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/moonandecho/origin-memorycore/agents-mdgit clone --depth 1 https://github.com/moonandecho/origin-memorycoreWhat 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 | $0.00690 | $0.00690 |
| Opus 5 | $0.00345 | $0.00345 |
| Sonnet 5 | $0.00138 | $0.00138 |
| Haiku 4.5 | $0.00069 | $0.00069 |
Grade A, and why
origin-memorycore 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.
What it actually says
AGENTS.md — origin-memorycore
项目定位
MemoryCore —— LLM Agent 记忆层治理方案(MIT 开源版)。
- 治理层 = MemoryCore(本仓库), 存储层 = Mnemosyne(远端), 上层 = Hermes/cron。
- 核心机制: 热层/冷层分层、写入路由、语义去重、容量溢流、回收站兜底、双通道召回。
开发约定(必须遵守)
- git commit 随时提交 — 每完成一个逻辑阶段就
git add -A && git commit -m "<描述>"。多次小提交优于一次大提交, 可追溯。禁止攒一堆改动一次性提交。 - 测试必须真实落盘 — 禁止只跑内联
python3 -c不写文件。测试文件要进 git、可复现、有断言 (git show <commit> --stat必须能看到测试文件)。 - 测试隔离生产路径 — 模块级
Path(...)默认值在 import 时绑定真实路径, 测试必须用 tempfile 覆盖后再写; 跑完检查生产文件无污染 (如 trash.json 不得出现 mock id)。 - 中英 README 同步 — 改 README.md 必须同步更新 README.zh-CN.md, 不得只改英文。
- 隐私红线 — 代码/文档/commit message 中不得出现真实本地路径、域名、IP、API key、token。发布前全仓 grep 清零。
- 外部依赖必须实测 — 涉及 ollama/embedding/远端服务的代码, 必须实测"依赖不可达"场景 (空缓存 + 断网/端点不可达), 不能只验 import 通过; "返回成功但数据坏了"比直接报错更危险, 要有零向量/空结果守卫。
- 兼容性声明必须实测 — "import 可过/无回归"要在实际解析出的依赖环境里跑通才算数, 不凭逻辑推断; 裸
>=依赖约束可能拉到破坏性新版本, 需检查。 - 验证再告知 — 改完必须确认文件已更新/测试已跑/效果已生效, 才能说"完成"。
常用命令
- 测试:
python -m pytest tests/ -q - 语法检查:
python -m py_compile <file>或直接 import 冒烟 - 发布前隐私扫描: 全仓 grep 路径/域名/IP/key/token 模式, 结果为零才算干净
工作流
- 修改仓库代码时, 每阶段 commit 后保留在服务器 (不 push), 经审查后再推 GitHub。
- 本文件与核心规则 (Hermes pi-workflow-rules) 冲突时, 以本文件为准 (项目级高于全局)。
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 · 30 lines · 690 tokens per session scan A 2df5fc709f51
origin-memorycore AGENTS.md is an instructions file published in the GitHub repository moonandecho/origin-memorycore (1 stars, last pushed 5d ago), licensed MIT. It adds 690 tokens to every session, about $0.0034 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
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.
duet-agent AGENTS.md
Instructions for dzhng/duet-agent, covering agent guidelines, treat types as documentation, keep names current, keep comments useful and prefer direct, local guarantees.
binance-mcp-server copilot-instructions.md
Instructions for AnalyticAce/binance-mcp-server, covering copilot instructions - best development practices, general instructions, python development, code style & structure and python best practices.
gitea-mcp-server AGENTS.md
AGENTS.md instructions for pxsloot/gitea-mcp-server, covering agent guidelines, what we build, developer handbook and fastmcp documentation.
tabyAgent AGENTS.md
AGENTS.md instructions for gpdir16/tabyAgent, covering tabyagent 개발 및 기여 규칙, 시스템 프롬프트 and 코드 스타일.
Vulnerability-Scanning AGENTS.md
Instructions for TheSethRose/Vulnerability-Scanning, covering agents.md, project overview, setup commands, test and validation commands and code style.