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/approaching-ai/aima/claude-mdgit clone --depth 1 https://github.com/Approaching-AI/AIMAWrote 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/approaching-ai/aima/claude-md)<a href="https://agentmods.dev/instructions/approaching-ai/aima/claude-md"><img src="https://agentmods.dev/badge/instructions/approaching-ai/aima/claude-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 | $0.09991 | $0.09991 |
| Opus 5 | $0.04995 | $0.04995 |
| Sonnet 5 | $0.01998 | $0.01998 |
| Haiku 4.5 | $0.00999 | $0.00999 |
Grade A, and why
AIMA CLAUDE.md scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
# 3. 直接 curl 测试（/stats 豁免, 其他必须带 device_id）： How it starts
The opening of the file, as written. The whole thing — 572 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AIMA — Claude Code Development Guide
What Is This
AIMA (AI-Inference-Managed-by-AI): a Go binary that manages AI inference on edge devices. It detects hardware, resolves optimal configs from a YAML knowledge base, generates K3S Pod YAML, and exposes a documented MCP tool surface for AI Agents to operate everything. This project is 100% developed by Claude Code.
Tech: Go (no CGO), K3S, HAMi, SQLite (modernc.org/sqlite), MCP (JSON-RPC 2.0), Cobra CLI, log/slog.
Design docs: design/ARCHITECTURE.md (system architecture), design/PRD.md, design/MRD.md.
====== Central Knowledge Server 已拆分 ======
internal/central/和cmd/central/已拆分至独立 repo，本 repo 中不再包含。
| 说明 | |
|---|---|
| 独立 repo | github.com/Approaching-AI/aima-central-knowledge (private) |
| 个人 fork | github.com/skyguan92/aima-central-knowledge (private) |
| 本地路径 | /Users/jguan/projects/aima-central-knowledge |
| API 契约 | aima-central-knowledge/api/openapi.yaml (OpenAPI 3.1) |
生产部署
Central 已部署到 aima-oversea 服务器，作为 aima-service docker-compose 中的独立容器。
| 项目 | 说明 |
|---|---|
| 生产 URL | https://aimaservice.ai/central |
| 默认 endpoint | Edge 代码默认使用此 URL（defaultCentralEndpoint in tooldeps_integration.go） |
| 覆盖方式 | system.config set central.endpoint <url> |
| Gateway 代理 | Rust gateway /central/* → strip 前缀 → http://central:8081 |
| 数据库 | PostgreSQL aima_central database（与 platform 隔离） |
| 升级 Central | cd /root/aima-central-knowledge && git pull && docker build -t aima-central:latest . && cd /root/aima-service && docker compose -f docker-compose.prod.yml up -d central |
| 升级 Gateway | cd /root/aima-service && git pull && docker compose -f docker-compose.prod.yml build gateway && docker compose -f docker-compose.prod.yml up -d gateway |
| 服务器 Git | aima-oversea 已配 SSH key（aima-oversea-deploy），两个 repo 均可 git pull |
开发警告
- 不要在本 repo 创建
internal/central/或cmd/central/— 已迁出 - 不要在本 repo 修改 Central Server 的逻辑 — 去
aima-central-knowledgerepo 改 - Edge→Central 通信仅通过 HTTP REST — 见
cmd/aima/tooldeps_integration.go，用map[string]any构造 payload，不 import central 包 - 修改 sync/ingest 的 JSON 字段时，必须同步检查
aima-central-knowledge/api/openapi.yaml的契约定义 - 本 repo 的
tooldeps_integration.go中的 normalization 函数（normalizeCentralAdvisory等）是 Edge 侧的 JSON 适配层，修改前需确认 Central 端对应端点的 response schema
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 · 572 lines · 9,991 tokens per session scan A c49609153d67
AIMA CLAUDE.md is an instructions file published in the GitHub repository Approaching-AI/AIMA (16 stars, last pushed 2d ago), licensed Apache-2.0. It adds 9,991 tokens to every session, about $0.0500 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
openclaw-operator CLAUDE.md
Claude Code instructions for paperclipinc/openclaw-operator, covering claude.md — openclaw kubernetes operator, project overview, commands, architecture and reconciliation rules.
bex CLAUDE.md
Claude Code instructions for bex-co/bex, covering claude.md, repo map, commands, local cluster workflow and environment variables.
kubara AGENTS.md
AGENTS.md instructions for kubara-io/kubara, covering ai agent context, scope, product intent (stable), truth hierarchy and reference map.
deltallm AGENTS.md
AGENTS.md instructions for deltawi/deltallm, covering repository instructions, required first step and precedence and maintenance.
in-cluster-observability AGENTS.md
AGENTS.md instructions for gke-labs/in-cluster-observability, covering agents.md, current state, where to read what, issue and pr tracking and branch and pr workflow.
yayamlls AGENTS.md
AGENTS.md instructions for home-operations/yayamlls, covering agents.md: yayamlls, working in this repo: ai usage, commits, and safety, baseline, project layout and errors.