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 instructions/bb4407777/areco/agents-mdgit clone --depth 1 https://github.com/bb4407777/arecoWrote 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/bb4407777/areco/agents-md)<a href="https://agentmods.dev/instructions/bb4407777/areco/agents-md"><img src="https://agentmods.dev/badge/instructions/bb4407777/areco/agents-md.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 | $0.01350 | $0.01350 |
| Opus 5 | $0.00675 | $0.00675 |
| Sonnet 5 | $0.00270 | $0.00270 |
| Haiku 4.5 | $0.00135 | $0.00135 |
Grade A, and why
areco 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 3d 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md（areco 仓内 agent 行为约束）
本仓由多 agent（Claude Code / Codex / WorkBuddy / Kimi CLI …）接力开发。 每条规则都踩过坑，别删，只增补。
交接纪律（2026-07-19 定）
- 每棒收尾前必须
git commit——工作区不过夜。攒一天 20+ 文件未提交， 出了回归无法归因是谁哪一棒引入的（当日桥水绑定/红绿灯两起回归即教训）。 - 行为变更必须拿真实数据自验再交接：跑一遍真实看板/真实 transcript 目录
（
~/.claude/projects、~/.codex/sessions、~/.codebuddy/projects）， 单测全绿不算完——严格绑定器单测全过、一碰真实软链双候选就拒绑即教训。 - 交接文件（
data/handoff/）写清：本棒 commit 范围、改了什么行为、 有什么没验证到。 - 每个新功能/修复 = 一份独立工程档案（2026-07-27 高律师定）：除「交接」用途外，
功能/修复本身要有一份独立档案
data/handoff/YYYY-MM-DD-<主题>.md，写清根因/动机、 改了哪些代码（文件:行）、怎么验证（测试/实测）、回滚方法、部署门槛、未办/风险。 下次同类故障先查档案 +git log，不从零排查——「不知道哪次修改把原有功能改没了」 即靠此追溯。无档案 = 没干完。 示范：data/handoff/2026-07-27-claude-transcript-binding-fix.md。
本仓操作
- 桌面/手机双端同步上线（2026-07-22 高律师定）：任何 UI 功能改动必须先想清 两端的落点——桌面侧栏（SessionSidebar）与手机看板（DashboardView 卡片流）是 两套组件，改一套不等于另一套生效。共用逻辑抽成公共模块（如 utils/sessionGroups）， 不许复制两份漂移；交付前两端各过一遍。
- 测试：
npm test（tsx --test，含服务端/客户端/共享层）；类型检查即构建前置。 - 部署：
./start.sh restart（launchd com.areco 已接管，脚本自动转发 kickstart）； 生产 8790 可能有用户在舱内开着的会话，重启前先/api/sessions看一眼。 - shell 脚本：macOS 系统 bash 3.2 下
$VAR后紧跟中文/全角字符会把首字节 粘进变量名（set -u 直接炸）——变量后接 CJK 一律写${VAR}。 config.json、data/、bin/是 gitignore 的本机私有物，不入仓。
复用模式清单（2026-07-24 高律师定：一套更换，改一处必同步）
这些是仓里已经沉淀的共用模块/版式约定。新功能先查这里有没有现成的， 不许复制第二份；改版式/判断逻辑时按「同步面」整组改，漏一处就是回归。
消息气泡版式（三处同构，改版式必须整组改）
- 统一结构：
.msg-meta（发送者名/模板名，泡泡上方）→.bubble→.msg-foot（左「📋 复制 / ✓ 已复制」，右完整时间fmtFullTime）。 - 落点：
ChatMessage.vue（对话模式 + 历史日志页共用组件，模板名走agentLabelprop） 与GroupChatView.vue消息块（项目，self 消息 foot 整体右对齐）。
utils/format.ts（会话展示的判断与格式化，唯一出处）
templateLabel/templateColor：模板名与颜色（模板已删有兜底）。chatCapable/sessionEntryPath：会话有无对话视图、按偏好算落点路由—— 看板点卡片、侧栏、新建会话三处共用，禁止在调用处重写判断。fmtFullTime：气泡右下角完整时间，两端统一格式。trafficColor/statusTagText：红绿灯与状态文案。
其他共用件
utils/sessionGroups.ts：桌面侧栏与手机看板的项目分组规则（双端同源）。utils/clipboard.tscopyPlainText：双通道复制（气泡/项目消息同用）。utils/filelinks.ts+FilePreview.vue：正文里文件路径 → chip 预览。stores/ui.ts：本机 UI 偏好（localStorageareco-ui）。加新偏好 = 加字段 +DEFAULT_PREFS+persist()+ setter，设置页用「对话模式」卡片的pref-row样式挂开关。SpawnDialog.vue：spawned事件必须传完整 SessionSummary——store 靠 ws 推送， spawn 返回瞬间byId查不到新会话（2026-07-23 落点判断失效即此坑）。- 组件：
TypingIndicator/ViewModeSwitch/PromptBar/MobileKeyBar全局复用。
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.
- 3d ago First seen · 61 lines · 1,350 tokens per session scan A 7855ab01b6be
areco AGENTS.md is an instructions file published in the GitHub repository bb4407777/areco (2 stars, last pushed 22d ago), licensed Apache-2.0. It adds 1,350 tokens to every session, about $0.0068 per session on Opus 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 2026-08-31.
Other instructions, from other repositories
CodeWhale CLAUDE.md
Claude Code instructions for Hmbown/CodeWhale, a project described as: Open-source coding agent for your terminal, built in Rust and on a journey of continuous community improvement. Issues and PRs welcome.
alook AGENTS.md
Instructions for alookai/alook, covering alook, navigation, must, release — unified version bump and e2e ui (browser tests).
parallel-code CLAUDE.md
Instructions for johannesjo/parallel-code, covering parallel code, stack, commands, project structure and conventions.
cezar AGENTS.md
Instructions for open-mercato/cezar, covering agents.md — working in this repository, zero config, changing a mechanism that already works, the http api and repository layout.
senpi AGENTS.md
Instructions for code-yeongyu/senpi, covering senpi repository guide, mandatory execution protocols — non-negotiable, protocol 1 — explicitly requested modifications, protocol 2 — user-requested pr reviews and structure.
crewplane GEMINI.md
Instructions for crewplaneai/crewplane, a project described as: Run reviewable, resumable coding-agent workflows across Claude Code, Codex, Gemini, GitHub Copilot CLI, or any CLI. You define the stages in Markdown; Crewplane runs the workflow, agents do the work, and every handoff stays on disk.