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/menfre01/waveloom/agents-mdgit clone --depth 1 https://github.com/Menfre01/waveloomWrote 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/menfre01/waveloom/agents-md)<a href="https://agentmods.dev/instructions/menfre01/waveloom/agents-md"><img src="https://agentmods.dev/badge/instructions/menfre01/waveloom/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 | $0.03069 | $0.03069 |
| Opus 5 | $0.01535 | $0.01535 |
| Sonnet 5 | $0.00614 | $0.00614 |
| Haiku 4.5 | $0.00307 | $0.00307 |
Grade A, and why
waveloom 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 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.
How it starts
The opening of the file, as written. The whole thing — 204 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Waveloom
终端编码代理（Go 实现），帮助用户编写、重构、调试和探索代码。
项目概要
- 语言：Go 1.25+
- LLM:DeepSeek(默认)/ Kimi / OpenAI,通过
llm.Client接口 + adapter 适配,支持/provider运行时切换 - TUI：Bubble Tea v2 + Glamour Markdown 渲染 + Lipgloss 样式
- LSP:
edit/write后自动运行 LSP diagnostics 验证(内置 gopls / rust-analyzer / typescript-language-server / clangd),未安装时静默跳过;构建工具(go build / npx tsc / cargo build / make)兜底 - 构建：
make build/make test/make run
cmd/waveloom/ CLI 入口(main, config, runner, tui)
pkg/
acp/ ACP v1 Agent 端(JSON-RPC over stdio),对接 cc-connect/Zed/JetBrains 等客户端
agentloop/ Think-Act-Observe 循环(Run → <-chan StepEvent;一次 Run = 一个 turn)
bash/ Shell 命令 AST 解析与危险命令安全检测
compaction/ 四级水位线上下文压缩(Snip/Prune/Summarize)
environment/ 工具链探测
filehistory/ 文件历史备份、快照、回退
hook/ Hook 系统(PreToolUse/PostToolUse 等事件,settings.json 配置外部脚本)
llm/ LLM Client(DeepSeek/Kimi/OpenAI adapter、流式、重试)
logging/ 日志
lsp/ LSP 诊断客户端(edit/write 后自动验证)
mcp/ MCP 客户端(配置、传输、工具代理)
memory/ AGENTS.md 层级加载
pathutil/ 路径工具
permission/ 权限守门人(规则引擎、路径/命令安全)
plugin/ 插件发现
pricing/ LLM token 计费(CNY/USD 双币种、模型级增量计价)
reference/ @ 文件引用展开
session/ 跨轮次消息历史与持久化(PrepareRun / CompleteRun,JSONL)
shellutil/ Shell 命令处理共享实用函数(供 tool/skill 复用)
skill/ Skill 系统(.claude/skills/ 与 .waveloom/skills/ 双路径加载)
slashcommand/ / 命令面板
subagent/ 子代理(Fork/Cold/Explore)
task/ 后台任务管理
todo/ Todo 状态管理
tool/ 工具系统(内置工具,TypedTool[P] 泛型接口)
specs/ 各组件规格书(修改前先阅读;内部文档,不纳入公开仓库)
编码规范
- 跨平台兼容:所有代码必须同时兼容 Windows / Linux / Darwin 三平台:
- 文件系统操作优先使用
filepath.WalkDir、os.ReadDir等标准库,禁止直接调用外部命令(如find、ls、dir) - 路径拼接必须使用
filepath.Join,分隔符使用filepath.Separator,禁止硬编码/或\ - 外部 API 调用前确认第三方包是否声明了跨平台支持,必要时用
runtime.GOOS条件编译
- 文件系统操作优先使用
代码审查
- 完成较大的代码改动(涉及 3+ 文件或 50+ 行变更)后,自动启动代码审查,审查维度包括:逻辑正确性、跨平台兼容、边界条件、安全风险
- 审查完成后将结果直接反馈给用户,无需用户主动要求
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 · 204 lines · 3,069 tokens per session scan A 102e6ffc5d18
waveloom AGENTS.md is an instructions file published in the GitHub repository Menfre01/waveloom (130 stars, last pushed yesterday), licensed Apache-2.0. It adds 3,069 tokens to every session, about $0.0153 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
microNeo AGENTS.md
Instructions for sollawen/microNeo, covering 基本规则, debug and 核心概念.
terminal AGENTS.md
Instructions for browser-use/terminal, covering agent notes, rust rewrite verification loop and terminal ui testing standard.
zot AGENTS.md
AGENTS.md instructions for patriceckhart/zot, covering working agreement for zot, product intent, starting a task, code ownership map and correctness contracts.
Tianshu-harness CLAUDE.md
Claude Code instructions for huiliyi37/Tianshu-harness, covering 天枢 (tianshu) / rivet, build & test, architecture, conventions and known constraints.
pvetui AGENTS.md
AGENTS.md instructions for devnullvoid/pvetui, covering agent instructions, initial setup, development workflow, quick reference and code quality standards.
hex1b AGENTS.md
Instructions for mitchdenny/hex1b, covering ai coding agent guidelines for hex1b, 🛠️ available skills, 📋 project overview, key technologies and repository layout.