创建、修改、删除或排查 DeterminFlow Prompt Template 与 system prompt section 时必须加载此技能；也适用于 section 顺序、workflowonly/chatonly、cache break、自定义 templatevariables、系统变量渲染以及 Agent Definition 的 prompttemplate 绑定。.
script-library-guide
创建、更新、删除、引用或排查 DeterminFlow Script Library 脚本时必须加载此技能；也适用于 Workflow Script 节点、inline 与 library 选择、SCRIPT.md、scriptargv、共享 workspace、WFVAR/scriptout 输出协议、Plugin 脚本 owner 冲突与 Task 身份冻结。.
skill-rule-authoring-guide
创建、更新、修补、删除、分组或排查 DeterminFlow Skill 与 Rule 时必须加载此技能；也适用于判断知识应进入 Skill、强制约束应进入 Rule、运行时 data/skills 与版本化 Core Skills 的边界、Plugin 只读资源以及幽灵配置清理。.