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 jianchen08/Agent-os-open --skill credit-delegationgit clone --depth 1 https://github.com/jianchen08/Agent-os-openWrote 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/jianchen08/agent-os-open/credit-delegation)<a href="https://agentmods.dev/skills/jianchen08/agent-os-open/credit-delegation"><img src="https://agentmods.dev/badge/skills/jianchen08/agent-os-open/credit-delegation/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/jianchen08/agent-os-open/credit-delegation"><img src="https://agentmods.dev/badge/skills/jianchen08/agent-os-open/credit-delegation.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 | $0.00098 | $0.01384 |
| Opus 5.5 | $0.00039 | $0.00554 |
| Sonnet 5.5 | $0.00020 | $0.00277 |
| Haiku 4.5 | $0.00010 | $0.00138 |
Grade A, and why
额度代理方法论 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 28d 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
额度代理方法论（Credit Delegation）
本技能是流程指引，不是逐条打勾清单：按场景判断使用，遇不适用情况保持裁量，不机械执行。
为什么需要方法论
很多 AI 工具送额度、闭源、无接口——computer use 是唯一入口。但裸用 computer use 的 token 成本集中在等待：目标工具干活是分钟级，若 LLM 每 30 秒 Snapshot 轮询，每次消耗（UIA 树/视觉 token）× 几十次 = 轻松烧掉十万级 token，而真正派发只需十几次调用。方法论的全部目标：派发成本固定且低，等待成本为零，收割只读一次。
接口优先级（决策树，computer use 永远是最后手段）
- 原生接口：CLI / IPC / URL scheme / 本地 API —— 有就直接用（一次 bash 调用 vs 十几次视觉调用）。
- 文件投递：目标工具支持打开文件/监听目录（如拖拽区、自动导入）→ 写文件触发。
- computer use 派发：以上皆无的闭源工具，走本方法论三阶段。
三阶段协议
阶段一：一次性派发（成本固定，≈10-20 次工具调用）
- 任务简报自足：目标+验收标准+约束+产出落盘路径一次写全。目标工具在它的额度里自主干活——不发碎对话，不做交互式来回（每次来回都是一轮 AgentOS token）。
- 产出落文件（本方法论的核心杠杆）：简报末尾必须约定"完成后把结果摘要/产物写入
<投递目录>/<约定文件名>"。这把后续的"读屏"降级成"读文件"——读屏一次几千 token，读文件几乎免费。 - 投递目录约定：
%USERPROFILE%\agentos_dispatch\（两方都能写的共享路径，按任务名建文件）。 - 派发动作本身按应用档案（见下）执行：聚焦 → 定位输入框 → 输入 → 发送 → 回读确认。
阶段二：失聪等待（零 token，时长无关）
派发确认后 LLM 立即收工——向用户报告"已派发，预计 X 分钟，完成后我会汇报"，然后结束本轮。等待由非 LLM 机制承担，按廉价程度选信号：
| 信号 | 检查方式 | 成本 |
|---|---|---|
| 结果文件出现 | 触发器定时 file_read/bash 查文件 | ≈0 |
| 进程/窗口标题变化 | bash 查进程名或窗口标题 | ≈0 |
| 剪辑板/剪贴目录 | 同上 | ≈0 |
| UIA 文本标记 | Snapshot（限 region，避免视觉） | 低，仅醒检时 |
用 trigger_setup 注册定时触发（间隔=任务预估时长的 1/2，不小于 2 分钟）唤醒自己；每次唤醒先查廉价信号，信号未出现就直接结束轮次等下次触发（不 Snapshot、不等待、不占用上下文）。
阶段三：一次收割
完成信号出现后：读结果文件（首选）→ 提炼回用户。仅当目标工具不产文件时，才做一次最终 Snapshot/截图读屏收割。收割后主动清理投递文件（防下次误读旧结果）。
应用档案（App Profile）
每个目标工具一份档案（技能目录），内容五要素：窗口匹配规则 / 输入定位方式 / 发送动作 / 完成信号 / 结果契约。档案里未记录的 UI 细节以首跑 Snapshot 实测为准并把实测锚点沉淀回档案。现有档案：
skills/zcode-dispatch/SKILL.md（ZCode）skills/workbuddy-dispatch/SKILL.md（WorkBuddy）
新增目标工具 = 照五要素写一份档案，不改方法论。
失败与安全
- 派发前回读输入内容（防误发）；剪贴板粘贴先告知覆盖。
- 目标工具忙/排队：确认入队后直接进入失聪等待——不要在它排队期间反复 Snapshot。
- 目标工具的审批卡/危险按钮：不代批，回报告知。
- 触发器多次唤醒信号仍未出现（超过任务预估 3 倍时长）：停止等待，如实报告"目标工具未在预期时间完成"，不编造结果。
Token 经济学（为什么这样做）
| 模式 | 派发 | 等待 20 分钟 | 收割 | 总计 |
|---|---|---|---|---|
| 裸 computer use 轮询 | ≈15k | 每 30s 一次快照树/视觉 ≈3-8k/次 ≈ 120-320k | ≈5k | ≈140-340k |
| 本方法论 | ≈15k | 0（触发器+文件信号） | ≈5k | ≈20k |
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.
- 28d ago First seen · 69 lines · 98 tokens per session scan A f9abc3e6dee9
额度代理方法论 is a skill published in the GitHub repository jianchen08/Agent-os-open (7 stars, last pushed 9d ago), licensed Apache-2.0. It adds 98 tokens to every session and 1,384 once invoked, about $0.0004 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 2026-09-19.
Other skills, from other repositories
background-task
Add or modify work that runs outside the request/response cycle — emails, document ingestion, webhooks, cleanups, scheduled jobs. Use when something is slow or fire-and-forget, or when adding a periodic/cron task. This project's queue is {{ cookiecutter.backgroundtasks }}.
agent-tool
Add a new tool/function the AI agent can call (e.g. look something up, hit an external API, perform an action). Use when extending the assistant's capabilities, wiring a new function into the agent, or when the model needs a new action. This project uses {{ cookiecutter.aiframework }}.
frontend-feature
Build a new page, view, or data-driven feature in the Next.js frontend. Use when adding a route under the dashboard/marketing area, wiring UI to a backend endpoint, adding client state, or creating a localized page. Covers App Router, data fetching, Zustand stores, and i18n.
rag-knowledge
Work with the RAG knowledge base — ingest documents, run semantic search, manage collections, or add a sync source/connector (Google Drive, S3). Use when populating or debugging the knowledge base, tuning retrieval, or adding a new document source. This project uses {{ cookiecutter.vectorstore }} + {{…
alembic-migration
Create, review, and apply database schema changes with Alembic. Use whenever a SQLAlchemy model is added or changed, a column/index/constraint needs to change, or a data backfill is required — anything that alters the PostgreSQL schema.
channel-bot
Work with messaging-channel bots (Telegram / Slack) — register a bot, route inbound messages through the AI agent, handle webhooks vs polling, or add a new channel adapter. Use when wiring chat into a messaging platform or debugging bot delivery.