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/alice-space/alice/agents-mdgit clone --depth 1 https://github.com/Alice-space/aliceWrote 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/alice-space/alice/agents-md)<a href="https://agentmods.dev/instructions/alice-space/alice/agents-md"><img src="https://agentmods.dev/badge/instructions/alice-space/alice/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 | $0.01481 | $0.01481 |
| Opus 5 | $0.00740 | $0.00740 |
| Sonnet 5 | $0.00296 | $0.00296 |
| Haiku 4.5 | $0.00148 | $0.00148 |
Grade A, and why
alice 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 — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS Collaboration Guide (Alice)
This file is the canonical collaboration and execution standard for contributors in this repository.
Scope
This standard applies to all human and AI contributors in this repository.
Repo-Local Skills First
- When working inside the Alice repository, treat repo-local skills under
.agents/skills/...as the default execution path for repository operations that already have a bundled workflow. - In particular, if the task is to update Alice itself, promote a release, merge
dev -> main, wait for GitHub Release artifacts, or run the post-release self-update flow, use the repo-local GitHub skill first:- read
.agents/skills/github/SKILL.md - run
.agents/skills/github/scripts/github.sh
- read
- Do not bypass the repo-local skill with ad-hoc
gh, installer, or release commands unless the skill is missing or clearly blocked.
1. Decision Discipline
- Facts first, then inference, then conclusion.
- Any diagnosis or proposal must explicitly separate:
Facts: command outputs, logs, file references.Inference: interpretation based on facts.Decision: the action to take.
- Do not make deployment/runtime claims without evidence.
2. Change Scope Rules
- One commit, one primary goal.
- Split refactor and behavior change:
- First commit: behavior-preserving refactor.
- Second commit: behavior change (if needed).
- Do not mix unrelated files in one commit.
3. Pre-Change Checklist
Before coding, define:
- Objective and non-objective.
- Expected behavior invariants (what must not change).
- Risks and rollback path.
- Acceptance criteria (tests/build/runtime checks).
If task involves runtime/deploy troubleshooting, collect facts first:
# default installer unit; if installed with --service, replace alice.service accordingly
journalctl --user-unit alice.service -n 200 --no-pager
journalctl --user-unit alice.service --since "30 min ago" --no-pager
If task involves isolated debugging or temporary rerun runtimes:
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 · 163 lines · 1,481 tokens per session scan A 4dad18ec370a
alice AGENTS.md is an instructions file published in the GitHub repository Alice-space/alice (5 stars, last pushed 29d ago), licensed MIT. It adds 1,481 tokens to every session, about $0.0074 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
ds4-control CLAUDE.md
Instructions for notatestuser/ds4-control, covering ds4 control — project guide for claude, purpose, deepseek v4 preview maintenance, stack and dev workflow.
carboncode AGENTS.md
Instructions for Yapie0/carboncode, covering agents.md, project context, current status, product direction and chosen base.
chatgpt-vue3-light-mvp AGENTS.md
Instructions for pdsuwwz/chatgpt-vue3-light-mvp, a project described as: 💭 一个可二次开发 Chat Bot 单轮对话 Web 端 MVP 原型模板, 基于 Vue 3, Vite8, TypeScript, Naive UI, Pinia(v3), UnoCSS 等主流技术构建, 🧤简单集成大模型 API, 采用单轮 AI 问答对话模式, 每次提问独立响应, 无需上下文, 支持 SSE 打字机效果流式输出, 集成 markdown-it Mermaid/KaTex/LaTex 公式高亮预览, 星火, 智谱, 硅基流动, Deepseek…
carboncode CLAUDE.md
Instructions for Yapie0/carboncode, covering claude.md, canonical rules (authoritative — follow these), dev workflow, architecture map (src/) and conventions.
DeepCopilot copilot-instructions.md
Instructions for deep-copilot/DeepCopilot, covering deepcopilot 项目级 copilot / ai 审核指引, 项目概述, 技术栈, 审查时必须关注的红线 and 代码风格.
dsh-oomol AGENTS.md
Instructions for oomol-lab/dsh-oomol, a project described as: OOMOL Connector for DeepSeek Harness—discover connected apps and execute Actions through progressive MCP discovery without exposing provider credentials.