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/maimorylab/bootagent/agents-mdgit clone --depth 1 https://github.com/MaimoryLab/BootAgentWhat 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 | $0.02445 | $0.02445 |
| Opus 5 | $0.01222 | $0.01222 |
| Sonnet 5 | $0.00489 | $0.00489 |
| Haiku 4.5 | $0.00245 | $0.00245 |
Grade A, and why
BootAgent 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 yesterday.
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 — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.
BootAgent 开发约定
当前代码线是 Go/Wails 稳定化主线。不要在本文硬编码发布版本;发布版本以 Git tag、
GitHub Release 和构建工作流注入的版本为准。唯一产品入口是
cmd/bootagent-desktop,React 只能通过生成的 Wails bindings 调用后端。
目录
internal/app:Status、Provider、Agent、Profile、Runtime、DesktopAgent、安装、 启动、设置和更新等用例,以及统一的写操作锁。internal/catalog:嵌入的agents.lock.json、providers.lock.json、runtimes.lock.json,以及内置 Provider 目录。internal/config:TOML/JSON/JSONC 适配器、配置发现和 golden fixtures。internal/install:默认安装最新版或可选精确版本的 Agent 包、registry 选择、 Node.js/uv runtime 引导(下载、校验、解压和 PATH 更新),以及 Aider 的 Python 管理边界。internal/profile与internal/securefs:Profile、密钥、备份、权限和原子写入。internal/mcp:MCP 规范化模型、秘密处理、Registry 私有存储、导入导出,以及 Claude Code、Codex、OpenCode、Kilo CLI 和 Hermes 原生配置适配器。internal/binding:React 与 Go 之间唯一的边界。Services聚合 Status、Provider、 Agent、Profile、Runtime、DesktopAgent、Transfer 和 MCP 八个服务;UpdateService 在桌面 入口中单独注册。这里的 DTO 发生变化时,必须重新生成frontend/bindings,并同步frontend/src/backend/wails.ts与frontend/src/types/api.ts。cmd/bootagent-desktop:Wails 桌面入口。frontend/bindings:Wails 生成文件,禁止手工编辑。
cmd/bootagent-release、cmd/bootagent-rc 和 cmd/bootagent-provider-smoke 已在
23805b0 删除,其职责转移到 .github/workflows/build-artifacts.yml。历史文档中
出现这些命令只代表背景,不是可执行指令。
公共站点已迁移到
MaimoryLab/BootAgent-site,本仓库不再
包含 site/。站点把发布 tag 中的 agents.lock.json 和 providers.lock.json 复制到
自己的 data/ 目录;发布完成后,构建工作流会通知站点刷新。直接修改本仓库的
main 不应立即改变站点,因为站点描述的是已发布版本支持的内容。
providers.lock.json 是内置 Provider endpoint、fallback model 和公共站点商业披露
字段的唯一事实来源。用户 Provider 与内置 Provider 覆盖项保存在
~/.bootagent/providers.json。
本地命令
go test ./...
go test -race ./...
go vet ./...
python3 -m unittest scripts/test_generate_third_party_licenses.py
python3 scripts/generate_third_party_licenses.py --check
python3 scripts/check-docs.py
cd frontend
pnpm install --frozen-lockfile
pnpm run test
pnpm run build
pnpm run test:e2e
.github/workflows/ci.yml 在 pull request 与 main push 上运行四组门禁:Go、
Frontend、Docs 和 Release compliance。Go 门禁还运行 staticcheck。
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.
- yesterday First seen · 173 lines · 2,445 tokens per session scan A 04157c0043c6
BootAgent AGENTS.md is an instructions file published in the GitHub repository MaimoryLab/BootAgent (96 stars, last pushed 4d ago), licensed Apache-2.0. It adds 2,445 tokens to every session, about $0.0122 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 2026-08-30.
Other instructions, from other repositories
clawdi AGENTS.md
Instructions for Clawdi-AI/clawdi, covering clawdi, oss boundary, repository map, local end-to-end and verification.
clawdi CLAUDE.md
Instructions for Clawdi-AI/clawdi: The canonical repo-wide agent instructions live in AGENTS.md.
zeroclaw AGENTS.md
Instructions for zeroclaw-labs/zeroclaw, covering agents.md - zeroclaw, single source of truth, safety and privacy, working rules and user-facing text.
hermes-webui AGENTS.md
Instructions for nesquena/hermes-webui, covering agent instructions for hermes webui, read first, onboarding and reinstall support, contribution style and before you open a pr — the change guidelines.
manifest CLAUDE.md
Instructions for mnfst/manifest, covering manifest development guidelines, what manifest is, important: cloud mode always, 1. ensure the postgresdb container is running and 2. create a pristine database with a unique name.
zeroclaw CLAUDE.md
Instructions for zeroclaw-labs/zeroclaw, covering claude.md — zeroclaw (claude code), claude code settings, hooks and slash commands.