Borrowing it
Nothing to install: this file belongs to ccch1mneyyy/working-activity. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/ccch1mneyyy/working-activity/main/AGENTS.mdgit clone --depth 1 https://github.com/ccch1mneyyy/working-activityWrote 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/instructions/ccch1mneyyy/working-activity/agents-md)<a href="https://agentmods.dev/instructions/ccch1mneyyy/working-activity/agents-md"><img src="https://agentmods.dev/badge/instructions/ccch1mneyyy/working-activity/agents-md/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/instructions/ccch1mneyyy/working-activity/agents-md"><img src="https://agentmods.dev/badge/instructions/ccch1mneyyy/working-activity/agents-md.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 | $0.00697 | $0.00697 |
| Opus 5.5 | $0.00279 | $0.00279 |
| Sonnet 5.5 | $0.00139 | $0.00139 |
| Haiku 4.5 | $0.00070 | $0.00070 |
Grade A, and why
working-activity AGENTS.md 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 2mo 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.
What it actually says
working-activity 项目规则
用途
"工作状态行"扩展的开源仓库,一个仓库维护两个平台适配:
- pi 版:源码
extensions/index.ts(无构建,pi 直接加载 TS),发布 npm 包pi-working-activity供pi install npm:pi-working-activity - DSH 版:插件在
packages/activity/working-activity/(cordis 宿主插件 +src/client/Web slot 插件),发布 npm 包dsh-working-activity供dsh plugin --profile <p> add dsh-working-activity
pi 版开发约定
- 唯一源码:
extensions/index.ts(无构建,pi 直接加载 TS) - 本机活动副本:
C:\Users\17481\.pi\agent\extensions\working-activity.ts,改完同步 +/reload - 语法校验:
node --experimental-strip-types(import 包解析失败是预期) - 调试:
working-activity.json里debugLog: true
DSH 版开发约定
- 插件源码:
packages/activity/working-activity/src/(host 插件)+src/client/(Web slot 插件) - 构建:
cd packages/activity/working-activity && pnpm install && pnpm run build(build:client出浏览器 bundle) - 测试:
pnpm test(vitest,依赖已发布到 npm 的官方@deepseek-ai/dsh-*@0.1.0-rc.6包,无需源码 workspace) - 自挂载 bundle:
cordis.patch.yml,dsh plugin add自动装配,无需手动挂载 - Web 端需 runtime 补丁:
patches/webui-working-activity.patch(应用到官方 rc.6 源码仓库,git apply --check验证) - 完整文档:
docs/dsh-working-activity.md(原 dsh 仓库 README)
文案
- 开源文案(README + 状态栏短语池)优先用 DeepSeek 官方 V4 Pro 生成
- 生成脚本:
.local/gen-with-ds.cjs/.local/gen-phrases.cjs/.local/apply-phrases.cjs(不入库) - 输出缓存:
.local/ds-gen/(不入库) - 风格:短、口语、俏皮、有活人感;游戏梗仅 rare 池;允许 deadpan 英文
发布
- pi 版:semver 功能 minor,修 bug patch;发布前
npm view pi-working-activity确认包名;在仓库根目录npm publish - DSH 版:在
packages/activity/working-activity/内npm publish;发版前确认package.json的 version 与 repository 指向本仓库 - 两个 npm 包名不要改:
pi-working-activity被 pi 用户直接安装,dsh-working-activity被 dsh-cc-tui 依赖
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.
- 2mo ago First seen · 32 lines · 697 tokens per session scan A a801e49e2b61
working-activity AGENTS.md is an instructions file published in the GitHub repository ccch1mneyyy/working-activity (666 stars, last pushed 19d ago), licensed MIT. It adds 697 tokens to every session, about $0.0028 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 2026-08-30.
working-activity AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| working-activity AGENTS.mdccch1mneyyy/working-activity | Instructions file | 666 | 19d ago | MIT | A | 697 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |